SlideShare a Scribd company logo
1 of 36
Download to read offline
Sarah Finch
Oct.14th, 2020
NLP Lab
Graph-to-Text Generation
and its Applications to Dialogue
Motivation
● Downstream application: graph-oriented dialogue system
● Dialogue response generation
Motivation
● Downstream application: graph-oriented dialogue system
● Dialogue response generation
○ Response selection/expansion
■ What should be said next?
Motivation
● Downstream application: graph-oriented dialogue system
● Dialogue response generation
○ Response selection/expansion
■ What should be said next?
○ Language Generation
■ How will it be said?
Motivation
● Downstream application: graph-oriented dialogue system
● Dialogue response generation
○ Response selection/expansion
■ What should be said next?
○ Language Generation
■ How will it be said?
Language Generation Task
● Graph-to-Text paradigm
● Given: Graph containing all information that was selected to be expressed
● Goal: Produce natural language capturing all AND only that information in the
graph
Graph-to-Text Datasets
● Most approaches are
structure-agnostic
● Focus on AMR
○ most semantically and topically diverse
and complex
○ most similar to (our) desired structure
for dialogue
Abstract Meaning
Representation
Rooted graph for
semantic meaning
WebNLG KGs consisting of
triples from DBpedia
AGENDA KGs representing
scientific abstracts of
AI papers
E2E restaurant
information meaning
representations
(intents and slots)
ViGGO video game
information meaning
representations
(intents and slots)
Syntax NMT syntax trees for
machine translation
Graph-to-Text Approach Types
● Rule Based
● Statistical
● Seq to Seq
● Graph to Seq
● Pretrained Language Model
Graph-to-Text Approach Types
● Rule Based
● Statistical
● Seq to Seq
● Graph to Seq
● Pretrained Language Model
Graph-to-Text: Advancements
● Graph to Seq
○ Recurrent Neural Networks
(GGNN2Seq, GraphLSTM)
○ Graph neural networks
(GCNSEQ, DGCN, G2S-GGNN)
○ Transformer
(GTransformer, Transformer-CNN,
Transformer-SA, HetGT, LG-MixGAT)
AMR15 AMR17
Table adapted from Yao et al (2020)
Graph-to-Text: Advancements
● Graph to Seq
○ Recurrent Neural Networks
(GGNN2Seq, GraphLSTM)
○ Graph neural networks
(GCNSEQ, DGCN, G2S-GGNN)
○ Transformer
(GTransformer, Transformer-CNN,
Transformer-SA, HetGT, LG-MixGAT)
AMR15 AMR17
Table adapted from Yao et al (2020)
* only directly consider first order
neighbors
Graph-to-Text: Advancements
● Graph to Seq
○ Recurrent Neural Networks
(GGNN2Seq, GraphLSTM)
○ Graph neural networks
(GCNSEQ, DGCN, G2S-GGNN)
○ Transformer
(GTransformer, Transformer-CNN,
Transformer-SA, HetGT, LG-MixGAT)
AMR15 AMR17
Table adapted from Yao et al (2020)
* downplay edge structures,
focusing more on modeling concept
nodes
Graph-to-Text: Advancements
● Graph to Seq
○ Recurrent Neural Networks
(GGNN2Seq, GraphLSTM)
○ Graph neural networks
(GCNSEQ, DGCN, G2S-GGNN)
○ Transformer
(GTransformer, Transformer-CNN,
Transformer-SA, HetGT, LG-MixGAT)
AMR15 AMR17
Table adapted from Yao et al (2020)
HetGT
Figure from Yao et al (2020)
Graph-to-Text: Pretrained Language Models
● Pretrained Language Model (PLM)
○ Decoder
(GPT-2)
○ Encoder-Decoder
(BART, T5)
Table adapted from Ribeiro et al (2020)
HetGT
GPT-2, Rec
GPT-2, SFC
AMR17
Graph-to-Text: Pretrained Language Models
● Main idea: Finetune pretrained LM
on Graph-to-Text data
○ Decoder LM (GPT-2)
○ Encoder-Decoder LM (BART, T5)
Table adapted from Ribeiro et al (2020)
HetGT
GPT-2, Rec
GPT-2, SFC
AMR17
Graph-to-Text: Pretrained Language Models
● Main idea: Finetune pretrained LM
on Graph-to-Text data
○ Decoder LM (GPT-2)
○ Encoder-Decoder LM (BART, T5)
Table adapted from Ribeiro et al (2020)
HetGT
GPT-2, Rec
GPT-2, SFC
AMR17
* these approaches use linearized
sequence representation of graphs (no
graph encoders)!
Graph-to-Text: Pretrained Language Models
● Main idea: Finetune pretrained LM
on Graph-to-Text data
○ Decoder LM (GPT-2)
○ Encoder-Decoder LM (BART, T5)
● Rerank text candidates
Table adapted from Ribeiro et al (2020)
HetGT
GPT-2, Rec
GPT-2, SFC
AMR17
Graph-to-Text: Pretrained Language Models
● Main idea: Finetune pretrained LM
on Graph-to-Text data
○ Decoder LM (GPT-2)
○ Encoder-Decoder LM (BART, T5)
● Rerank text candidates
○ Reconstruction score
Table adapted from Ribeiro et al (2020)
HetGT
GPT-2, Rec
GPT-2, SFC
AMR17
text
model
AMR
parser
Rec.
score
0.75
Graph-to-Text: Pretrained Language Models
● Main idea: Finetune pretrained LM
on Graph-to-Text data
○ Decoder LM (GPT-2)
○ Encoder-Decoder LM (BART, T5)
● Rerank text candidates
○ Reconstruction score
○ Semantic Fidelity Classifier
Table adapted from Ribeiro et al (2020)
HetGT
GPT-2, Rec
GPT-2, SFC
AMR17
text
model
AMR
parser
Rec.
score
0.75
text
model SFC Fidelity Label
(accurate, omit, repeat, …)
How good are current systems really?
● Challenging to interpret automated metrics in grounded way
● Automated metrics (like BLEU) seem to agree with human judgements
● Missing information seems to be the most prevalent error
● Low fluency occurs with high rates of anonymization and repetition in output
Table adapted from Manning et al (2020)
Observed Shortcomings
● Omission and hallucination
● Unnatural-sounding
○ Repetition
○ Ungrammatical
● “Open-class” tokens
● Edge label encodings
○ not “real” words
Model Ideas
● Leverage both graph encoders and pretrained language model
Model Ideas
● Leverage both graph encoders and pretrained language model
GE GD
graph
text
Multi-objective
loss
perplexity
Model Ideas
● Leverage both graph encoders and pretrained language model
GE GD
graph
text
Multi-objective
loss
perplexity
GE GD
graph
text
Hierarchical
PLME PLMD
text
Model Ideas
● Leverage both graph encoders and pretrained language model
GE GD
graph
text
Multi-objective
loss
perplexity
GE GD
graph
text
Hierarchical
PLME PLMD
text
GE GD
graph linearized graph
Ensemble
PLME PLMD
text
Graph-to-Text on Dialogue Language
● More first and second person expressions, rather than third
● More collaborative language
● Dialogue utterance types
Graph-to-Text on Dialogue Language
● More first and second person expressions, rather than third
● More collaborative language
● Dialogue utterance types
● predicate statement (i like cookies)
● predicate question (what did you buy?)
Graph-to-Text on Dialogue Language
● More first and second person expressions, rather than third
● More collaborative language
● Dialogue utterance types
● predicate statement (i like cookies)
● predicate question (what did you buy?)
● clarification question (oh a brother?)
● generic agreement prefix (yeah, it was fun)
● emotional reaction prefix (that’s great, i hope you enjoyed it a lot)
● yes-answer
● no-answer
● isolated concept answer (a dog)
● single word question (why?)
Graph-to-Text on Dialogue Language
1. Silver AMR annotations of dialogue (DAMR)
2. Graph-to-Text models on DAMR
Graph-to-Text on Dialogue Language
1. Silver AMR annotations of dialogue (DAMR)
2. Graph-to-Text models on DAMR
setup limitations:
● current AMR parsers not trained on dialogue data, so silver annotations are potentially more
noisy/incomplete than standard
● still should reveal information about what the models are missing
Two Main Threads
● Explore Graph-to-Text on Dialogue ● Implement Graph-to-Text
improvements over previous work
Two Main Threads
● Explore Graph-to-Text on Dialogue
1. Collect dialogue graph structures for
evaluation
2. Collect current approaches for
Graph-to-Text
3. Apply current approaches to dialogue
(pretrained, finetuned, scratch)
4. Identify main limitations
5. Devise strategies to overcome
● Implement Graph-to-Text
improvements over previous work
Two Main Threads
● Explore Graph-to-Text on Dialogue
1. Collect dialogue graph structures for
evaluation
2. Collect current approaches for
Graph-to-Text
3. Apply current approaches to dialogue
(pretrained, finetuned, scratch)
4. Identify main limitations
5. Devise strategies to overcome
● Implement Graph-to-Text
improvements over previous work
1. Start with Language Modeling ideas
2. Incorporate strategies from #5
3. Apply to standard datasets and dialogue
References
Daniel Beck, Gholamreza Haffari, and Trevor Cohn. 2018. Graph-to-sequence learning using gated graph neural networks. In Proceedings of the 56th Annual Meeting of the Association
for Com- putational Linguistics (Volume 1: Long Papers), pages 273–283, Melbourne, Australia. Association for Computational Linguistics.
Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang, and Daniel Gildea. 2017. AMR-to-text gener- ation with synchronous node replacement grammar. In Proceedings of the 55th
Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 7–13, Vancouver, Canada. Association for Computational Linguistics.
Marco Damonte and Shay B. Cohen. 2019. Structural neural encoders for AMR-to-text generation. In Pro- ceedings of the 2019 Conference of the North Amer- ican Chapter of the
Association for Computational Linguistics: Human Language Technologies, Vol- ume 1 (Long and Short Papers), pages 3649–3658, Minneapolis, Minnesota. Association for Computa-
tional Linguistics.
Zhijiang Guo, Yan Zhang, Zhiyang Teng, and Wei Lu. 2019. Densely connected graph convolutional networks for graph-to-sequence learning. Transac- tions of the Association for
Computational Linguis- tics, 7:297–312.
Leonardo F. R. Ribeiro, Claire Gardent, and Iryna Gurevych. 2019. Enhancing AMR-to-text genera- tion with dual graph representations. In Proceed- ings of the 2019 Conference on
Empirical Methods in Natural Language Processing and the 9th Inter- national Joint Conference on Natural Language Pro- cessing (EMNLP-IJCNLP), pages 3181–3192, Hong Kong,
China. Association for Computational Lin- guistics.
Jie Zhu, Junhui Li, Muhua Zhu, Longhua Qian, Min Zhang, and Guodong Zhou. 2019. Modeling graph structure in transformer for better AMR-to-text gen- eration. In Proceedings of the
2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natu- ral Language Processing (EMNLP-IJCNLP), pages
5458–5467, Hong Kong, China. Association for Computational Linguistics.
Deng Cai and Wai Lam. 2020. Graph transformer for graph-to-sequence learning. In Proceedings of The Thirty-Fourth AAAI Conference on Artificial Intelli- gence (AAAI).
Yao, S., Wang, T. and Wan, X., 2020, July. Heterogeneous Graph Transformer for Graph-to-Sequence Learning. In Proceedings of the 58th Annual Meeting of the Association for
Computational Linguistics (pp. 7145-7154).
References
Manuel Mager, Ramo ́n Fernandez Astudillo, Tahira Naseem, Md Arafat Sultan, Young-Suk Lee, Radu Florian, and Salim Roukos. 2020. GPT-too: A language-model-first approach for
AMR-to-text gen- eration. In Proceedings of the 58th Annual Meet- ing of the Association for Computational Linguistics, pages 1846–1852, Online. Association for Computa- tional
Linguistics.
Hamza Harkous, Isabel Groves, and Amir Saffari. 2020.
Have your text and use it too! end-to-end neural data- to-text generation with semantic fidelity. arXiv e- prints.
Ribeiro, L.F., Schmitt, M., Schütze, H. and Gurevych, I., 2020. Investigating Pretrained Language Models for Graph-to-Text Generation. arXiv preprint arXiv:2007.08426.
Manning, E., Wein, S. and Schneider, N., 2020. A Human Evaluation of AMR-to-English Generation Systems. arXiv preprint arXiv:2004.06814.

More Related Content

What's hot

The DE-9IM Matrix in Details using ST_Relate: In Picture and SQL
The DE-9IM Matrix in Details using ST_Relate: In Picture and SQLThe DE-9IM Matrix in Details using ST_Relate: In Picture and SQL
The DE-9IM Matrix in Details using ST_Relate: In Picture and SQLtorp42
 
On the Semantics of Linking and Importing in Modular Ontologies
On the Semantics of Linking and Importing in Modular OntologiesOn the Semantics of Linking and Importing in Modular Ontologies
On the Semantics of Linking and Importing in Modular OntologiesJie Bao
 
A project on advanced C language
A project on advanced C languageA project on advanced C language
A project on advanced C languagesvrohith 9
 
Mit203 analysis and design of algorithms
Mit203  analysis and design of algorithmsMit203  analysis and design of algorithms
Mit203 analysis and design of algorithmssmumbahelp
 
Bytewise Approximate Match: Theory, Algorithms and Applications
Bytewise Approximate Match:  Theory, Algorithms and ApplicationsBytewise Approximate Match:  Theory, Algorithms and Applications
Bytewise Approximate Match: Theory, Algorithms and ApplicationsLiwei Ren任力偉
 
Spatial Indexing
Spatial IndexingSpatial Indexing
Spatial Indexingtorp42
 
Algorithms,graph theory and combinatorics
Algorithms,graph theory and combinatoricsAlgorithms,graph theory and combinatorics
Algorithms,graph theory and combinatoricsProf.Dr.Hanumanthappa J
 
Natural Language Generation in the Wild
Natural Language Generation in the WildNatural Language Generation in the Wild
Natural Language Generation in the WildDaniel Beck
 
Knowledg graphs yosi mass
Knowledg graphs yosi massKnowledg graphs yosi mass
Knowledg graphs yosi massdiannepatricia
 
Reference Scope Identification in Citing Sentences
Reference Scope Identification in Citing SentencesReference Scope Identification in Citing Sentences
Reference Scope Identification in Citing SentencesAkihiro Kameda
 
Dsl overview
Dsl overviewDsl overview
Dsl overviewClarkTony
 
Distributed Keyword Search over RDF via MapReduce
Distributed Keyword Search over RDF via MapReduceDistributed Keyword Search over RDF via MapReduce
Distributed Keyword Search over RDF via MapReduceAntonio Maccioni
 
Regular Expressions -- SAS and Perl
Regular Expressions -- SAS and PerlRegular Expressions -- SAS and Perl
Regular Expressions -- SAS and PerlMark Tabladillo
 
Pptphrase tagset mapping for french and english treebanks and its application...
Pptphrase tagset mapping for french and english treebanks and its application...Pptphrase tagset mapping for french and english treebanks and its application...
Pptphrase tagset mapping for french and english treebanks and its application...Lifeng (Aaron) Han
 
A New Reusability Metric for Object-Oriented Software
A New Reusability Metric for Object-Oriented SoftwareA New Reusability Metric for Object-Oriented Software
A New Reusability Metric for Object-Oriented Softwarenewreusabilitymetric
 
Data compression using python draft
Data compression using python draftData compression using python draft
Data compression using python draftAshok Govindarajan
 
SIMILARITY SEARCH FOR TRAJECTORIES OF RFID TAGS IN SUPPLY CHAIN TRAFFIC
SIMILARITY SEARCH FOR TRAJECTORIES OF RFID TAGS IN SUPPLY CHAIN TRAFFICSIMILARITY SEARCH FOR TRAJECTORIES OF RFID TAGS IN SUPPLY CHAIN TRAFFIC
SIMILARITY SEARCH FOR TRAJECTORIES OF RFID TAGS IN SUPPLY CHAIN TRAFFICijdms
 

What's hot (20)

grammer
grammergrammer
grammer
 
The DE-9IM Matrix in Details using ST_Relate: In Picture and SQL
The DE-9IM Matrix in Details using ST_Relate: In Picture and SQLThe DE-9IM Matrix in Details using ST_Relate: In Picture and SQL
The DE-9IM Matrix in Details using ST_Relate: In Picture and SQL
 
On the Semantics of Linking and Importing in Modular Ontologies
On the Semantics of Linking and Importing in Modular OntologiesOn the Semantics of Linking and Importing in Modular Ontologies
On the Semantics of Linking and Importing in Modular Ontologies
 
A project on advanced C language
A project on advanced C languageA project on advanced C language
A project on advanced C language
 
Cs 2001
Cs 2001Cs 2001
Cs 2001
 
Mit203 analysis and design of algorithms
Mit203  analysis and design of algorithmsMit203  analysis and design of algorithms
Mit203 analysis and design of algorithms
 
Bytewise Approximate Match: Theory, Algorithms and Applications
Bytewise Approximate Match:  Theory, Algorithms and ApplicationsBytewise Approximate Match:  Theory, Algorithms and Applications
Bytewise Approximate Match: Theory, Algorithms and Applications
 
Spatial Indexing
Spatial IndexingSpatial Indexing
Spatial Indexing
 
Algorithms,graph theory and combinatorics
Algorithms,graph theory and combinatoricsAlgorithms,graph theory and combinatorics
Algorithms,graph theory and combinatorics
 
Natural Language Generation in the Wild
Natural Language Generation in the WildNatural Language Generation in the Wild
Natural Language Generation in the Wild
 
COMPUTER LABORATORY-4 LAB MANUAL BE COMPUTER ENGINEERING
COMPUTER LABORATORY-4 LAB MANUAL BE COMPUTER ENGINEERINGCOMPUTER LABORATORY-4 LAB MANUAL BE COMPUTER ENGINEERING
COMPUTER LABORATORY-4 LAB MANUAL BE COMPUTER ENGINEERING
 
Knowledg graphs yosi mass
Knowledg graphs yosi massKnowledg graphs yosi mass
Knowledg graphs yosi mass
 
Reference Scope Identification in Citing Sentences
Reference Scope Identification in Citing SentencesReference Scope Identification in Citing Sentences
Reference Scope Identification in Citing Sentences
 
Dsl overview
Dsl overviewDsl overview
Dsl overview
 
Distributed Keyword Search over RDF via MapReduce
Distributed Keyword Search over RDF via MapReduceDistributed Keyword Search over RDF via MapReduce
Distributed Keyword Search over RDF via MapReduce
 
Regular Expressions -- SAS and Perl
Regular Expressions -- SAS and PerlRegular Expressions -- SAS and Perl
Regular Expressions -- SAS and Perl
 
Pptphrase tagset mapping for french and english treebanks and its application...
Pptphrase tagset mapping for french and english treebanks and its application...Pptphrase tagset mapping for french and english treebanks and its application...
Pptphrase tagset mapping for french and english treebanks and its application...
 
A New Reusability Metric for Object-Oriented Software
A New Reusability Metric for Object-Oriented SoftwareA New Reusability Metric for Object-Oriented Software
A New Reusability Metric for Object-Oriented Software
 
Data compression using python draft
Data compression using python draftData compression using python draft
Data compression using python draft
 
SIMILARITY SEARCH FOR TRAJECTORIES OF RFID TAGS IN SUPPLY CHAIN TRAFFIC
SIMILARITY SEARCH FOR TRAJECTORIES OF RFID TAGS IN SUPPLY CHAIN TRAFFICSIMILARITY SEARCH FOR TRAJECTORIES OF RFID TAGS IN SUPPLY CHAIN TRAFFIC
SIMILARITY SEARCH FOR TRAJECTORIES OF RFID TAGS IN SUPPLY CHAIN TRAFFIC
 

Similar to Graph-to-Text Generation and its Applications to Dialogue

Shedding Light on Software Engineering-specific Metaphors and Idioms
Shedding Light on Software Engineering-specific Metaphors and IdiomsShedding Light on Software Engineering-specific Metaphors and Idioms
Shedding Light on Software Engineering-specific Metaphors and IdiomsMia Mohammad Imran
 
Transformer Seq2Sqe Models: Concepts, Trends & Limitations (DLI)
Transformer Seq2Sqe Models: Concepts, Trends & Limitations (DLI)Transformer Seq2Sqe Models: Concepts, Trends & Limitations (DLI)
Transformer Seq2Sqe Models: Concepts, Trends & Limitations (DLI)Deep Learning Italia
 
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRFEnd-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRFJayavardhan Reddy Peddamail
 
cis5-204-Project-ch11c - Evan, Le, Mata.pdf
cis5-204-Project-ch11c - Evan, Le, Mata.pdfcis5-204-Project-ch11c - Evan, Le, Mata.pdf
cis5-204-Project-ch11c - Evan, Le, Mata.pdfMinhLe595264
 
Introduction to Large Language Models and the Transformer Architecture.pdf
Introduction to Large Language Models and the Transformer Architecture.pdfIntroduction to Large Language Models and the Transformer Architecture.pdf
Introduction to Large Language Models and the Transformer Architecture.pdfsudeshnakundu10
 
Integration of speech recognition with computer assisted translation
Integration of speech recognition with computer assisted translationIntegration of speech recognition with computer assisted translation
Integration of speech recognition with computer assisted translationChamani Shiranthika
 
aRangodb, un package per l'utilizzo di ArangoDB con R
aRangodb, un package per l'utilizzo di ArangoDB con RaRangodb, un package per l'utilizzo di ArangoDB con R
aRangodb, un package per l'utilizzo di ArangoDB con RGraphRM
 
Nlp 2020 global ai conf -jeff_shomaker_final
Nlp 2020 global ai conf -jeff_shomaker_finalNlp 2020 global ai conf -jeff_shomaker_final
Nlp 2020 global ai conf -jeff_shomaker_finalJeffrey Shomaker
 
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Transl...
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Transl...Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Transl...
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Transl...Jungo Kasai
 
Learning to Generate Pseudo-code from Source Code using Statistical Machine T...
Learning to Generate Pseudo-code from Source Code using Statistical Machine T...Learning to Generate Pseudo-code from Source Code using Statistical Machine T...
Learning to Generate Pseudo-code from Source Code using Statistical Machine T...Yusuke Oda
 
Semantics2018 Zhang,Petrak,Maynard: Adapted TextRank for Term Extraction: A G...
Semantics2018 Zhang,Petrak,Maynard: Adapted TextRank for Term Extraction: A G...Semantics2018 Zhang,Petrak,Maynard: Adapted TextRank for Term Extraction: A G...
Semantics2018 Zhang,Petrak,Maynard: Adapted TextRank for Term Extraction: A G...Johann Petrak
 
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty DialogueTransformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty DialogueJinho Choi
 
Script identification using dct coefficients 2
Script identification using dct coefficients 2Script identification using dct coefficients 2
Script identification using dct coefficients 2IAEME Publication
 
Two Level Disambiguation Model for Query Translation
Two Level Disambiguation Model for Query TranslationTwo Level Disambiguation Model for Query Translation
Two Level Disambiguation Model for Query TranslationIJECEIAES
 
Compiler gate question key
Compiler gate question keyCompiler gate question key
Compiler gate question keyArthyR3
 
Speech To Speech Translation
Speech To Speech TranslationSpeech To Speech Translation
Speech To Speech TranslationIRJET Journal
 
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...Vimukthi Wickramasinghe
 

Similar to Graph-to-Text Generation and its Applications to Dialogue (20)

The NLP Muppets revolution!
The NLP Muppets revolution!The NLP Muppets revolution!
The NLP Muppets revolution!
 
Shedding Light on Software Engineering-specific Metaphors and Idioms
Shedding Light on Software Engineering-specific Metaphors and IdiomsShedding Light on Software Engineering-specific Metaphors and Idioms
Shedding Light on Software Engineering-specific Metaphors and Idioms
 
Transformer Seq2Sqe Models: Concepts, Trends & Limitations (DLI)
Transformer Seq2Sqe Models: Concepts, Trends & Limitations (DLI)Transformer Seq2Sqe Models: Concepts, Trends & Limitations (DLI)
Transformer Seq2Sqe Models: Concepts, Trends & Limitations (DLI)
 
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRFEnd-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
 
CIS 5 Project.pdf
CIS 5 Project.pdfCIS 5 Project.pdf
CIS 5 Project.pdf
 
cis5-204-Project-ch11c - Evan, Le, Mata.pdf
cis5-204-Project-ch11c - Evan, Le, Mata.pdfcis5-204-Project-ch11c - Evan, Le, Mata.pdf
cis5-204-Project-ch11c - Evan, Le, Mata.pdf
 
N20181217
N20181217N20181217
N20181217
 
Introduction to Large Language Models and the Transformer Architecture.pdf
Introduction to Large Language Models and the Transformer Architecture.pdfIntroduction to Large Language Models and the Transformer Architecture.pdf
Introduction to Large Language Models and the Transformer Architecture.pdf
 
Integration of speech recognition with computer assisted translation
Integration of speech recognition with computer assisted translationIntegration of speech recognition with computer assisted translation
Integration of speech recognition with computer assisted translation
 
aRangodb, un package per l'utilizzo di ArangoDB con R
aRangodb, un package per l'utilizzo di ArangoDB con RaRangodb, un package per l'utilizzo di ArangoDB con R
aRangodb, un package per l'utilizzo di ArangoDB con R
 
Nlp 2020 global ai conf -jeff_shomaker_final
Nlp 2020 global ai conf -jeff_shomaker_finalNlp 2020 global ai conf -jeff_shomaker_final
Nlp 2020 global ai conf -jeff_shomaker_final
 
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Transl...
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Transl...Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Transl...
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Transl...
 
Learning to Generate Pseudo-code from Source Code using Statistical Machine T...
Learning to Generate Pseudo-code from Source Code using Statistical Machine T...Learning to Generate Pseudo-code from Source Code using Statistical Machine T...
Learning to Generate Pseudo-code from Source Code using Statistical Machine T...
 
Semantics2018 Zhang,Petrak,Maynard: Adapted TextRank for Term Extraction: A G...
Semantics2018 Zhang,Petrak,Maynard: Adapted TextRank for Term Extraction: A G...Semantics2018 Zhang,Petrak,Maynard: Adapted TextRank for Term Extraction: A G...
Semantics2018 Zhang,Petrak,Maynard: Adapted TextRank for Term Extraction: A G...
 
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty DialogueTransformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
 
Script identification using dct coefficients 2
Script identification using dct coefficients 2Script identification using dct coefficients 2
Script identification using dct coefficients 2
 
Two Level Disambiguation Model for Query Translation
Two Level Disambiguation Model for Query TranslationTwo Level Disambiguation Model for Query Translation
Two Level Disambiguation Model for Query Translation
 
Compiler gate question key
Compiler gate question keyCompiler gate question key
Compiler gate question key
 
Speech To Speech Translation
Speech To Speech TranslationSpeech To Speech Translation
Speech To Speech Translation
 
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
 

More from Jinho Choi

Analysis of Hierarchical Multi-Content Text Classification Model on B-SHARP D...
Analysis of Hierarchical Multi-Content Text Classification Model on B-SHARP D...Analysis of Hierarchical Multi-Content Text Classification Model on B-SHARP D...
Analysis of Hierarchical Multi-Content Text Classification Model on B-SHARP D...Jinho Choi
 
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-b...
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-b...Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-b...
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-b...Jinho Choi
 
The Myth of Higher-Order Inference in Coreference Resolution
The Myth of Higher-Order Inference in Coreference ResolutionThe Myth of Higher-Order Inference in Coreference Resolution
The Myth of Higher-Order Inference in Coreference ResolutionJinho Choi
 
Noise Pollution in Hospital Readmission Prediction: Long Document Classificat...
Noise Pollution in Hospital Readmission Prediction: Long Document Classificat...Noise Pollution in Hospital Readmission Prediction: Long Document Classificat...
Noise Pollution in Hospital Readmission Prediction: Long Document Classificat...Jinho Choi
 
Abstract Meaning Representation
Abstract Meaning RepresentationAbstract Meaning Representation
Abstract Meaning RepresentationJinho Choi
 
Semantic Role Labeling
Semantic Role LabelingSemantic Role Labeling
Semantic Role LabelingJinho Choi
 
CS329 - WordNet Similarities
CS329 - WordNet SimilaritiesCS329 - WordNet Similarities
CS329 - WordNet SimilaritiesJinho Choi
 
CS329 - Lexical Relations
CS329 - Lexical RelationsCS329 - Lexical Relations
CS329 - Lexical RelationsJinho Choi
 
Automatic Knowledge Base Expansion for Dialogue Management
Automatic Knowledge Base Expansion for Dialogue ManagementAutomatic Knowledge Base Expansion for Dialogue Management
Automatic Knowledge Base Expansion for Dialogue ManagementJinho Choi
 
Attention is All You Need for AMR Parsing
Attention is All You Need for AMR ParsingAttention is All You Need for AMR Parsing
Attention is All You Need for AMR ParsingJinho Choi
 
Real-time Coreference Resolution for Dialogue Understanding
Real-time Coreference Resolution for Dialogue UnderstandingReal-time Coreference Resolution for Dialogue Understanding
Real-time Coreference Resolution for Dialogue UnderstandingJinho Choi
 
Topological Sort
Topological SortTopological Sort
Topological SortJinho Choi
 
Multi-modal Embedding Learning for Early Detection of Alzheimer's Disease
Multi-modal Embedding Learning for Early Detection of Alzheimer's DiseaseMulti-modal Embedding Learning for Early Detection of Alzheimer's Disease
Multi-modal Embedding Learning for Early Detection of Alzheimer's DiseaseJinho Choi
 
Building Widely-Interpretable Semantic Networks for Dialogue Contexts
Building Widely-Interpretable Semantic Networks for Dialogue ContextsBuilding Widely-Interpretable Semantic Networks for Dialogue Contexts
Building Widely-Interpretable Semantic Networks for Dialogue ContextsJinho Choi
 
How to make Emora talk about Sports Intelligently
How to make Emora talk about Sports IntelligentlyHow to make Emora talk about Sports Intelligently
How to make Emora talk about Sports IntelligentlyJinho Choi
 
Text-to-SQL with Data-Driven Templates
Text-to-SQL with Data-Driven TemplatesText-to-SQL with Data-Driven Templates
Text-to-SQL with Data-Driven TemplatesJinho Choi
 
Resume Classification with Term Attention Embeddings
Resume Classification with Term Attention EmbeddingsResume Classification with Term Attention Embeddings
Resume Classification with Term Attention EmbeddingsJinho Choi
 
[DSA-Java] Heap Sort
[DSA-Java] Heap Sort[DSA-Java] Heap Sort
[DSA-Java] Heap SortJinho Choi
 

More from Jinho Choi (20)

Analysis of Hierarchical Multi-Content Text Classification Model on B-SHARP D...
Analysis of Hierarchical Multi-Content Text Classification Model on B-SHARP D...Analysis of Hierarchical Multi-Content Text Classification Model on B-SHARP D...
Analysis of Hierarchical Multi-Content Text Classification Model on B-SHARP D...
 
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-b...
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-b...Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-b...
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-b...
 
The Myth of Higher-Order Inference in Coreference Resolution
The Myth of Higher-Order Inference in Coreference ResolutionThe Myth of Higher-Order Inference in Coreference Resolution
The Myth of Higher-Order Inference in Coreference Resolution
 
Noise Pollution in Hospital Readmission Prediction: Long Document Classificat...
Noise Pollution in Hospital Readmission Prediction: Long Document Classificat...Noise Pollution in Hospital Readmission Prediction: Long Document Classificat...
Noise Pollution in Hospital Readmission Prediction: Long Document Classificat...
 
Abstract Meaning Representation
Abstract Meaning RepresentationAbstract Meaning Representation
Abstract Meaning Representation
 
Semantic Role Labeling
Semantic Role LabelingSemantic Role Labeling
Semantic Role Labeling
 
CKY Parsing
CKY ParsingCKY Parsing
CKY Parsing
 
CS329 - WordNet Similarities
CS329 - WordNet SimilaritiesCS329 - WordNet Similarities
CS329 - WordNet Similarities
 
CS329 - Lexical Relations
CS329 - Lexical RelationsCS329 - Lexical Relations
CS329 - Lexical Relations
 
Automatic Knowledge Base Expansion for Dialogue Management
Automatic Knowledge Base Expansion for Dialogue ManagementAutomatic Knowledge Base Expansion for Dialogue Management
Automatic Knowledge Base Expansion for Dialogue Management
 
Attention is All You Need for AMR Parsing
Attention is All You Need for AMR ParsingAttention is All You Need for AMR Parsing
Attention is All You Need for AMR Parsing
 
Real-time Coreference Resolution for Dialogue Understanding
Real-time Coreference Resolution for Dialogue UnderstandingReal-time Coreference Resolution for Dialogue Understanding
Real-time Coreference Resolution for Dialogue Understanding
 
Topological Sort
Topological SortTopological Sort
Topological Sort
 
Tries - Put
Tries - PutTries - Put
Tries - Put
 
Multi-modal Embedding Learning for Early Detection of Alzheimer's Disease
Multi-modal Embedding Learning for Early Detection of Alzheimer's DiseaseMulti-modal Embedding Learning for Early Detection of Alzheimer's Disease
Multi-modal Embedding Learning for Early Detection of Alzheimer's Disease
 
Building Widely-Interpretable Semantic Networks for Dialogue Contexts
Building Widely-Interpretable Semantic Networks for Dialogue ContextsBuilding Widely-Interpretable Semantic Networks for Dialogue Contexts
Building Widely-Interpretable Semantic Networks for Dialogue Contexts
 
How to make Emora talk about Sports Intelligently
How to make Emora talk about Sports IntelligentlyHow to make Emora talk about Sports Intelligently
How to make Emora talk about Sports Intelligently
 
Text-to-SQL with Data-Driven Templates
Text-to-SQL with Data-Driven TemplatesText-to-SQL with Data-Driven Templates
Text-to-SQL with Data-Driven Templates
 
Resume Classification with Term Attention Embeddings
Resume Classification with Term Attention EmbeddingsResume Classification with Term Attention Embeddings
Resume Classification with Term Attention Embeddings
 
[DSA-Java] Heap Sort
[DSA-Java] Heap Sort[DSA-Java] Heap Sort
[DSA-Java] Heap Sort
 

Recently uploaded

AI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by AnitarajAI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by AnitarajAnitaRaj43
 
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...WSO2
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDropbox
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Victor Rentea
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Victor Rentea
 
Stronger Together: Developing an Organizational Strategy for Accessible Desig...
Stronger Together: Developing an Organizational Strategy for Accessible Desig...Stronger Together: Developing an Organizational Strategy for Accessible Desig...
Stronger Together: Developing an Organizational Strategy for Accessible Desig...caitlingebhard1
 
Decarbonising Commercial Real Estate: The Role of Operational Performance
Decarbonising Commercial Real Estate: The Role of Operational PerformanceDecarbonising Commercial Real Estate: The Role of Operational Performance
Decarbonising Commercial Real Estate: The Role of Operational PerformanceIES VE
 
Quantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation ComputingQuantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation ComputingWSO2
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelDeepika Singh
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontologyjohnbeverley2021
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityWSO2
 
Modernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using BallerinaModernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using BallerinaWSO2
 

Recently uploaded (20)

AI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by AnitarajAI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by Anitaraj
 
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
WSO2 Micro Integrator for Enterprise Integration in a Decentralized, Microser...
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering Developers
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
Stronger Together: Developing an Organizational Strategy for Accessible Desig...
Stronger Together: Developing an Organizational Strategy for Accessible Desig...Stronger Together: Developing an Organizational Strategy for Accessible Desig...
Stronger Together: Developing an Organizational Strategy for Accessible Desig...
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Decarbonising Commercial Real Estate: The Role of Operational Performance
Decarbonising Commercial Real Estate: The Role of Operational PerformanceDecarbonising Commercial Real Estate: The Role of Operational Performance
Decarbonising Commercial Real Estate: The Role of Operational Performance
 
Quantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation ComputingQuantum Leap in Next-Generation Computing
Quantum Leap in Next-Generation Computing
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
Modernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using BallerinaModernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using Ballerina
 

Graph-to-Text Generation and its Applications to Dialogue

  • 1. Sarah Finch Oct.14th, 2020 NLP Lab Graph-to-Text Generation and its Applications to Dialogue
  • 2. Motivation ● Downstream application: graph-oriented dialogue system ● Dialogue response generation
  • 3. Motivation ● Downstream application: graph-oriented dialogue system ● Dialogue response generation ○ Response selection/expansion ■ What should be said next?
  • 4. Motivation ● Downstream application: graph-oriented dialogue system ● Dialogue response generation ○ Response selection/expansion ■ What should be said next? ○ Language Generation ■ How will it be said?
  • 5. Motivation ● Downstream application: graph-oriented dialogue system ● Dialogue response generation ○ Response selection/expansion ■ What should be said next? ○ Language Generation ■ How will it be said?
  • 6. Language Generation Task ● Graph-to-Text paradigm ● Given: Graph containing all information that was selected to be expressed ● Goal: Produce natural language capturing all AND only that information in the graph
  • 7. Graph-to-Text Datasets ● Most approaches are structure-agnostic ● Focus on AMR ○ most semantically and topically diverse and complex ○ most similar to (our) desired structure for dialogue Abstract Meaning Representation Rooted graph for semantic meaning WebNLG KGs consisting of triples from DBpedia AGENDA KGs representing scientific abstracts of AI papers E2E restaurant information meaning representations (intents and slots) ViGGO video game information meaning representations (intents and slots) Syntax NMT syntax trees for machine translation
  • 8. Graph-to-Text Approach Types ● Rule Based ● Statistical ● Seq to Seq ● Graph to Seq ● Pretrained Language Model
  • 9. Graph-to-Text Approach Types ● Rule Based ● Statistical ● Seq to Seq ● Graph to Seq ● Pretrained Language Model
  • 10. Graph-to-Text: Advancements ● Graph to Seq ○ Recurrent Neural Networks (GGNN2Seq, GraphLSTM) ○ Graph neural networks (GCNSEQ, DGCN, G2S-GGNN) ○ Transformer (GTransformer, Transformer-CNN, Transformer-SA, HetGT, LG-MixGAT) AMR15 AMR17 Table adapted from Yao et al (2020)
  • 11. Graph-to-Text: Advancements ● Graph to Seq ○ Recurrent Neural Networks (GGNN2Seq, GraphLSTM) ○ Graph neural networks (GCNSEQ, DGCN, G2S-GGNN) ○ Transformer (GTransformer, Transformer-CNN, Transformer-SA, HetGT, LG-MixGAT) AMR15 AMR17 Table adapted from Yao et al (2020) * only directly consider first order neighbors
  • 12. Graph-to-Text: Advancements ● Graph to Seq ○ Recurrent Neural Networks (GGNN2Seq, GraphLSTM) ○ Graph neural networks (GCNSEQ, DGCN, G2S-GGNN) ○ Transformer (GTransformer, Transformer-CNN, Transformer-SA, HetGT, LG-MixGAT) AMR15 AMR17 Table adapted from Yao et al (2020) * downplay edge structures, focusing more on modeling concept nodes
  • 13. Graph-to-Text: Advancements ● Graph to Seq ○ Recurrent Neural Networks (GGNN2Seq, GraphLSTM) ○ Graph neural networks (GCNSEQ, DGCN, G2S-GGNN) ○ Transformer (GTransformer, Transformer-CNN, Transformer-SA, HetGT, LG-MixGAT) AMR15 AMR17 Table adapted from Yao et al (2020)
  • 14. HetGT Figure from Yao et al (2020)
  • 15. Graph-to-Text: Pretrained Language Models ● Pretrained Language Model (PLM) ○ Decoder (GPT-2) ○ Encoder-Decoder (BART, T5) Table adapted from Ribeiro et al (2020) HetGT GPT-2, Rec GPT-2, SFC AMR17
  • 16. Graph-to-Text: Pretrained Language Models ● Main idea: Finetune pretrained LM on Graph-to-Text data ○ Decoder LM (GPT-2) ○ Encoder-Decoder LM (BART, T5) Table adapted from Ribeiro et al (2020) HetGT GPT-2, Rec GPT-2, SFC AMR17
  • 17. Graph-to-Text: Pretrained Language Models ● Main idea: Finetune pretrained LM on Graph-to-Text data ○ Decoder LM (GPT-2) ○ Encoder-Decoder LM (BART, T5) Table adapted from Ribeiro et al (2020) HetGT GPT-2, Rec GPT-2, SFC AMR17 * these approaches use linearized sequence representation of graphs (no graph encoders)!
  • 18. Graph-to-Text: Pretrained Language Models ● Main idea: Finetune pretrained LM on Graph-to-Text data ○ Decoder LM (GPT-2) ○ Encoder-Decoder LM (BART, T5) ● Rerank text candidates Table adapted from Ribeiro et al (2020) HetGT GPT-2, Rec GPT-2, SFC AMR17
  • 19. Graph-to-Text: Pretrained Language Models ● Main idea: Finetune pretrained LM on Graph-to-Text data ○ Decoder LM (GPT-2) ○ Encoder-Decoder LM (BART, T5) ● Rerank text candidates ○ Reconstruction score Table adapted from Ribeiro et al (2020) HetGT GPT-2, Rec GPT-2, SFC AMR17 text model AMR parser Rec. score 0.75
  • 20. Graph-to-Text: Pretrained Language Models ● Main idea: Finetune pretrained LM on Graph-to-Text data ○ Decoder LM (GPT-2) ○ Encoder-Decoder LM (BART, T5) ● Rerank text candidates ○ Reconstruction score ○ Semantic Fidelity Classifier Table adapted from Ribeiro et al (2020) HetGT GPT-2, Rec GPT-2, SFC AMR17 text model AMR parser Rec. score 0.75 text model SFC Fidelity Label (accurate, omit, repeat, …)
  • 21. How good are current systems really? ● Challenging to interpret automated metrics in grounded way ● Automated metrics (like BLEU) seem to agree with human judgements ● Missing information seems to be the most prevalent error ● Low fluency occurs with high rates of anonymization and repetition in output Table adapted from Manning et al (2020)
  • 22. Observed Shortcomings ● Omission and hallucination ● Unnatural-sounding ○ Repetition ○ Ungrammatical ● “Open-class” tokens ● Edge label encodings ○ not “real” words
  • 23. Model Ideas ● Leverage both graph encoders and pretrained language model
  • 24. Model Ideas ● Leverage both graph encoders and pretrained language model GE GD graph text Multi-objective loss perplexity
  • 25. Model Ideas ● Leverage both graph encoders and pretrained language model GE GD graph text Multi-objective loss perplexity GE GD graph text Hierarchical PLME PLMD text
  • 26. Model Ideas ● Leverage both graph encoders and pretrained language model GE GD graph text Multi-objective loss perplexity GE GD graph text Hierarchical PLME PLMD text GE GD graph linearized graph Ensemble PLME PLMD text
  • 27. Graph-to-Text on Dialogue Language ● More first and second person expressions, rather than third ● More collaborative language ● Dialogue utterance types
  • 28. Graph-to-Text on Dialogue Language ● More first and second person expressions, rather than third ● More collaborative language ● Dialogue utterance types ● predicate statement (i like cookies) ● predicate question (what did you buy?)
  • 29. Graph-to-Text on Dialogue Language ● More first and second person expressions, rather than third ● More collaborative language ● Dialogue utterance types ● predicate statement (i like cookies) ● predicate question (what did you buy?) ● clarification question (oh a brother?) ● generic agreement prefix (yeah, it was fun) ● emotional reaction prefix (that’s great, i hope you enjoyed it a lot) ● yes-answer ● no-answer ● isolated concept answer (a dog) ● single word question (why?)
  • 30. Graph-to-Text on Dialogue Language 1. Silver AMR annotations of dialogue (DAMR) 2. Graph-to-Text models on DAMR
  • 31. Graph-to-Text on Dialogue Language 1. Silver AMR annotations of dialogue (DAMR) 2. Graph-to-Text models on DAMR setup limitations: ● current AMR parsers not trained on dialogue data, so silver annotations are potentially more noisy/incomplete than standard ● still should reveal information about what the models are missing
  • 32. Two Main Threads ● Explore Graph-to-Text on Dialogue ● Implement Graph-to-Text improvements over previous work
  • 33. Two Main Threads ● Explore Graph-to-Text on Dialogue 1. Collect dialogue graph structures for evaluation 2. Collect current approaches for Graph-to-Text 3. Apply current approaches to dialogue (pretrained, finetuned, scratch) 4. Identify main limitations 5. Devise strategies to overcome ● Implement Graph-to-Text improvements over previous work
  • 34. Two Main Threads ● Explore Graph-to-Text on Dialogue 1. Collect dialogue graph structures for evaluation 2. Collect current approaches for Graph-to-Text 3. Apply current approaches to dialogue (pretrained, finetuned, scratch) 4. Identify main limitations 5. Devise strategies to overcome ● Implement Graph-to-Text improvements over previous work 1. Start with Language Modeling ideas 2. Incorporate strategies from #5 3. Apply to standard datasets and dialogue
  • 35. References Daniel Beck, Gholamreza Haffari, and Trevor Cohn. 2018. Graph-to-sequence learning using gated graph neural networks. In Proceedings of the 56th Annual Meeting of the Association for Com- putational Linguistics (Volume 1: Long Papers), pages 273–283, Melbourne, Australia. Association for Computational Linguistics. Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang, and Daniel Gildea. 2017. AMR-to-text gener- ation with synchronous node replacement grammar. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 7–13, Vancouver, Canada. Association for Computational Linguistics. Marco Damonte and Shay B. Cohen. 2019. Structural neural encoders for AMR-to-text generation. In Pro- ceedings of the 2019 Conference of the North Amer- ican Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol- ume 1 (Long and Short Papers), pages 3649–3658, Minneapolis, Minnesota. Association for Computa- tional Linguistics. Zhijiang Guo, Yan Zhang, Zhiyang Teng, and Wei Lu. 2019. Densely connected graph convolutional networks for graph-to-sequence learning. Transac- tions of the Association for Computational Linguis- tics, 7:297–312. Leonardo F. R. Ribeiro, Claire Gardent, and Iryna Gurevych. 2019. Enhancing AMR-to-text genera- tion with dual graph representations. In Proceed- ings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th Inter- national Joint Conference on Natural Language Pro- cessing (EMNLP-IJCNLP), pages 3181–3192, Hong Kong, China. Association for Computational Lin- guistics. Jie Zhu, Junhui Li, Muhua Zhu, Longhua Qian, Min Zhang, and Guodong Zhou. 2019. Modeling graph structure in transformer for better AMR-to-text gen- eration. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natu- ral Language Processing (EMNLP-IJCNLP), pages 5458–5467, Hong Kong, China. Association for Computational Linguistics. Deng Cai and Wai Lam. 2020. Graph transformer for graph-to-sequence learning. In Proceedings of The Thirty-Fourth AAAI Conference on Artificial Intelli- gence (AAAI). Yao, S., Wang, T. and Wan, X., 2020, July. Heterogeneous Graph Transformer for Graph-to-Sequence Learning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 7145-7154).
  • 36. References Manuel Mager, Ramo ́n Fernandez Astudillo, Tahira Naseem, Md Arafat Sultan, Young-Suk Lee, Radu Florian, and Salim Roukos. 2020. GPT-too: A language-model-first approach for AMR-to-text gen- eration. In Proceedings of the 58th Annual Meet- ing of the Association for Computational Linguistics, pages 1846–1852, Online. Association for Computa- tional Linguistics. Hamza Harkous, Isabel Groves, and Amir Saffari. 2020. Have your text and use it too! end-to-end neural data- to-text generation with semantic fidelity. arXiv e- prints. Ribeiro, L.F., Schmitt, M., Schütze, H. and Gurevych, I., 2020. Investigating Pretrained Language Models for Graph-to-Text Generation. arXiv preprint arXiv:2007.08426. Manning, E., Wein, S. and Schneider, N., 2020. A Human Evaluation of AMR-to-English Generation Systems. arXiv preprint arXiv:2004.06814.