SlideShare a Scribd company logo
1 of 24
Download to read offline
Training a Natural Language Generator From
Unaligned Data
PHILIP ARTHUR
MT STUDY GROUP
9/3/2015 1
Paper Description
Title: Training a Natural Language Generator From Unaligned Data
Author: Ondrej Dusek and Filip Jurcicek
Meeting: ACL
Year: 2015
Type: Long Paper
Reference: https://aclweb.org/anthology/P/P15/P15-1044.pdf
9/3/2015 2
Natural Language Generation
• Generating a natural language from abstract representation.
9/3/2015 3
Motivation & Contribution
• Motivation
• Current NLG system requires separate training data alignment step.
• Using CFG or phrase based limit the ability to capture long-range syntactic dependencies.
• Contribution
• Novel method that integrates alignment step into sentence planner.
• Using deep-syntactic trees with rule based surface realization.
• Ability to learn from incomplete tree.
9/3/2015 4
System Overview
9/3/2015 5
Main contribution
About the data structure
• Each node has a lemma and formeme. (Dušek et al., 2012)
• Contain nodes for content words (nouns, full verbs, adjectives, adverbs) and coordinating
conjunctions.
• Treex toolkit is used to generate this dependency tree for the input.
9/3/2015 6
Dataset
• BAGEL: dataset of restaurant, consists of Dialogue Acts (DA) & list of slot-value pairs (SVPs),
contains information about restaurants.
• Where: http://farm2.user.srcf.net/research/bagel/ACL10-inform-training.txt
• Example:
9/3/2015 7
FULL_DA = inform(name="Green Man",eattype=restaurant)
ABSTRACT_DA = inform(name="X1",eattype=restaurant)
-> "[name+X]X []is a [eattype+restaurant]restaurant.";
Sentence Planner
• Building a deep syntactic tree based on A* search. (2 Hypotheses: Open + Closed)
• Based on: Candidate Generator + Scorer/Ranker
9/3/2015 8
Sentence Planner Algorithm
Init: Start from an open set with a single empty sentence plan tree and an empty closed set.
Loop:
1. Select the best-scoring candidate C from the open set. Add C to closed set.
2. The candidate generator generates C, a set of possible successors to C. These are trees that
have more nodes than C and are deemed viable. Note that C may be empty.
3. The scorer scores all successors in C and if they are not already in the closed set, it adds
them to the open set.
4. Check if the best successor in the open set scores better than the best candidate in the
closed set.
Stop: The algorithm finishes if the top score in the open set is lower than the top score in the
closed set for d consecutive iterations, or if there are no more candidates in the open set. It
returns the best-scoring candidate from both sets.
9/3/2015 9
Candidate Generator
• Adding one new node in all possible positions with all possible lemmas and formemes.
9/3/2015 10
CG + Expansion Filtering
1. Lemma-formeme compatibility: nodes with combination of lemma + formeme in Training.
2. Syntatic vialibility: new node generated compatible with parent (seen before, including
dependency of left and right child).
3. Number of children: For particular parent node, #child can’t exceed the max #child of same
node in Training.
4. Tree Size: #nodes in tree can’t exceed the max #nodes of tree in training data. For each level.
5. Weak semantic compatibility: Include node that appears in training, containing SVPs from
the current input.
6. Strong semantic compatibility: For each lemma + formeme, there is a compatibility list.
Node generation is allowed if all of SVPs are present in the current input DA.
9/3/2015 11
Scorer / Ranker
• Is a function that maps global features from sentence plan 𝑡 + input 𝑚 to a real value.
• Based on basic perceptron scorer:
9/3/2015 12
Training
Objective:
Init: all 𝑤 ∈ 𝐰 = 1
For each input MR in Training:
1. 𝑡𝑡𝑜𝑝 = Generate a sentence plan of the input based on current weight.
2. 𝑡 𝑔𝑜𝑙𝑑 = Parsed input by using automatic annotator (treex).
3. Update:
9/3/2015 13
Differing Subtrees Update
• Starting from the common subtree 𝑡 𝑐 of 𝑡𝑡𝑜𝑝and 𝑡 𝑔𝑜𝑙𝑑, pairs of differing subtrees 𝑡𝑡𝑜𝑝
𝑖
, 𝑡 𝑔𝑜𝑙𝑑
𝑖
are
created by gradually adding nodes from 𝑡𝑡𝑜𝑝into 𝑡𝑡𝑜𝑝
𝑖
and from 𝑡 𝑔𝑜𝑙𝑑 into 𝑡 𝑔𝑜𝑙𝑑
𝑖
.
9/3/2015 14
Algorithm Differing Subtree Update
• In the third step of training, substitute “full-tree” update with “” update:
• It is reported that if we don’t use the same size of subtree, performance will degrade.
9/3/2015 15
Future Promise Estimation
• The same idea of A* search where score = scorer(input, weight) + heuristic(input).
• Based on Expected number of children 𝐸𝑐(𝑛) of different node types.
• The future promise (fp) of a particular sentence plan 𝑡 is calculated based on its node 𝑛1 … 𝑛 𝑡:
• 𝑐(𝑛𝑖) is the current number of children.
• 𝜆 is a preset parameter.
• Not included in stop criterion check.
9/3/2015 16
Averaging Weight + Parallel Training
• Using Iterative mixing approrach (McDonald et al. 2010).
• Training data are splitted into several parts.
• Weights updated are averaged after each pass through the training data.
• Record weights after each training pass, take an average at the end  Final weight.
9/3/2015 17
Surface Realizer
• Built using Treex NLP toolkit (Ptacek, 2008).
• Rule based simple pipeline, outlining:
1. Agreement
2. Word Ordering
3. Compound verb forms
4. Grammatical words
5. Punctuation
6. Word Inflection
7. Phonetic Changes
• Round trip test using automatic analysis with subsequent generation reached 89.79% BLEU.
9/3/2015 18
Features
• current tree properties: depth, #nodes, #repeated_nodes
• tree and input DA: #nodes/SVP, #repeated_nodes/SVP
• node features: lemma, formeme, #children of all nodes in the current tree.
• input features: whole SVPs (slot+value), just slots, and pairs of slots in the DA
• combinations of node and input features
• repeat features: #repeated_lemma_formeme with #repeated_slots in the input DA.
• dependency features: parent-child pairs for lemmas + formeme, including left or right.
• sibling features: sibling pairs for lemmas + formeme, combined with SVP.
• bigram features: pairs of lemmas + formeme adjacent in tree left-right order, combined with
SVP.
9/3/2015 19
Setup
• #iterations do not improve:
• Training = 3
• Testing = 4
• Maximum 200 sentence planner iterations per input DA.
• 𝛼 = 0.1
• If fp is used then 𝛼 = 0.3
• 10 folds cross validation is used in the experiment.
9/3/2015 20
Results
• The Proposed method gives improvement on both BLEU and NIST with whole training portion.
• Compare to the previous work (67%) is still lower.  Task is harder, no alignment is used.
• Larger training data can demonstrate the effectiveness of the proposed method.
• Both improvement gain a 95% confidence of statistical significance testing (Koehn, 2004).
9/3/2015 21
Example of Generated pairs
9/3/2015 22
Discussion
+ Generator learns to produce meaningful utterances that correspond well to the input DA.
- Not all required information is always present.
- Some facts are sometimes repeated or irrelevant information Appears
◦ Occurs because of the data sparsity.
◦ Design a scorer features that discourage conflicting information.
- Repeated slots in input are not handled correctly.
9/3/2015 23
Conclusion
• The paper presented a NLG, capable of learning from unaligned pairs.
• The contribution consists of A* based sentence planner, rule-based surface realization from
Treex toolkit.
• The empiric results shows a promising result, although didn’t surpass the previous work, but
their work is substantially harder.
• Code: https://github.com/UFAL-DSG/tgen
9/3/2015 24

More Related Content

What's hot

Lecture 6: Ensemble Methods
Lecture 6: Ensemble Methods Lecture 6: Ensemble Methods
Lecture 6: Ensemble Methods Marina Santini
 
ensemble learning
ensemble learningensemble learning
ensemble learningbutest
 
Semi supervised learning machine learning made simple
Semi supervised learning  machine learning made simpleSemi supervised learning  machine learning made simple
Semi supervised learning machine learning made simpleDevansh16
 
Machine Learning and Data Mining: 16 Classifiers Ensembles
Machine Learning and Data Mining: 16 Classifiers EnsemblesMachine Learning and Data Mining: 16 Classifiers Ensembles
Machine Learning and Data Mining: 16 Classifiers EnsemblesPier Luca Lanzi
 
Teaching calculus with Wolfram Alpha
Teaching calculus with Wolfram AlphaTeaching calculus with Wolfram Alpha
Teaching calculus with Wolfram AlphaMarta Padilla
 
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...NAVER Engineering
 
H2O World - Ensembles with Erin LeDell
H2O World - Ensembles with Erin LeDellH2O World - Ensembles with Erin LeDell
H2O World - Ensembles with Erin LeDellSri Ambati
 
Ensemble Learning Featuring the Netflix Prize Competition and ...
Ensemble Learning Featuring the Netflix Prize Competition and ...Ensemble Learning Featuring the Netflix Prize Competition and ...
Ensemble Learning Featuring the Netflix Prize Competition and ...butest
 
Semi-supervised Learning
Semi-supervised LearningSemi-supervised Learning
Semi-supervised Learningbutest
 
(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised Learning(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised LearningYamato OKAMOTO
 
Lecture 9: Machine Learning in Practice (2)
Lecture 9: Machine Learning in Practice (2)Lecture 9: Machine Learning in Practice (2)
Lecture 9: Machine Learning in Practice (2)Marina Santini
 
Instance based learning
Instance based learningInstance based learning
Instance based learningSlideshare
 
BigML Education - Feature Engineering with Flatline
BigML Education - Feature Engineering with FlatlineBigML Education - Feature Engineering with Flatline
BigML Education - Feature Engineering with FlatlineBigML, Inc
 
Lecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
Lecture 3: Basic Concepts of Machine Learning - Induction & EvaluationLecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
Lecture 3: Basic Concepts of Machine Learning - Induction & EvaluationMarina Santini
 
Boosting Algorithms Omar Odibat
Boosting Algorithms Omar Odibat Boosting Algorithms Omar Odibat
Boosting Algorithms Omar Odibat omarodibat
 
Learning loss for active learning
Learning loss for active learningLearning loss for active learning
Learning loss for active learningNAVER Engineering
 
Feature Importance Analysis with XGBoost in Tax audit
Feature Importance Analysis with XGBoost in Tax auditFeature Importance Analysis with XGBoost in Tax audit
Feature Importance Analysis with XGBoost in Tax auditMichael BENESTY
 
Linear Regression Ex
Linear Regression ExLinear Regression Ex
Linear Regression Exmailund
 

What's hot (20)

Lecture 6: Ensemble Methods
Lecture 6: Ensemble Methods Lecture 6: Ensemble Methods
Lecture 6: Ensemble Methods
 
ensemble learning
ensemble learningensemble learning
ensemble learning
 
Semi supervised learning machine learning made simple
Semi supervised learning  machine learning made simpleSemi supervised learning  machine learning made simple
Semi supervised learning machine learning made simple
 
Machine Learning and Data Mining: 16 Classifiers Ensembles
Machine Learning and Data Mining: 16 Classifiers EnsemblesMachine Learning and Data Mining: 16 Classifiers Ensembles
Machine Learning and Data Mining: 16 Classifiers Ensembles
 
Teaching calculus with Wolfram Alpha
Teaching calculus with Wolfram AlphaTeaching calculus with Wolfram Alpha
Teaching calculus with Wolfram Alpha
 
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
 
H2O World - Ensembles with Erin LeDell
H2O World - Ensembles with Erin LeDellH2O World - Ensembles with Erin LeDell
H2O World - Ensembles with Erin LeDell
 
Ensemble Learning Featuring the Netflix Prize Competition and ...
Ensemble Learning Featuring the Netflix Prize Competition and ...Ensemble Learning Featuring the Netflix Prize Competition and ...
Ensemble Learning Featuring the Netflix Prize Competition and ...
 
Semi-supervised Learning
Semi-supervised LearningSemi-supervised Learning
Semi-supervised Learning
 
(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised Learning(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised Learning
 
Lecture 9: Machine Learning in Practice (2)
Lecture 9: Machine Learning in Practice (2)Lecture 9: Machine Learning in Practice (2)
Lecture 9: Machine Learning in Practice (2)
 
Exposé Ontology
Exposé OntologyExposé Ontology
Exposé Ontology
 
Instance based learning
Instance based learningInstance based learning
Instance based learning
 
BigML Education - Feature Engineering with Flatline
BigML Education - Feature Engineering with FlatlineBigML Education - Feature Engineering with Flatline
BigML Education - Feature Engineering with Flatline
 
Meta learning tutorial
Meta learning tutorialMeta learning tutorial
Meta learning tutorial
 
Lecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
Lecture 3: Basic Concepts of Machine Learning - Induction & EvaluationLecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
Lecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
 
Boosting Algorithms Omar Odibat
Boosting Algorithms Omar Odibat Boosting Algorithms Omar Odibat
Boosting Algorithms Omar Odibat
 
Learning loss for active learning
Learning loss for active learningLearning loss for active learning
Learning loss for active learning
 
Feature Importance Analysis with XGBoost in Tax audit
Feature Importance Analysis with XGBoost in Tax auditFeature Importance Analysis with XGBoost in Tax audit
Feature Importance Analysis with XGBoost in Tax audit
 
Linear Regression Ex
Linear Regression ExLinear Regression Ex
Linear Regression Ex
 

Viewers also liked

NLTK: Natural Language Processing made easy
NLTK: Natural Language Processing made easyNLTK: Natural Language Processing made easy
NLTK: Natural Language Processing made easyoutsider2
 
GPU Accelerated Natural Language Processing by Guillermo Molini
GPU Accelerated Natural Language Processing by Guillermo MoliniGPU Accelerated Natural Language Processing by Guillermo Molini
GPU Accelerated Natural Language Processing by Guillermo MoliniBig Data Spain
 
Words and lexemes ppt
Words and lexemes pptWords and lexemes ppt
Words and lexemes pptAngeline-dbz
 
Practical Natural Language Processing
Practical Natural Language ProcessingPractical Natural Language Processing
Practical Natural Language ProcessingJaganadh Gopinadhan
 

Viewers also liked (6)

Syntax analysis
Syntax analysisSyntax analysis
Syntax analysis
 
NLTK: Natural Language Processing made easy
NLTK: Natural Language Processing made easyNLTK: Natural Language Processing made easy
NLTK: Natural Language Processing made easy
 
GPU Accelerated Natural Language Processing by Guillermo Molini
GPU Accelerated Natural Language Processing by Guillermo MoliniGPU Accelerated Natural Language Processing by Guillermo Molini
GPU Accelerated Natural Language Processing by Guillermo Molini
 
Words and lexemes ppt
Words and lexemes pptWords and lexemes ppt
Words and lexemes ppt
 
Practical Natural Language Processing
Practical Natural Language ProcessingPractical Natural Language Processing
Practical Natural Language Processing
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
 

Similar to [Paper Introduction] Training a Natural Language Generator From Unaligned Data

PPT SLIDES
PPT SLIDESPPT SLIDES
PPT SLIDESbutest
 
PPT SLIDES
PPT SLIDESPPT SLIDES
PPT SLIDESbutest
 
Self training improves_nlu
Self training improves_nlu Self training improves_nlu
Self training improves_nlu taeseon ryu
 
Presentation on supervised learning
Presentation on supervised learningPresentation on supervised learning
Presentation on supervised learningTonmoy Bhagawati
 
activelearning.ppt
activelearning.pptactivelearning.ppt
activelearning.pptbutest
 
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...Universitat Politècnica de Catalunya
 
Active learning for ranking through expected loss optimization
Active learning for ranking through expected loss optimizationActive learning for ranking through expected loss optimization
Active learning for ranking through expected loss optimizationPvrtechnologies Nellore
 
Modelling and evaluation
Modelling and evaluationModelling and evaluation
Modelling and evaluationeShikshak
 
Winning Kaggle 101: Introduction to Stacking
Winning Kaggle 101: Introduction to StackingWinning Kaggle 101: Introduction to Stacking
Winning Kaggle 101: Introduction to StackingTed Xiao
 
Chinese Named Entity Recognition with Graph-based Semi-supervised Learning Model
Chinese Named Entity Recognition with Graph-based Semi-supervised Learning ModelChinese Named Entity Recognition with Graph-based Semi-supervised Learning Model
Chinese Named Entity Recognition with Graph-based Semi-supervised Learning ModelLifeng (Aaron) Han
 
Andrew NG machine learning
Andrew NG machine learningAndrew NG machine learning
Andrew NG machine learningShareDocView.com
 
Generating test cases using UML Communication Diagram
Generating test cases using UML Communication Diagram Generating test cases using UML Communication Diagram
Generating test cases using UML Communication Diagram Praveen Penumathsa
 
TEACHING AND LEARNING BASED OPTIMISATION
TEACHING AND LEARNING BASED OPTIMISATIONTEACHING AND LEARNING BASED OPTIMISATION
TEACHING AND LEARNING BASED OPTIMISATIONUday Wankar
 

Similar to [Paper Introduction] Training a Natural Language Generator From Unaligned Data (20)

PPT SLIDES
PPT SLIDESPPT SLIDES
PPT SLIDES
 
PPT SLIDES
PPT SLIDESPPT SLIDES
PPT SLIDES
 
Self training improves_nlu
Self training improves_nlu Self training improves_nlu
Self training improves_nlu
 
Presentation on supervised learning
Presentation on supervised learningPresentation on supervised learning
Presentation on supervised learning
 
ANN - UNIT 3.pptx
ANN - UNIT 3.pptxANN - UNIT 3.pptx
ANN - UNIT 3.pptx
 
ANN - UNIT 3.pptx
ANN - UNIT 3.pptxANN - UNIT 3.pptx
ANN - UNIT 3.pptx
 
activelearning.ppt
activelearning.pptactivelearning.ppt
activelearning.ppt
 
Artificial Neural Networks , Recurrent networks , Perceptron's
Artificial Neural Networks , Recurrent networks , Perceptron'sArtificial Neural Networks , Recurrent networks , Perceptron's
Artificial Neural Networks , Recurrent networks , Perceptron's
 
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
 
Active learning for ranking through expected loss optimization
Active learning for ranking through expected loss optimizationActive learning for ranking through expected loss optimization
Active learning for ranking through expected loss optimization
 
Modelling and evaluation
Modelling and evaluationModelling and evaluation
Modelling and evaluation
 
FLY-SMOTE.pdf
FLY-SMOTE.pdfFLY-SMOTE.pdf
FLY-SMOTE.pdf
 
Winning Kaggle 101: Introduction to Stacking
Winning Kaggle 101: Introduction to StackingWinning Kaggle 101: Introduction to Stacking
Winning Kaggle 101: Introduction to Stacking
 
Chinese Named Entity Recognition with Graph-based Semi-supervised Learning Model
Chinese Named Entity Recognition with Graph-based Semi-supervised Learning ModelChinese Named Entity Recognition with Graph-based Semi-supervised Learning Model
Chinese Named Entity Recognition with Graph-based Semi-supervised Learning Model
 
Andrew NG machine learning
Andrew NG machine learningAndrew NG machine learning
Andrew NG machine learning
 
Machine learning yearning
Machine learning yearningMachine learning yearning
Machine learning yearning
 
Generating test cases using UML Communication Diagram
Generating test cases using UML Communication Diagram Generating test cases using UML Communication Diagram
Generating test cases using UML Communication Diagram
 
Large Scale Distributed Deep Networks
Large Scale Distributed Deep NetworksLarge Scale Distributed Deep Networks
Large Scale Distributed Deep Networks
 
Co primes teacher-notes
Co primes teacher-notesCo primes teacher-notes
Co primes teacher-notes
 
TEACHING AND LEARNING BASED OPTIMISATION
TEACHING AND LEARNING BASED OPTIMISATIONTEACHING AND LEARNING BASED OPTIMISATION
TEACHING AND LEARNING BASED OPTIMISATION
 

More from NAIST Machine Translation Study Group

[Paper Introduction] Efficient Lattice Rescoring Using Recurrent Neural Netwo...
[Paper Introduction] Efficient Lattice Rescoring Using Recurrent Neural Netwo...[Paper Introduction] Efficient Lattice Rescoring Using Recurrent Neural Netwo...
[Paper Introduction] Efficient Lattice Rescoring Using Recurrent Neural Netwo...NAIST Machine Translation Study Group
 
[Paper Introduction] Distant supervision for relation extraction without labe...
[Paper Introduction] Distant supervision for relation extraction without labe...[Paper Introduction] Distant supervision for relation extraction without labe...
[Paper Introduction] Distant supervision for relation extraction without labe...NAIST Machine Translation Study Group
 
[Paper Introduction] Efficient top down btg parsing for machine translation p...
[Paper Introduction] Efficient top down btg parsing for machine translation p...[Paper Introduction] Efficient top down btg parsing for machine translation p...
[Paper Introduction] Efficient top down btg parsing for machine translation p...NAIST Machine Translation Study Group
 
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...NAIST Machine Translation Study Group
 
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...NAIST Machine Translation Study Group
 
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...NAIST Machine Translation Study Group
 
[Paper Introduction] Bilingual word representations with monolingual quality ...
[Paper Introduction] Bilingual word representations with monolingual quality ...[Paper Introduction] Bilingual word representations with monolingual quality ...
[Paper Introduction] Bilingual word representations with monolingual quality ...NAIST Machine Translation Study Group
 
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...NAIST Machine Translation Study Group
 

More from NAIST Machine Translation Study Group (14)

[Paper Introduction] Efficient Lattice Rescoring Using Recurrent Neural Netwo...
[Paper Introduction] Efficient Lattice Rescoring Using Recurrent Neural Netwo...[Paper Introduction] Efficient Lattice Rescoring Using Recurrent Neural Netwo...
[Paper Introduction] Efficient Lattice Rescoring Using Recurrent Neural Netwo...
 
[Paper Introduction] Distant supervision for relation extraction without labe...
[Paper Introduction] Distant supervision for relation extraction without labe...[Paper Introduction] Distant supervision for relation extraction without labe...
[Paper Introduction] Distant supervision for relation extraction without labe...
 
On using monolingual corpora in neural machine translation
On using monolingual corpora in neural machine translationOn using monolingual corpora in neural machine translation
On using monolingual corpora in neural machine translation
 
RNN-based Translation Models (Japanese)
RNN-based Translation Models (Japanese)RNN-based Translation Models (Japanese)
RNN-based Translation Models (Japanese)
 
[Paper Introduction] Efficient top down btg parsing for machine translation p...
[Paper Introduction] Efficient top down btg parsing for machine translation p...[Paper Introduction] Efficient top down btg parsing for machine translation p...
[Paper Introduction] Efficient top down btg parsing for machine translation p...
 
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
[Paper Introduction] Translating into Morphologically Rich Languages with Syn...
 
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
[Paper Introduction] Supervised Phrase Table Triangulation with Neural Word E...
 
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
[Paper Introduction] Evaluating MT Systems with Second Language Proficiency T...
 
[Paper Introduction] Bilingual word representations with monolingual quality ...
[Paper Introduction] Bilingual word representations with monolingual quality ...[Paper Introduction] Bilingual word representations with monolingual quality ...
[Paper Introduction] Bilingual word representations with monolingual quality ...
 
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
[Paper Introduction] A Context-Aware Topic Model for Statistical Machine Tran...
 
[Book Reading] 機械翻訳 - Section 3 No.1
[Book Reading] 機械翻訳 - Section 3 No.1[Book Reading] 機械翻訳 - Section 3 No.1
[Book Reading] 機械翻訳 - Section 3 No.1
 
[Book Reading] 機械翻訳 - Section 5 No.2
[Book Reading] 機械翻訳 - Section 5 No.2[Book Reading] 機械翻訳 - Section 5 No.2
[Book Reading] 機械翻訳 - Section 5 No.2
 
[Book Reading] 機械翻訳 - Section 7 No.1
[Book Reading] 機械翻訳 - Section 7 No.1[Book Reading] 機械翻訳 - Section 7 No.1
[Book Reading] 機械翻訳 - Section 7 No.1
 
[Book Reading] 機械翻訳 - Section 2 No.2
 [Book Reading] 機械翻訳 - Section 2 No.2 [Book Reading] 機械翻訳 - Section 2 No.2
[Book Reading] 機械翻訳 - Section 2 No.2
 

Recently uploaded

Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticssakshisoni2385
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsSérgio Sacani
 
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professormuralinath2
 
Grade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its FunctionsGrade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its FunctionsOrtegaSyrineMay
 
FAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and SpectrometryFAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and SpectrometryAlex Henderson
 
FAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceFAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceAlex Henderson
 
Call Girls Ahmedabad +917728919243 call me Independent Escort Service
Call Girls Ahmedabad +917728919243 call me Independent Escort ServiceCall Girls Ahmedabad +917728919243 call me Independent Escort Service
Call Girls Ahmedabad +917728919243 call me Independent Escort Serviceshivanisharma5244
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000Sapana Sha
 
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICESAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICEayushi9330
 
Sector 62, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 62, Noida Call girls :8448380779 Model Escorts | 100% verifiedSector 62, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 62, Noida Call girls :8448380779 Model Escorts | 100% verifiedDelhi Call girls
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)Areesha Ahmad
 
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...Silpa
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfrohankumarsinghrore1
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and ClassificationsAreesha Ahmad
 
Introduction to Viruses
Introduction to VirusesIntroduction to Viruses
Introduction to VirusesAreesha Ahmad
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPirithiRaju
 
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verifiedConnaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verifiedDelhi Call girls
 

Recently uploaded (20)

Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceuticsPulmonary drug delivery system M.pharm -2nd sem P'ceutics
Pulmonary drug delivery system M.pharm -2nd sem P'ceutics
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
 
Site Acceptance Test .
Site Acceptance Test                    .Site Acceptance Test                    .
Site Acceptance Test .
 
Clean In Place(CIP).pptx .
Clean In Place(CIP).pptx                 .Clean In Place(CIP).pptx                 .
Clean In Place(CIP).pptx .
 
Grade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its FunctionsGrade 7 - Lesson 1 - Microscope and Its Functions
Grade 7 - Lesson 1 - Microscope and Its Functions
 
FAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and SpectrometryFAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
FAIRSpectra - Enabling the FAIRification of Spectroscopy and Spectrometry
 
FAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceFAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical Science
 
Call Girls Ahmedabad +917728919243 call me Independent Escort Service
Call Girls Ahmedabad +917728919243 call me Independent Escort ServiceCall Girls Ahmedabad +917728919243 call me Independent Escort Service
Call Girls Ahmedabad +917728919243 call me Independent Escort Service
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
 
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICESAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
 
Sector 62, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 62, Noida Call girls :8448380779 Model Escorts | 100% verifiedSector 62, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 62, Noida Call girls :8448380779 Model Escorts | 100% verified
 
GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)GBSN - Microbiology (Unit 2)
GBSN - Microbiology (Unit 2)
 
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
Locating and isolating a gene, FISH, GISH, Chromosome walking and jumping, te...
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdf
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
 
Introduction to Viruses
Introduction to VirusesIntroduction to Viruses
Introduction to Viruses
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
 
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verifiedConnaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
 

[Paper Introduction] Training a Natural Language Generator From Unaligned Data

  • 1. Training a Natural Language Generator From Unaligned Data PHILIP ARTHUR MT STUDY GROUP 9/3/2015 1
  • 2. Paper Description Title: Training a Natural Language Generator From Unaligned Data Author: Ondrej Dusek and Filip Jurcicek Meeting: ACL Year: 2015 Type: Long Paper Reference: https://aclweb.org/anthology/P/P15/P15-1044.pdf 9/3/2015 2
  • 3. Natural Language Generation • Generating a natural language from abstract representation. 9/3/2015 3
  • 4. Motivation & Contribution • Motivation • Current NLG system requires separate training data alignment step. • Using CFG or phrase based limit the ability to capture long-range syntactic dependencies. • Contribution • Novel method that integrates alignment step into sentence planner. • Using deep-syntactic trees with rule based surface realization. • Ability to learn from incomplete tree. 9/3/2015 4
  • 6. About the data structure • Each node has a lemma and formeme. (Dušek et al., 2012) • Contain nodes for content words (nouns, full verbs, adjectives, adverbs) and coordinating conjunctions. • Treex toolkit is used to generate this dependency tree for the input. 9/3/2015 6
  • 7. Dataset • BAGEL: dataset of restaurant, consists of Dialogue Acts (DA) & list of slot-value pairs (SVPs), contains information about restaurants. • Where: http://farm2.user.srcf.net/research/bagel/ACL10-inform-training.txt • Example: 9/3/2015 7 FULL_DA = inform(name="Green Man",eattype=restaurant) ABSTRACT_DA = inform(name="X1",eattype=restaurant) -> "[name+X]X []is a [eattype+restaurant]restaurant.";
  • 8. Sentence Planner • Building a deep syntactic tree based on A* search. (2 Hypotheses: Open + Closed) • Based on: Candidate Generator + Scorer/Ranker 9/3/2015 8
  • 9. Sentence Planner Algorithm Init: Start from an open set with a single empty sentence plan tree and an empty closed set. Loop: 1. Select the best-scoring candidate C from the open set. Add C to closed set. 2. The candidate generator generates C, a set of possible successors to C. These are trees that have more nodes than C and are deemed viable. Note that C may be empty. 3. The scorer scores all successors in C and if they are not already in the closed set, it adds them to the open set. 4. Check if the best successor in the open set scores better than the best candidate in the closed set. Stop: The algorithm finishes if the top score in the open set is lower than the top score in the closed set for d consecutive iterations, or if there are no more candidates in the open set. It returns the best-scoring candidate from both sets. 9/3/2015 9
  • 10. Candidate Generator • Adding one new node in all possible positions with all possible lemmas and formemes. 9/3/2015 10
  • 11. CG + Expansion Filtering 1. Lemma-formeme compatibility: nodes with combination of lemma + formeme in Training. 2. Syntatic vialibility: new node generated compatible with parent (seen before, including dependency of left and right child). 3. Number of children: For particular parent node, #child can’t exceed the max #child of same node in Training. 4. Tree Size: #nodes in tree can’t exceed the max #nodes of tree in training data. For each level. 5. Weak semantic compatibility: Include node that appears in training, containing SVPs from the current input. 6. Strong semantic compatibility: For each lemma + formeme, there is a compatibility list. Node generation is allowed if all of SVPs are present in the current input DA. 9/3/2015 11
  • 12. Scorer / Ranker • Is a function that maps global features from sentence plan 𝑡 + input 𝑚 to a real value. • Based on basic perceptron scorer: 9/3/2015 12
  • 13. Training Objective: Init: all 𝑤 ∈ 𝐰 = 1 For each input MR in Training: 1. 𝑡𝑡𝑜𝑝 = Generate a sentence plan of the input based on current weight. 2. 𝑡 𝑔𝑜𝑙𝑑 = Parsed input by using automatic annotator (treex). 3. Update: 9/3/2015 13
  • 14. Differing Subtrees Update • Starting from the common subtree 𝑡 𝑐 of 𝑡𝑡𝑜𝑝and 𝑡 𝑔𝑜𝑙𝑑, pairs of differing subtrees 𝑡𝑡𝑜𝑝 𝑖 , 𝑡 𝑔𝑜𝑙𝑑 𝑖 are created by gradually adding nodes from 𝑡𝑡𝑜𝑝into 𝑡𝑡𝑜𝑝 𝑖 and from 𝑡 𝑔𝑜𝑙𝑑 into 𝑡 𝑔𝑜𝑙𝑑 𝑖 . 9/3/2015 14
  • 15. Algorithm Differing Subtree Update • In the third step of training, substitute “full-tree” update with “” update: • It is reported that if we don’t use the same size of subtree, performance will degrade. 9/3/2015 15
  • 16. Future Promise Estimation • The same idea of A* search where score = scorer(input, weight) + heuristic(input). • Based on Expected number of children 𝐸𝑐(𝑛) of different node types. • The future promise (fp) of a particular sentence plan 𝑡 is calculated based on its node 𝑛1 … 𝑛 𝑡: • 𝑐(𝑛𝑖) is the current number of children. • 𝜆 is a preset parameter. • Not included in stop criterion check. 9/3/2015 16
  • 17. Averaging Weight + Parallel Training • Using Iterative mixing approrach (McDonald et al. 2010). • Training data are splitted into several parts. • Weights updated are averaged after each pass through the training data. • Record weights after each training pass, take an average at the end  Final weight. 9/3/2015 17
  • 18. Surface Realizer • Built using Treex NLP toolkit (Ptacek, 2008). • Rule based simple pipeline, outlining: 1. Agreement 2. Word Ordering 3. Compound verb forms 4. Grammatical words 5. Punctuation 6. Word Inflection 7. Phonetic Changes • Round trip test using automatic analysis with subsequent generation reached 89.79% BLEU. 9/3/2015 18
  • 19. Features • current tree properties: depth, #nodes, #repeated_nodes • tree and input DA: #nodes/SVP, #repeated_nodes/SVP • node features: lemma, formeme, #children of all nodes in the current tree. • input features: whole SVPs (slot+value), just slots, and pairs of slots in the DA • combinations of node and input features • repeat features: #repeated_lemma_formeme with #repeated_slots in the input DA. • dependency features: parent-child pairs for lemmas + formeme, including left or right. • sibling features: sibling pairs for lemmas + formeme, combined with SVP. • bigram features: pairs of lemmas + formeme adjacent in tree left-right order, combined with SVP. 9/3/2015 19
  • 20. Setup • #iterations do not improve: • Training = 3 • Testing = 4 • Maximum 200 sentence planner iterations per input DA. • 𝛼 = 0.1 • If fp is used then 𝛼 = 0.3 • 10 folds cross validation is used in the experiment. 9/3/2015 20
  • 21. Results • The Proposed method gives improvement on both BLEU and NIST with whole training portion. • Compare to the previous work (67%) is still lower.  Task is harder, no alignment is used. • Larger training data can demonstrate the effectiveness of the proposed method. • Both improvement gain a 95% confidence of statistical significance testing (Koehn, 2004). 9/3/2015 21
  • 22. Example of Generated pairs 9/3/2015 22
  • 23. Discussion + Generator learns to produce meaningful utterances that correspond well to the input DA. - Not all required information is always present. - Some facts are sometimes repeated or irrelevant information Appears ◦ Occurs because of the data sparsity. ◦ Design a scorer features that discourage conflicting information. - Repeated slots in input are not handled correctly. 9/3/2015 23
  • 24. Conclusion • The paper presented a NLG, capable of learning from unaligned pairs. • The contribution consists of A* based sentence planner, rule-based surface realization from Treex toolkit. • The empiric results shows a promising result, although didn’t surpass the previous work, but their work is substantially harder. • Code: https://github.com/UFAL-DSG/tgen 9/3/2015 24