文献紹介:SemEval-2012 Task 1: English Lexical SimplificationTomoyuki Kajiwara
Lucia Specia, Sujay Kumar Jauhar, Rada Mihalcea. SemEval-2012 Task 1: English Lexical Simplification. In Proceedings of the 6th International Workshop on Semantic Evaluation (SemEval-2012), pp.347-355, 2012.
EMNLP 2015 読み会 @ 小町研 "Morphological Analysis for Unsegmented Languages using ...Yuki Tomo
首都大学東京 情報通信システム学域 小町研究室に行われた EMNLP 2015 読み会で "Morphological Analysis for Unsegmented Languages using Recurrent Neural Network Language Model" を紹介した際の資料です。
文献紹介:SemEval-2012 Task 1: English Lexical SimplificationTomoyuki Kajiwara
Lucia Specia, Sujay Kumar Jauhar, Rada Mihalcea. SemEval-2012 Task 1: English Lexical Simplification. In Proceedings of the 6th International Workshop on Semantic Evaluation (SemEval-2012), pp.347-355, 2012.
EMNLP 2015 読み会 @ 小町研 "Morphological Analysis for Unsegmented Languages using ...Yuki Tomo
首都大学東京 情報通信システム学域 小町研究室に行われた EMNLP 2015 読み会で "Morphological Analysis for Unsegmented Languages using Recurrent Neural Network Language Model" を紹介した際の資料です。
Neural Models for Information Retrieval
Bhaskar Mitra, Nick Craswell
(Submitted on 3 May 2017)
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ machine learning techniques over hand-crafted IR features. By contrast, neural models learn representations of language from raw text that can bridge the gap between query and document vocabulary. Unlike classical IR models, these new machine learning based approaches are data-hungry, requiring large scale training data before they can be deployed. This tutorial introduces basic concepts and intuitions behind neural IR models, and places them in the context of traditional retrieval models. We begin by introducing fundamental concepts of IR and different neural and non-neural approaches to learning vector representations of text. We then review shallow neural IR methods that employ pre-trained neural term embeddings without learning the IR task end-to-end. We introduce deep neural networks next, discussing popular deep architectures. Finally, we review the current DNN models for information retrieval. We conclude with a discussion on potential future directions for neural IR.
Variational Template Machine for Data-to-Text Generationharmonylab
公開URL:https://openreview.net/forum?id=HkejNgBtPB
出典:Rong Ye, Wenxian Shi, Hao Zhou, Zhongyu Wei, Lei Li : Variational Template Machine for Data-to-Text Generation, 8th International Conference on Learning Representations(ICLR2020), Addis Ababa, Ethiopia (2020)
概要:Table形式の構造化データから文章を生成するタスク(Data-to-Text)において、Variational Auto Encoder(VAE)ベースの手法Variational Template Machine(VTM)を提案する論文です。Encoder-Decoderモデルを用いた既存のアプローチでは、生成文の多様性に欠けるという課題があります。本論文では多様な文章を生成するためにはテンプレートが重要であるという主張に基づき、テンプレートを学習可能なVAEベースの手法を提案します。提案手法では潜在変数の空間をテンプレート空間とコンテンツ空間に明示的に分離することによって、正確で多様な文生成が可能となります。また、table-textのペアデータだけではなくtableデータのないraw textデータを利用した半教師あり学習を行います。
Courteously yours inducing courteous behavior in customer care responses usi...ryoma yoshimura
1) The document proposes a framework to induce courteous behavior in customer care responses using a reinforced pointer generator network.
2) It creates a new dataset of actual customer service conversations called the Courteously Yours Customer Care Dataset to train and evaluate models.
3) Experimental results show the model is able to generate courteous responses that preserve content from the conversation history based on automatic and human evaluations, though some minor inaccuracies remain.
Neural Models for Information Retrieval
Bhaskar Mitra, Nick Craswell
(Submitted on 3 May 2017)
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ machine learning techniques over hand-crafted IR features. By contrast, neural models learn representations of language from raw text that can bridge the gap between query and document vocabulary. Unlike classical IR models, these new machine learning based approaches are data-hungry, requiring large scale training data before they can be deployed. This tutorial introduces basic concepts and intuitions behind neural IR models, and places them in the context of traditional retrieval models. We begin by introducing fundamental concepts of IR and different neural and non-neural approaches to learning vector representations of text. We then review shallow neural IR methods that employ pre-trained neural term embeddings without learning the IR task end-to-end. We introduce deep neural networks next, discussing popular deep architectures. Finally, we review the current DNN models for information retrieval. We conclude with a discussion on potential future directions for neural IR.
Variational Template Machine for Data-to-Text Generationharmonylab
公開URL:https://openreview.net/forum?id=HkejNgBtPB
出典:Rong Ye, Wenxian Shi, Hao Zhou, Zhongyu Wei, Lei Li : Variational Template Machine for Data-to-Text Generation, 8th International Conference on Learning Representations(ICLR2020), Addis Ababa, Ethiopia (2020)
概要:Table形式の構造化データから文章を生成するタスク(Data-to-Text)において、Variational Auto Encoder(VAE)ベースの手法Variational Template Machine(VTM)を提案する論文です。Encoder-Decoderモデルを用いた既存のアプローチでは、生成文の多様性に欠けるという課題があります。本論文では多様な文章を生成するためにはテンプレートが重要であるという主張に基づき、テンプレートを学習可能なVAEベースの手法を提案します。提案手法では潜在変数の空間をテンプレート空間とコンテンツ空間に明示的に分離することによって、正確で多様な文生成が可能となります。また、table-textのペアデータだけではなくtableデータのないraw textデータを利用した半教師あり学習を行います。
Courteously yours inducing courteous behavior in customer care responses usi...ryoma yoshimura
1) The document proposes a framework to induce courteous behavior in customer care responses using a reinforced pointer generator network.
2) It creates a new dataset of actual customer service conversations called the Courteously Yours Customer Care Dataset to train and evaluate models.
3) Experimental results show the model is able to generate courteous responses that preserve content from the conversation history based on automatic and human evaluations, though some minor inaccuracies remain.
9. 実験1 Text Simplification
Data sets
● Parallel WIkipedia Simplification Corpus (PWKP) (Zhu et al., 2010)
○ train 89,042 pair
○ dev 205 pair
○ test 100 pair
● English Wikipedia and Simple English Wikipedia (EW-SEW) (Hwang et al.2015)
○ train 280,000 pair
○ dev 2000 pair
○ test 359 pair
10. 実験1 Text Simplification
Evaluation Metrics
● Automatic evaluation. BLEU(Paineni et al., 2002)
○ PWKP single reference
○ EW-SEW multi reference
● Human evaluation. (1 is very bad, 5 is very good)
○ Fluency(流暢性) 1 ~ 5
○ Adequacy(妥当性)1 ~ 5
○ Simplicity(簡潔性) 1 ~ 5
16. 実験2 Large Scale Text Summarization
Dataset
Large Scale Chinese Social Media Short Text Summarization Dataset(LCSTS)
2,400,000文ペア
● Part1 2,400,591ペア train
● Part2 8,685ぺア validation
● Part3 725ペア test
Part2とPart3は1~5で自動評価されていて、スコア3以上のものを選択