Table-to-Text: Describing Table Region With Natural Language

In this paper, we present a generative model to generate a natural language sentence describing a table region, e.g., a row. The model maps a row from a table to a continuous vector and then generates a natural language sentence by leveraging the semantics of a table. To deal with rare words appearing in a table, we develop a flexible copying mechanism that selectively replicates contents from the table in the output sequence. Extensive experiments demonstrate the accuracy of the model and the power of the copying mechanism. On two synthetic datasets, WIKIBIO and SIMPLEQUESTIONS, our model improves the current state-of-the-art BLEU-4 score from 34.70 to 40.26 and from 33.32 to 39.12, respectively. Furthermore, we introduce an open-domain dataset WIKITABLETEXT including 13,318 explanatory sentences for 4,962 tables. Our model achieves a BLEU-4 score of 38.23, which outperforms template based and language model based approaches.

[1]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[2]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[3]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[4]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[5]  Yang Liu,et al.  Modeling Coverage for Neural Machine Translation , 2016, ACL.

[6]  Xin Jiang,et al.  Neural Generative Question Answering , 2015, IJCAI.

[7]  Zhoujun Li,et al.  DocChat: An Information Retrieval Approach for Chatbot Engines Using Unstructured Documents , 2016, ACL.

[8]  Mirella Lapata,et al.  Collective Content Selection for Concept-to-Text Generation , 2005, HLT.

[9]  Ion Androutsopoulos,et al.  Generating Natural Language Descriptions from OWL Ontologies: the NaturalOWL System , 2013, J. Artif. Intell. Res..

[10]  Yoshua Bengio,et al.  Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus , 2016, ACL.

[11]  Quoc V. Le,et al.  Addressing the Rare Word Problem in Neural Machine Translation , 2014, ACL.

[12]  Jim Hunter,et al.  Choosing words in computer-generated weather forecasts , 2005, Artif. Intell..

[13]  Percy Liang,et al.  Compositional Semantic Parsing on Semi-Structured Tables , 2015, ACL.

[14]  Mirella Lapata,et al.  A Global Model for Concept-to-Text Generation , 2013, J. Artif. Intell. Res..

[15]  Raymond J. Mooney,et al.  Learning to sportscast: a test of grounded language acquisition , 2008, ICML '08.

[16]  Jason Weston,et al.  Large-scale Simple Question Answering with Memory Networks , 2015, ArXiv.

[17]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[18]  Eduard H. Hovy,et al.  Tables as Semi-structured Knowledge for Question Answering , 2016, ACL.

[19]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

[20]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[21]  Yoshua Bengio,et al.  Attention-Based Models for Speech Recognition , 2015, NIPS.

[22]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[23]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[24]  Phil Blunsom,et al.  Recurrent Continuous Translation Models , 2013, EMNLP.

[25]  Matthew R. Walter,et al.  What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment , 2015, NAACL.

[26]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[27]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.

[28]  Hao Ma,et al.  Table Cell Search for Question Answering , 2016, WWW.

[29]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[30]  Qun Liu,et al.  Interactive Attention for Neural Machine Translation , 2016, COLING.

[31]  Mirella Lapata,et al.  Concept-to-text Generation via Discriminative Reranking , 2012, ACL.

[32]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[33]  Bowen Zhou,et al.  Pointing the Unknown Words , 2016, ACL.

[34]  Alexander M. Rush,et al.  Challenges in Data-to-Document Generation , 2017, EMNLP.

[35]  Yann Dauphin,et al.  A Convolutional Encoder Model for Neural Machine Translation , 2016, ACL.

[36]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[37]  Bowen Zhou,et al.  Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond , 2016, CoNLL.

[38]  Dan Klein,et al.  A Simple Domain-Independent Probabilistic Approach to Generation , 2010, EMNLP.

[39]  Jianfeng Gao,et al.  A Neural Network Approach to Context-Sensitive Generation of Conversational Responses , 2015, NAACL.

[40]  Qun Liu,et al.  Encoding Source Language with Convolutional Neural Network for Machine Translation , 2015, ACL.

[41]  Shi Feng,et al.  Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation , 2016, COLING.

[42]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[43]  J. Koenderink.  Q… , 2014, Les noms officiels des communes de Wallonie, de Bruxelles-Capitale et de la communaute germanophone.

[44]  David Grangier,et al.  Neural Text Generation from Structured Data with Application to the Biography Domain , 2016, EMNLP.

[45]  Dan Klein,et al.  Learning Semantic Correspondences with Less Supervision , 2009, ACL.