End-to-End Content and Plan Selection for Data-to-Text Generation

Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents a survey of several extensions to sequence-to-sequence models to account for the latent content selection process, particularly variants of copy attention and coverage decoding. We further propose a training method based on diverse ensembling to encourage models to learn distinct sentence templates during training. An empirical evaluation of these techniques shows an increase in the quality of generated text across five automated metrics, as well as human evaluation.

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

[2]  Yejin Choi,et al.  Neural AMR: Sequence-to-Sequence Models for Parsing and Generation , 2017, ACL.

[3]  Michael Cogswell,et al.  Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles , 2016, NIPS.

[4]  C. Lawrence Zitnick,et al.  CIDEr: Consensus-based image description evaluation , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

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

[7]  Markus Freitag,et al.  Unsupervised Natural Language Generation with Denoising Autoencoders , 2018, EMNLP.

[8]  Verena Rieser,et al.  The E2E Dataset: New Challenges For End-to-End Generation , 2017, SIGDIAL Conference.

[9]  Verena Rieser,et al.  Findings of the E2E NLG Challenge , 2018, INLG.

[10]  Marilyn A. Walker,et al.  A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation , 2018, NAACL.

[11]  George R. Doddington,et al.  Automatic Evaluation of Machine Translation Quality Using N-gram Co-Occurrence Statistics , 2002 .

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

[13]  David Vandyke,et al.  Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems , 2015, EMNLP.

[14]  Marilyn A. Walker,et al.  Trainable Sentence Planning for Complex Information Presentations in Spoken Dialog Systems , 2004, ACL.

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

[16]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[17]  Andreas Vlachos,et al.  Imitation learning for language generation from unaligned data , 2016, COLING.

[18]  Yun-Nung Chen,et al.  Natural Language Generation by Hierarchical Decoding with Linguistic Patterns , 2018, NAACL.

[19]  Steve J. Young,et al.  Stochastic Language Generation in Dialogue using Factored Language Models , 2014, Computational Linguistics.

[20]  Alexander I. Rudnicky,et al.  Stochastic Language Generation for Spoken Dialogue Systems , 2000 .

[21]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[22]  Alexander M. Rush,et al.  OpenNMT: Open-Source Toolkit for Neural Machine Translation , 2017, ACL.

[23]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[24]  Marilyn A. Walker,et al.  Individual and Domain Adaptation in Sentence Planning for Dialogue , 2007, J. Artif. Intell. Res..

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

[26]  Jinwoo Shin,et al.  Confident Multiple Choice Learning , 2017, ICML.

[27]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

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

[29]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[31]  Pushmeet Kohli,et al.  Multiple Choice Learning: Learning to Produce Multiple Structured Outputs , 2012, NIPS.

[32]  Ondrej Dusek,et al.  Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings , 2016, ACL.

[33]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[34]  Blake Howald,et al.  A Statistical NLG Framework for Aggregated Planning and Realization , 2013, ACL.

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

[36]  Matt Post,et al.  Efficient Elicitation of Annotations for Human Evaluation of Machine Translation , 2014, WMT@ACL.

[37]  Xiaochang Peng,et al.  Addressing the Data Sparsity Issue in Neural AMR Parsing , 2017, EACL.

[38]  Emiel Krahmer,et al.  Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation , 2017, INLG.

[39]  Alon Lavie,et al.  Meteor Universal: Language Specific Translation Evaluation for Any Target Language , 2014, WMT@ACL.

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