Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts, and we use it to directly compare two-step generation with separate sentence planning and surface realization stages to a joint, one-step approach. We were able to train both setups successfully using very little training data. The joint setup offers better performance, surpassing state-of-the-art with regards to n-gram-based scores while providing more relevant outputs.

[1]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[2]  Ehud Reiter,et al.  Book Reviews: Building Natural Language Generation Systems , 2000, CL.

[3]  Marilyn A. Walker,et al.  SPoT: A Trainable Sentence Planner , 2001, NAACL.

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

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

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

[7]  Philipp Koehn,et al.  Statistical Significance Tests for Machine Translation Evaluation , 2004, EMNLP.

[8]  Roger Evans,et al.  Empirically-based Control of Natural Language Generation , 2005, ACL.

[9]  Maxine Eskénazi,et al.  Let's go public! taking a spoken dialog system to the real world , 2005, INTERSPEECH.

[10]  Raymond J. Mooney,et al.  Generation by Inverting a Semantic Parser that Uses Statistical Machine Translation , 2007, NAACL.

[11]  Milica Gasic,et al.  Phrase-Based Statistical Language Generation Using Graphical Models and Active Learning , 2010, ACL.

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

[13]  Oliver Lemon,et al.  Optimising Information Presentation for Spoken Dialogue Systems , 2010, ACL.

[14]  Milica Gasic,et al.  The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management , 2010, Comput. Speech Lang..

[15]  Zdenek Zabokrtský,et al.  TectoMT: Modular NLP Framework , 2010, IceTAL.

[16]  Ondrej Dusek,et al.  Formemes in English-Czech Deep Syntactic MT , 2012, WMT@NAACL-HLT.

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

[18]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[19]  Helen F. Hastie,et al.  Conditional Random Fields for Responsive Surface Realisation using Global Features , 2013, ACL.

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

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

[22]  Yoshua Bengio,et al.  On Using Very Large Target Vocabulary for Neural Machine Translation , 2014, ACL.

[23]  Ondrej Dusek,et al.  Training a Natural Language Generator From Unaligned Data , 2015, ACL.

[24]  David Vandyke,et al.  Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking , 2015, SIGDIAL Conference.

[25]  Ondrej Dusek,et al.  New Language Pairs in TectoMT , 2015, WMT@EMNLP.

[26]  Geoffrey E. Hinton,et al.  Grammar as a Foreign Language , 2014, NIPS.

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

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

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

[30]  Marc'Aurelio Ranzato,et al.  Sequence Level Training with Recurrent Neural Networks , 2015, ICLR.

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