DeepAI AI Chat
Log In Sign Up

Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring?

by   Lena Reed, et al.
University of California Santa Cruz

Responses in task-oriented dialogue systems often realize multiple propositions whose ultimate form depends on the use of sentence planning and discourse structuring operations. For example a recommendation may consist of an explicitly evaluative utterance e.g. Chanpen Thai is the best option, along with content related by the justification discourse relation, e.g. It has great food and service, that combines multiple propositions into a single phrase. While neural generation methods integrate sentence planning and surface realization in one end- to-end learning framework, previous work has not shown that neural generators can: (1) perform common sentence planning and discourse structuring operations; (2) make decisions as to whether to realize content in a single sentence or over multiple sentences; (3) generalize sentence planning and discourse relation operations beyond what was seen in training. We systematically create large training corpora that exhibit particular sentence planning operations and then test neural models to see what they learn. We compare models without explicit latent variables for sentence planning with ones that provide explicit supervision during training. We show that only the models with additional supervision can reproduce sentence planing and discourse operations and generalize to situations unseen in training.


page 1

page 2

page 3

page 4


DisSent: Sentence Representation Learning from Explicit Discourse Relations

Sentence vectors represent an appealing approach to meaning: learn an em...

Mining Discourse Markers for Unsupervised Sentence Representation Learning

Current state of the art systems in NLP heavily rely on manually annotat...

TransSent: Towards Generation of Structured Sentences with Discourse Marker

This paper focuses on the task of generating long structured sentences w...

Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

Natural language generators for task-oriented dialogue must effectively ...

Hierarchical Text Generation and Planning for Strategic Dialogue

End-to-end models for strategic dialogue are challenging to train, becau...

Reframing Societal Discourse as Requirements Negotiation: Vision Statement

Challenges in spatial planning include adjusting settlement patterns to ...

WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse

We release a corpus of 43 million atomic edits across 8 languages. These...