Work

Globally Coherent Text Generation with Neural Checklist Models

Year: 2016

Type: conference-paper

Abstract: Recurrent neural networks can generate locally coherent text but often have difficulties representing what has already been generatedand what still needs to be said -especially when constructing long texts.We present the neural checklist model, a recurrent neural network that models global coherence by storing and updating an agenda of text strings which should be mentioned somewhere in the output.The model generates output by dynamically adjusting the interpolation among a language model and a pair of attention models that encourage references to agenda items.Evaluations on cooking recipes and dialogue system responses demonstrate high coherence with greatly improved semantic coverage of the agenda.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/d16-1032

Authors: Chloé Kiddon, Luke Zettlemoyer, Yejin Choi

Institution: University of Washington

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, International Science and Technology Center, Defense Advanced Research Projects Agency, Army Research Office

Awards: RI: Small: A Data-Driven Framework to Sketch-to-Text Generation, G5385673730, CAREER: Learning Scalable Models for Grounded Semantic Parsing, G7452299184