Work

Dynamic Entity Representations in Neural Language Models

Year: 2017

Type: conference-paper

Abstract: Understanding a long document requires tracking how entities are introduced and evolve over time.We present a new type of language model, ENTITYNLM, that can explicitly model entities, dynamically update their representations, and contextually generate their mentions.Our model is generative and flexible; it can model an arbitrary number of entities in context while generating each entity mention at an arbitrary length.In addition, it can be used for several different tasks such as language modeling, coreference resolution, and entity prediction.Experimental results with all these tasks demonstrate that our model consistently outperforms strong baselines and prior work.

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

DOI: 10.18653/v1/d17-1195

Authors: Yangfeng Ji, Chenhao Tan, Sebastian Martschat, Yejin Choi, Noah A. Smith

Institutions: University of Washington, Heidelberg University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid