[CaCL] Thursday: Dynamic Entity Representations in Neural Language Models (Ji et al 2017)

Jaffe, Evan jaffe.59 at buckeyemail.osu.edu
Fri Jan 24 16:43:02 EST 2020


Hi all,
Let's read Ji et al 2017 (EMNLP) for Thursday. https://www.aclweb.org/anthology/D17-1195.pdf. Abstract below - see you then!

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.

-Evan
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osu.edu/pipermail/cacl/attachments/20200124/a071b9ce/attachment.html>


More information about the CaCL mailing list