Learning Cross-Context Entity Representations from Text
Jeffrey Ling, Nicholas FitzGerald, Zifei Shan, Livio Baldini Soares,, Thibault F\'evry, David Weiss, Tom Kwiatkowski

TL;DR
This paper introduces a fill-in-the-blank training method to learn high-quality, context-independent entity representations from text, demonstrating improvements across entity typing, linking, and trivia question answering tasks.
Contribution
The authors propose a novel fill-in-the-blank approach for entity representation learning, achieving state-of-the-art results without relying on external knowledge bases or linking-specific features.
Findings
64% error reduction on TypeNet benchmark
Achieved 89.8% on TAC-KBP 2010 without external resources
Successfully answered trivia questions with fine-grained entity types
Abstract
Language modeling tasks, in which words, or word-pieces, are predicted on the basis of a local context, have been very effective for learning word embeddings and context dependent representations of phrases. Motivated by the observation that efforts to code world knowledge into machine readable knowledge bases or human readable encyclopedias tend to be entity-centric, we investigate the use of a fill-in-the-blank task to learn context independent representations of entities from the text contexts in which those entities were mentioned. We show that large scale training of neural models allows us to learn high quality entity representations, and we demonstrate successful results on four domains: (1) existing entity-level typing benchmarks, including a 64% error reduction over previous work on TypeNet (Murty et al., 2018); (2) a novel few-shot category reconstruction task; (3) existing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Data Quality and Management
