Context-Dependent Fine-Grained Entity Type Tagging
This addresses the issue of poor generalization in entity tagging for NLP applications, but it is incremental as it builds on existing fine-grained tagging methods.
The paper tackles the problem of spurious labels in fine-grained entity type tagging by proposing context-dependent fine type tagging, where labels are restricted to those deducible from local context, and introduces a new dataset of 12,017 annotated mentions with baseline results.
Entity type tagging is the task of assigning category labels to each mention of an entity in a document. While standard systems focus on a small set of types, recent work (Ling and Weld, 2012) suggests that using a large fine-grained label set can lead to dramatic improvements in downstream tasks. In the absence of labeled training data, existing fine-grained tagging systems obtain examples automatically, using resolved entities and their types extracted from a knowledge base. However, since the appropriate type often depends on context (e.g. Washington could be tagged either as city or government), this procedure can result in spurious labels, leading to poorer generalization. We propose the task of context-dependent fine type tagging, where the set of acceptable labels for a mention is restricted to only those deducible from the local context (e.g. sentence or document). We introduce new resources for this task: 12,017 mentions annotated with their context-dependent fine types, and we provide baseline experimental results on this data.