Building a Fine-Grained Entity Typing System Overnight for a New X (X = Language, Domain, Genre)

TL;DR

This paper introduces an unsupervised, adaptable entity typing system that leverages semantic embeddings and linguistic structures, enabling rapid deployment across diverse languages, domains, and genres without requiring labeled data.

Contribution

The proposed framework is the first to combine symbolic and distributional semantics in an unsupervised manner for fine-grained entity typing, adaptable to new languages and domains.

Findings

Achieves comparable performance to supervised systems on news and forum data.

Demonstrates portability across multiple languages including English, Chinese, Japanese, Hausa, and Yoruba.

Effectively adapts to various domains such as general and biomedical texts.

Abstract

Recent research has shown great progress on fine-grained entity typing. Most existing methods require pre-defining a set of types and training a multi-class classifier from a large labeled data set based on multi-level linguistic features. They are thus limited to certain domains, genres and languages. In this paper, we propose a novel unsupervised entity typing framework by combining symbolic and distributional semantics. We start from learning general embeddings for each entity mention, compose the embeddings of specific contexts using linguistic structures, link the mention to knowledge bases and learn its related knowledge representations. Then we develop a novel joint hierarchical clustering and linking algorithm to type all mentions using these representations. This framework doesn't rely on any annotated data, predefined typing schema, or hand-crafted features, therefore it can be quickly adapted to a new domain, genre and language. Furthermore, it has great flexibility at incorporating linguistic structures (e.g., Abstract Meaning Representation (AMR), dependency relations) to improve specific context representation. Experiments on genres (news and discussion forum) show comparable performance with state-of-the-art supervised typing systems trained from a large amount of labeled data. Results on various languages (English, Chinese, Japanese, Hausa, and Yoruba) and domains (general and biomedical) demonstrate the portability of our framework.