Multilingual Relation Extraction using Compositional Universal Schema

TL;DR

This paper presents an advanced multilingual relation extraction model based on universal schema, capable of generalizing to unseen patterns and languages, significantly improving knowledge base construction without relying on extensive manual annotations.

Contribution

It introduces a neural compositional approach to universal schema that enhances coverage, enables multilingual transfer, and improves relation extraction for unseen entities and languages.

Findings

Outperforms previous top systems on TAC KBP benchmarks.

Achieves accurate relation extraction in Spanish without Spanish annotations.

Multilingual training boosts English relation extraction accuracy.

Abstract

Universal schema builds a knowledge base (KB) of entities and relations by jointly embedding all relation types from input KBs as well as textual patterns expressing relations from raw text. In most previous applications of universal schema, each textual pattern is represented as a single embedding, preventing generalization to unseen patterns. Recent work employs a neural network to capture patterns' compositional semantics, providing generalization to all possible input text. In response, this paper introduces significant further improvements to the coverage and flexibility of universal schema relation extraction: predictions for entities unseen in training and multilingual transfer learning to domains with no annotation. We evaluate our model through extensive experiments on the English and Spanish TAC KBP benchmark, outperforming the top system from TAC 2013 slot-filling using no handwritten patterns or additional annotation. We also consider a multilingual setting in which English training data entities overlap with the seed KB, but Spanish text does not. Despite having no annotation for Spanish data, we train an accurate predictor, with additional improvements obtained by tying word embeddings across languages. Furthermore, we find that multilingual training improves English relation extraction accuracy. Our approach is thus suited to broad-coverage automated knowledge base construction in a variety of languages and domains.