Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction

TL;DR

This paper introduces two novel encoder-decoder based methods for joint entity and relation extraction from text, effectively handling overlapping entities and multiple relation tuples, and demonstrates superior performance on a benchmark dataset.

Contribution

The paper presents two innovative encoder-decoder approaches for joint extraction of entities and relations, improving over prior pipeline methods by capturing interactions among tuples.

Findings

Outperforms previous methods on the NYT corpus with higher F1 scores.

Handles overlapping entities and multiple relation tuples effectively.

Uses a representation scheme and pointer network-based decoding for improved extraction.

Abstract

A relation tuple consists of two entities and the relation between them, and often such tuples are found in unstructured text. There may be multiple relation tuples present in a text and they may share one or both entities among them. Extracting such relation tuples from a sentence is a difficult task and sharing of entities or overlapping entities among the tuples makes it more challenging. Most prior work adopted a pipeline approach where entities were identified first followed by finding the relations among them, thus missing the interaction among the relation tuples in a sentence. In this paper, we propose two approaches to use encoder-decoder architecture for jointly extracting entities and relations. In the first approach, we propose a representation scheme for relation tuples which enables the decoder to generate one word at a time like machine translation models and still finds all the tuples present in a sentence with full entity names of different length and with overlapping entities. Next, we propose a pointer network-based decoding approach where an entire tuple is generated at every time step. Experiments on the publicly available New York Times corpus show that our proposed approaches outperform previous work and achieve significantly higher F1 scores.