A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency

Abstract

Definition Extraction (DE) is one of the well-known topics in Information Extraction that aims to identify terms and their corresponding definitions in unstructured texts. This task can be formalized either as a sentence classification task (i.e., containing term-definition pairs or not) or a sequential labeling task (i.e., identifying the boundaries of the terms and definitions). The previous works for DE have only focused on one of the two approaches, failing to model the inter-dependencies between the two tasks. In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies. Our model features deep learning architectures to exploit the global structures of the input sentences as well as the semantic consistencies between the terms and the definitions, thereby improving the quality of the representation vectors for DE. Besides the joint inference between sentence classification and sequential labeling, the proposed model is fundamentally different from the prior work for DE in that the prior work has only employed the local structures of the input sentences (i.e., word-to-word relations), and not yet considered the semantic consistencies between terms and definitions. In order to implement these novel ideas, our model presents a multi-task learning framework that employs graph convolutional neural networks and predicts the dependency paths between the terms and the definitions. We also seek to enforce the consistency between the representations of the terms and definitions both globally (i.e., increasing semantic consistency between the representations of the entire sentences and the terms/definitions) and locally (i.e., promoting the similarity between the representations of the terms and the definitions). The extensive experiments on three benchmark datasets demonstrate the effectiveness of our approach.1

Definition Extraction from Generic and Mathematical Domains with Deep Ensemble Learning

“…To see that our approach may be used for general definitions as well, we have chosen the WCL dataset [15], the W00 dataset [15] and the DEFT dataset [34]. The DefMiner system (used here as one of the baselines) is the system that was first applied to W00, and to this day it produced the best results on it; several systems that were suggested in the literature [1,20,42], were unable to outperform the DefMiner system on W00.…”

WIKITIDE: A WIKIPEDIA-BASED TIMESTAMPED DEFINITION Pairs Dataset

“…Definitions Definitions have traditionally played a crucial role in NLP and computational lexicography. As the building blocks of dictionaries and encyclopedias, they are used when the meaning of a word is sought (Navigli and Velardi, 2010), and thus the task of automatically constructing glossaries and terminologies is a well established task in NLP and Information Retrieval (Espinosa-Anke and Schockaert, 2018;Spala et al, 2019Spala et al, , 2020Veyseh et al, 2020;Azarbonyad et al, 2023).…”

Graphine: A Dataset for Graph-aware Terminology Definition Generation

“…Existing works related to terminology definition mainly focus on definition extraction (Westerhout, 2009;Anke and Schockaert, 2018;Veyseh et al, 2020;Li et al, 2016) and technology entity recognition (Fahmi and Bouma, 2006;Gao et al, 2018). Definitions are extracted from different sources, such as Wikipedia (Espinosa-Anke and Saggion, 2014; Li et al, 2016) and scholarly articles (Jin et al, 2013;Spala et al, 2019).…”