Compositional approaches for representing relations between words: A comparative study



Hakami, Huda and Bollegala, Danushka ORCID: 0000-0003-4476-7003
(2017) Compositional approaches for representing relations between words: A comparative study. KNOWLEDGE-BASED SYSTEMS, 136. pp. 172-182.

This is the latest version of this item.

[img] Text
Compositionality for RelRep.pdf - Submitted version

Download (603kB)
[img] Text
Compositionality for RelRep.pdf - Author Accepted Manuscript

Download (558kB)
[img] Text
Compositionality for RelRep.pdf - Author Accepted Manuscript

Download (603kB)

Abstract

Identifying the relations that exist between words (or entities) is important for various natural language processing tasks such as, relational search, noun-modifier classification and analogy detection. A popular approach to represent the relations between a pair of words is to extract the patterns in which the words co-occur with from a corpus, and assign each word-pair a vector of pattern frequencies. Despite the simplicity of this approach, it suffers from data sparseness, information scalability and linguistic creativity as the model is unable to handle previously unseen word pairs in a corpus. In contrast, a compositional approach for representing relations between words overcomes these issues by using the attributes of each individual word to indirectly compose a representation for the common relations that hold between the two words. This study aims to compare different operations for creating relation representations from word-level representations. We investigate the performance of the compositional methods by measuring the relational similarities using several benchmark datasets for word analogy. Moreover, we evaluate the different relation representations in a knowledge base completion task.

Item Type: Article
Uncontrolled Keywords: Relation representations, Compositional semantics, Semantic relations, Relational similarity
Depositing User: Symplectic Admin
Date Deposited: 17 Apr 2018 06:32
Last Modified: 19 Jan 2023 06:35
DOI: 10.1016/j.knosys.2017.09.008
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3020233

Available Versions of this Item