Concurrent Learning of Semantic Relations

TL;DR

This paper explores multi-task and semi-supervised learning approaches to improve the detection of semantic relations between words, demonstrating that concurrent learning of multiple relations enhances performance across various scenarios.

Contribution

It introduces a multi-task learning framework for semantic relation detection and shows that concurrent learning of multiple relations improves accuracy with limited labeled data.

Findings

Concurrent learning improves relation detection performance.

Semi-supervised approach benefits from unlabeled data.

State-of-the-art features enhance learning effectiveness.

Abstract

Discovering whether words are semantically related and identifying the specific semantic relation that holds between them is of crucial importance for NLP as it is essential for tasks like query expansion in IR. Within this context, different methodologies have been proposed that either exclusively focus on a single lexical relation (e.g. hypernymy vs. random) or learn specific classifiers capable of identifying multiple semantic relations (e.g. hypernymy vs. synonymy vs. random). In this paper, we propose another way to look at the problem that relies on the multi-task learning paradigm. In particular, we want to study whether the learning process of a given semantic relation (e.g. hypernymy) can be improved by the concurrent learning of another semantic relation (e.g. co-hyponymy). Within this context, we particularly examine the benefits of semi-supervised learning where the training of a prediction function is performed over few labeled data jointly with many unlabeled ones. Preliminary results based on simple learning strategies and state-of-the-art distributional feature representations show that concurrent learning can lead to improvements in a vast majority of tested situations.