Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Borchert, Philipp, De Weerdt, Jochen, Moens, Marie-Francine
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913281875116032
author Borchert, Philipp
De Weerdt, Jochen
Moens, Marie-Francine
author_facet Borchert, Philipp
De Weerdt, Jochen
Moens, Marie-Francine
contents Differentiating relationships between entity pairs with limited labeled instances poses a significant challenge in few-shot relation classification. Representations of textual data extract rich information spanning the domain, entities, and relations. In this paper, we introduce a novel approach to enhance information extraction combining multiple sentence representations and contrastive learning. While representations in relation classification are commonly extracted using entity marker tokens, we argue that substantial information within the internal model representations remains untapped. To address this, we propose aligning multiple sentence representations, such as the [CLS] token, the [MASK] token used in prompting, and entity marker tokens. Our method employs contrastive learning to extract complementary discriminative information from these individual representations. This is particularly relevant in low-resource settings where information is scarce. Leveraging multiple sentence representations is especially effective in distilling discriminative information for relation classification when additional information, like relation descriptions, are not available. We validate the adaptability of our approach, maintaining robust performance in scenarios that include relation descriptions, and showcasing its flexibility to adapt to different resource constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16543
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning
Borchert, Philipp
De Weerdt, Jochen
Moens, Marie-Francine
Computation and Language
Artificial Intelligence
Differentiating relationships between entity pairs with limited labeled instances poses a significant challenge in few-shot relation classification. Representations of textual data extract rich information spanning the domain, entities, and relations. In this paper, we introduce a novel approach to enhance information extraction combining multiple sentence representations and contrastive learning. While representations in relation classification are commonly extracted using entity marker tokens, we argue that substantial information within the internal model representations remains untapped. To address this, we propose aligning multiple sentence representations, such as the [CLS] token, the [MASK] token used in prompting, and entity marker tokens. Our method employs contrastive learning to extract complementary discriminative information from these individual representations. This is particularly relevant in low-resource settings where information is scarce. Leveraging multiple sentence representations is especially effective in distilling discriminative information for relation classification when additional information, like relation descriptions, are not available. We validate the adaptability of our approach, maintaining robust performance in scenarios that include relation descriptions, and showcasing its flexibility to adapt to different resource constraints.
title Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2403.16543