Linguistically Conditioned Semantic Textual Similarity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tu, Jingxuan, Xu, Keer, Yue, Liulu, Ye, Bingyang, Rim, Kyeongmin, Pustejovsky, James
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917686368272384
author Tu, Jingxuan
Xu, Keer
Yue, Liulu
Ye, Bingyang
Rim, Kyeongmin
Pustejovsky, James
author_facet Tu, Jingxuan
Xu, Keer
Yue, Liulu
Ye, Bingyang
Rim, Kyeongmin
Pustejovsky, James
contents Semantic textual similarity (STS) is a fundamental NLP task that measures the semantic similarity between a pair of sentences. In order to reduce the inherent ambiguity posed from the sentences, a recent work called Conditional STS (C-STS) has been proposed to measure the sentences' similarity conditioned on a certain aspect. Despite the popularity of C-STS, we find that the current C-STS dataset suffers from various issues that could impede proper evaluation on this task. In this paper, we reannotate the C-STS validation set and observe an annotator discrepancy on 55% of the instances resulting from the annotation errors in the original label, ill-defined conditions, and the lack of clarity in the task definition. After a thorough dataset analysis, we improve the C-STS task by leveraging the models' capability to understand the conditions under a QA task setting. With the generated answers, we present an automatic error identification pipeline that is able to identify annotation errors from the C-STS data with over 80% F1 score. We also propose a new method that largely improves the performance over baselines on the C-STS data by training the models with the answers. Finally we discuss the conditionality annotation based on the typed-feature structure (TFS) of entity types. We show in examples that the TFS is able to provide a linguistic foundation for constructing C-STS data with new conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03673
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Linguistically Conditioned Semantic Textual Similarity
Tu, Jingxuan
Xu, Keer
Yue, Liulu
Ye, Bingyang
Rim, Kyeongmin
Pustejovsky, James
Computation and Language
Artificial Intelligence
Semantic textual similarity (STS) is a fundamental NLP task that measures the semantic similarity between a pair of sentences. In order to reduce the inherent ambiguity posed from the sentences, a recent work called Conditional STS (C-STS) has been proposed to measure the sentences' similarity conditioned on a certain aspect. Despite the popularity of C-STS, we find that the current C-STS dataset suffers from various issues that could impede proper evaluation on this task. In this paper, we reannotate the C-STS validation set and observe an annotator discrepancy on 55% of the instances resulting from the annotation errors in the original label, ill-defined conditions, and the lack of clarity in the task definition. After a thorough dataset analysis, we improve the C-STS task by leveraging the models' capability to understand the conditions under a QA task setting. With the generated answers, we present an automatic error identification pipeline that is able to identify annotation errors from the C-STS data with over 80% F1 score. We also propose a new method that largely improves the performance over baselines on the C-STS data by training the models with the answers. Finally we discuss the conditionality annotation based on the typed-feature structure (TFS) of entity types. We show in examples that the TFS is able to provide a linguistic foundation for constructing C-STS data with new conditions.
title Linguistically Conditioned Semantic Textual Similarity
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2406.03673