cs.CLSep 15, 2025

Unsupervised Candidate Ranking for Lexical Substitution via Holistic Sentence Semantics

Authors: Zhongyang Hu, Naijie Gu, Xiangzhi Tao, Tianhui Gu, Yibing Zhou

Organizations: University of Science and Technology of China

Abstract

A key subtask in lexical substitution is ranking the given candidate words. A common approach is to replace the target word with a candidate in the original sentence and feed the modified sentence into a model to capture semantic differences before and after substitution. However, effectively modeling the bidirectional influence of candidate substitution on both the target word and its context remains challenging. Existing methods often focus solely on semantic changes at the target position or rely on parameter tuning over multiple evaluation metrics, making it difficult to accurately characterize semantic variation. To address this, we investigate two approaches: one based on attention weights and another leveraging the more interpretable integrated gradients method, both designed to measure the influence of context tokens on the target token and to rank candidates by incorporating semantic similarity between the original and substituted sentences. Experiments on the LS07 and SWORDS datasets demonstrate that both approaches improve ranking performance.

Figures & tables

Explore similar work

CardsList
  1. Evaluating the Evaluator: Problems with SemEval-2020 Task 1 for Lexical Semantic Change Detection

    Apr 14, 2026Bach Phan-Tat, Kris Heylen, Dirk Geeraerts +2Semantic Change Detection

  2. The BD-LSC Dataset: Facilitating the Benchmarking of Models for Lexical Semantic Change Detection in Slang and Standard Usage

    Jun 15, 2026Afnan Aloraini, Riza Batista-NavarroSemantic Change DetectionWord Sense Disambiguation

  3. Rethinking Metrics for Lexical Semantic Change Detection

    Feb 17, 2026Roksana Goworek, Haim DubossarskySemantic Change DetectionDistributional Semantics