This paper has been withdrawn by Zhongyang Hu
[Submitted on 15 Sep 2025 (v1), last revised 11 Nov 2026 (this version, v2)]
No PDF available, click to view other formats
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.
Submission history
From: Zhongyang Hu [view email]
[v1] Mon, 15 Sep 2025 01:57:09 UTC (18 KB)
[v2] Wed, 11 Nov 2026 13:19:28 UTC (1 KB) (withdrawn)
