arXiv 论文撤稿：基于整句语义的词汇替换无监督候选词排序研究（arXiv:2509.11513）
Unsupervised Candidate Ranking for Lexical Substitution via Holistic Sentence Semantics
AI 导读
作者 Zhongyang Hu 撤回了 arXiv:2509.11513 这篇关于词汇替换候选词无监督排序的论文，撤稿原因是另一篇同名论文已被接收，内容略有不同。原论文提出基于注意力权重和 integrated gradients 两种方法度量上下文 token 对目标 token 的影响，并结合替换前后句子的语义相似度对候选词排序，在 LS07 和 SWORDS 数据集上均提升了排序效果。
正文 · 原文
This paper has been withdrawn by Zhongyang Hu
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.
| Comments: | A paper I recently submitted has been accepted; it shares the same title but the content is slightly different. |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2509.11513 [cs.CL] |
| (or arXiv:2509.11513v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2509.11513 arXiv-issued DOI via DataCite |
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Wed, 11 Nov 2026 13:19:28 UTC (1 KB) (withdrawn)
来源：arXiv cs.AI · arxiv.org