Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents

Jannis Vamvas, Rico Sennrich
5/22/2023
cs.CL

Official code: ZurichNLP/recognizing-semantic-differences (2 stars, MIT, last commit 2025-06-23).

Abstract

Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications. We formulate recognizing semantic differences (RSD) as a token-level regression task and study three unsupervised approaches that rely on a masked language model. To assess the approaches, we begin with basic English sentences and gradually move to more complex, cross-lingual document pairs. Our results show that an approach based on word alignment and sentence-level contrastive learning has a robust correlation to gold labels. However, all unsupervised approaches still leave a large margin of improvement. Code to reproduce our experiments is available at https://github.com/ZurichNLP/recognizing-semantic-differences

View on arXivView PDF

Code Implementations(1)

ZurichNLP/recognizing-semantic-differencesOfficial100%
MIT

Code for the paper "Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents"

21PythonMay 22, 20231 years agoMIT

Similar Papers

Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences

86% match2023

SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents

83% match2025

Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring

82% match2026

mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learning

81% match2023

From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification

81% match2026

Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages

81% match1 repo62023

Cite this paper

@article{vamvas2023towards,
  title  = {Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents},
  author = {Jannis Vamvas and Rico Sennrich},
  year   = {2023},
  eprint = {2305.13303},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.13303v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.13303.svg)](https://codeofpaper.com/paper/2305.13303)

Discussion