mlsanityData to 13 Oct 2026

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

arXiv 2305.13303 ↗First posted 22 May 2023cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Builds on 16 of its 24 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

16 of 24 references.

References · 16

  1. 2017Attention Is All You Needcited by 60,106
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,107
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,480
  5. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,916
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,170
  7. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 400
  8. 2021Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translationcited by 334
  9. 2019PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identificationcited by 263
  10. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 155
  11. 2021Measuring and Increasing Context Usage in Context-Aware Machine Translationcited by 48
  12. 2020It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Informationcited by 26
4 more
  1. 2021Translation Error Detection as Rationale Extractioncited by 22
  2. 2023The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metricscited by 15
  3. 2022Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learningcited by 13
  4. 2016Interpretable Semantic Textual Similarity: Finding and explaining differences between sentencescited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Interpretable Text Embeddings and Text Similarity Explanation: A Surveycited by 12
  2. 2025FAID: Fine-Grained AI-Generated Text Detection Using Multi-Task Auxiliary and Multi-Level Contrastive Learningcited by 5
  3. 202520min-XD: A Comparable Corpus of Swiss News Articlescited by 2
  4. 2026Scaling Unsupervised Word Alignment to Documents via Structural Constraintscited by 1
  5. 2026Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanationscited by 0