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

Jannis Vamvas, Rico Sennrich

Submission Type: Regular Short Paper

Submission Track: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.

Keywords: recognizing semantic differences, semantic similarity, multilinguality

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.

Submission Number: 510