Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders
Previous works have demonstrated the effectiveness of utilising pre-trained sentence encoders based on their sentence representations for meaning comparison tasks. Though such representations are shown to capture hidden syntax structures, the direct similarity comparison between them exhibits weak sensitivity to word order and structural differences in given sentences. A single similarity score further makes the comparison process hard to interpret. Therefore, we here propose to combine sentence encoders with an alignment component by representing each sentence as a list of predicate-argument spans (where their span representations are derived from sentence encoders), and decomposing the sentence-level meaning comparison into the alignment between their spans for paraphrase identification tasks. Empirical results show that the alignment component brings in both improved performance and interpretability for various sentence encoders. After closer investigation, the proposed approach indicates increased sensitivity to structural difference and enhanced ability to distinguish non-paraphrases with high lexical overlap.
Code (0)
등록된 구현이 없습니다.
Tasks
Paraphrase IdentificationSensitivitySentenceSimilar Papers 제목 키워드 기반
RuPAWS: A Russian Adversarial Dataset for Paraphrase Identification
Paraphrase identification task can be easily challenged by changing word order, e.g. as in “Can a good person become bad?”. While for English this problem was tackled by the PAWS dataset (Zhang et al., 2019), datasets fo…
Paraphrase IdentificationRoParQ: Paraphrase-Aware Alignment of Large Language Models Towards Robustness to Paraphrased Questions
Large Language Models (LLMs) often exhibit inconsistent behavior when answering paraphrased questions, suggesting a reliance on surface-level patterns rather than true semantic understanding. To address this limitation, …
Improving Large-scale Paraphrase Acquisition and Generation
This paper addresses the quality issues in existing Twitter-based paraphrase datasets, and discusses the necessity of using two separate definitions of paraphrase for identification and generation tasks. We present a new…
Language ModelingLanguage ModellingParaphrase GenerationParaphrase Identification+1Discriminative Phrase Embedding for Paraphrase Identification
This work, concerning paraphrase identification task, on one hand contributes to expanding deep learning embeddings to include continuous and discontinuous linguistic phrases. On the other hand, it comes up with a new sc…
Paraphrase IdentificationParaphrase Identification with Deep Learning: A Review of Datasets and Methods
The rapid progress of Natural Language Processing (NLP) technologies has led to the widespread availability and effectiveness of text generation tools such as ChatGPT and Claude. While highly useful, these technologies a…
Paraphrase IdentificationText Generation