mlsanityData to 14 Oct 2026

Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders

arXiv 2210.05302 ↗First posted 11 Oct 2022cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 48 references that are in the map. First posted on arXiv 11 Oct 2022.

Builds on

25 of 48 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  7. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  8. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 1,003
  9. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 432
  10. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 402
  11. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  12. 2015Skip-Thought Vectorscited by 322
13 more
  1. 2017Efficient Natural Language Response Suggestion for Smart Replycited by 229
  2. 2021Whitening Sentence Representations for Better Semantics and Faster Retrievalcited by 202
  3. 2016Enhanced LSTM for Natural Language Inferencecited by 200
  4. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  5. 2020Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Taskscited by 138
  6. 2017Bilateral Multi-Perspective Matching for Natural Language Sentencescited by 121
  7. 2020On the Sentence Embeddings from Pre-trained Language Modelscited by 83
  8. 2017A Continuously Growing Dataset of Sentential Paraphrasescited by 72
  9. 2016Text Matching as Image Recognitioncited by 59
  10. 2016Sentence Similarity Learning by Lexical Decomposition and Compositioncited by 16
  11. 2019Transfer Fine-Tuning: A BERT Case Studycited by 8
  12. 2018Character-based Neural Networks for Sentence Pair Modelingcited by 4
  13. 2019Explicit Pairwise Word Interaction Modeling Improves Pretrained Transformers for English Semantic Similarity Taskscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Paraphrase Identification with Deep Learning: A Review of Datasets and Methodscited by 13