# Contextualized Semantic Distance between Highly Overlapped Texts

arXiv: https://arxiv.org/abs/2110.01176 · HTML: https://mlsanity.com/paper/2110.01176/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 4 Oct 2021.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [An Unsupervised Sentence Embedding Method by Mutual Information Maximization](https://mlsanity.com/paper/2009.12061/) (2020)
- [Lower Perplexity is Not Always Human-Like](https://mlsanity.com/paper/2106.01229/) (2021)
- [Neural Extractive Text Summarization with Syntactic Compression](https://mlsanity.com/paper/1902.00863/) (2019)
- [Incomplete Utterance Rewriting as Semantic Segmentation](https://mlsanity.com/paper/2009.13166/) (2020)
- [Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR](https://mlsanity.com/paper/2008.08896/) (2020)
- [Correlation Coefficients and Semantic Textual Similarity](https://mlsanity.com/paper/1905.07790/) (2019)
- [High-order Semantic Role Labeling](https://mlsanity.com/paper/2010.04641/) (2020)
- [Structured Tuning for Semantic Role Labeling](https://mlsanity.com/paper/2005.00496/) (2020)
- [Global Greedy Dependency Parsing](https://mlsanity.com/paper/1911.08673/) (2019)
- [Syntactically Look-Ahead Attention Network for Sentence Compression](https://mlsanity.com/paper/2002.01145/) (2020)
- [Deleter: Leveraging BERT to Perform Unsupervised Successive Text Compression](https://mlsanity.com/paper/1909.03223/) (2019)

## Built on by (most cited first, 2 of 2)

- [Less than One-shot: Named Entity Recognition via Extremely Weak Supervision](https://mlsanity.com/paper/2311.02861/) (2023)
- [Semantics-Preserved Distortion for Personal Privacy Protection in Information Management](https://mlsanity.com/paper/2201.00965/) (2022)

## Abstract (arXiv)

Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. Better evaluation of the semantic distance between the overlapped sentences benefits the language system's understanding and guides the generation. Since conventional semantic metrics are based on word representations, they are vulnerable to the disturbance of overlapped components with similar representations. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence (LCS) as neighboring words and use masked language modeling (MLM) from pre-trained language models (PLMs) to predict the distributions on their positions. Our metric, Neighboring Distribution Divergence (NDD), represent the semantic distance by calculating the divergence between distributions in the overlapped parts. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts. Based on the discovery, we further implement an unsupervised and training-free method for text compression, leading to a significant improvement on the previous perplexity-based method. The high scalability of our method even enables NDD to outperform the supervised state-of-the-art in domain adaption by a huge margin. Further experiments on syntax and semantics analyses verify the awareness of internal sentence structures, indicating the high potential of NDD for further studies.