# Sentence Similarity Learning by Lexical Decomposition and Composition

arXiv: https://arxiv.org/abs/1602.07019 · HTML: https://mlsanity.com/paper/1602.07019/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Feb 2016.

## Built on by (most cited first, 16 of 16)

- [Sentence Similarity Based on Contexts](https://mlsanity.com/paper/2105.07623/) (2021)
- [Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents](https://mlsanity.com/paper/2203.02898/) (2022)
- [Question-Answer Sentence Graph for Joint Modeling Answer Selection](https://mlsanity.com/paper/2203.03549/) (2022)
- [SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text](https://mlsanity.com/paper/2411.12764/) (2024)
- [Applying Transfer Learning for Improving Domain-Specific Search Experience Using Query to Question Similarity](https://mlsanity.com/paper/2101.02351/) (2021)
- [A novel hybrid methodology of measuring sentence similarity](https://mlsanity.com/paper/2105.00648/) (2021)
- [LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching](https://mlsanity.com/paper/2108.02915/) (2021)
- [Sharif-STR at SemEval-2024 Task 1: Transformer as a Regression Model for Fine-Grained Scoring of Textual Semantic Relations](https://mlsanity.com/paper/2407.12426/) (2024)
- [Paraphrasing, textual entailment, and semantic similarity above word level](https://mlsanity.com/paper/2208.05387/) (2022)
- [Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders](https://mlsanity.com/paper/2210.05302/) (2022)
- [TexIm FAST: Text-to-Image Representation for Semantic Similarity Evaluation using Transformers](https://mlsanity.com/paper/2406.04438/) (2024)
- [Hierarchical Ranking for Answer Selection](https://mlsanity.com/paper/2102.00677/) (2021)
- [Contextualized Embeddings based Convolutional Neural Networks for Duplicate Question Identification](https://mlsanity.com/paper/2109.01560/) (2021)
- [GAPX: Generalized Autoregressive Paraphrase-Identification X](https://mlsanity.com/paper/2210.01979/) (2022)
- [A General and Flexible Multi-concept Parsing Framework for Multilingual Semantic Matching](https://mlsanity.com/paper/2403.02975/) (2024)
- [R-DEIM Net: An Efficient Rationale-Augmented Dual-Expert Interaction Model for Paraphrase Detection](https://mlsanity.com/paper/2609.30100/) (2026)

## Abstract (arXiv)

Most conventional sentence similarity methods only focus on similar parts of two input sentences, and simply ignore the dissimilar parts, which usually give us some clues and semantic meanings about the sentences. In this work, we propose a model to take into account both the similarities and dissimilarities by decomposing and composing lexical semantics over sentences. The model represents each word as a vector, and calculates a semantic matching vector for each word based on all words in the other sentence. Then, each word vector is decomposed into a similar component and a dissimilar component based on the semantic matching vector. After this, a two-channel CNN model is employed to capture features by composing the similar and dissimilar components. Finally, a similarity score is estimated over the composed feature vectors. Experimental results show that our model gets the state-of-the-art performance on the answer sentence selection task, and achieves a comparable result on the paraphrase identification task.