# Matching Natural Language Sentences with Hierarchical Sentence Factorization

arXiv: https://arxiv.org/abs/1803.00179 · HTML: https://mlsanity.com/paper/1803.00179/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2018.

## Built on by (most cited first, 5 of 5)

- [Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social-Text Classification](https://mlsanity.com/paper/2209.13017/) (2022)
- [Unbalanced Optimal Transport for Unbalanced Word Alignment](https://mlsanity.com/paper/2306.04116/) (2023)
- [Improving word mover's distance by leveraging self-attention matrix](https://mlsanity.com/paper/2211.06229/) (2022)
- [Similarity Embedding Networks for Robust Human Activity Recognition](https://mlsanity.com/paper/2106.15283/) (2021)
- [TAG: Toward Accurate Social Media Content Tagging with a Concept Graph](https://mlsanity.com/paper/2110.06892/) (2021)

## Abstract (arXiv)

Semantic matching of natural language sentences or identifying the relationship between two sentences is a core research problem underlying many natural language tasks. Depending on whether training data is available, prior research has proposed both unsupervised distance-based schemes and supervised deep learning schemes for sentence matching. However, previous approaches either omit or fail to fully utilize the ordered, hierarchical, and flexible structures of language objects, as well as the interactions between them. In this paper, we propose Hierarchical Sentence Factorization---a technique to factorize a sentence into a hierarchical representation, with the components at each different scale reordered into a "predicate-argument" form. The proposed sentence factorization technique leads to the invention of: 1) a new unsupervised distance metric which calculates the semantic distance between a pair of text snippets by solving a penalized optimal transport problem while preserving the logical relationship of words in the reordered sentences, and 2) new multi-scale deep learning models for supervised semantic training, based on factorized sentence hierarchies. We apply our techniques to text-pair similarity estimation and text-pair relationship classification tasks, based on multiple datasets such as STSbenchmark, the Microsoft Research paraphrase identification (MSRP) dataset, the SICK dataset, etc. Extensive experiments show that the proposed hierarchical sentence factorization can be used to significantly improve the performance of existing unsupervised distance-based metrics as well as multiple supervised deep learning models based on the convolutional neural network (CNN) and long short-term memory (LSTM).