# Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference

arXiv: https://arxiv.org/abs/1801.00102 · HTML: https://mlsanity.com/paper/1801.00102/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2017.

## Built on by (most cited first, 10 of 10)

- [Rethinking Search: Making Domain Experts out of Dilettantes](https://mlsanity.com/paper/2105.02274/) (2021)
- [Probing Multimodal Large Language Models for Global and Local Semantic Representations](https://mlsanity.com/paper/2402.17304/) (2024)
- [Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inference](https://mlsanity.com/paper/2405.12434/) (2024)
- [Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents](https://mlsanity.com/paper/2203.02898/) (2022)
- [SILT: Efficient transformer training for inter-lingual inference](https://mlsanity.com/paper/2103.09635/) (2021)
- [Context-Aware Interaction Network for Question Matching](https://mlsanity.com/paper/2104.08451/) (2021)
- [BERT-DRE: BERT with Deep Recursive Encoder for Natural Language Sentence Matching](https://mlsanity.com/paper/2111.02188/) (2021)
- [DEIM: An effective deep encoding and interaction model for sentence matching](https://mlsanity.com/paper/2203.10482/) (2022)
- [MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text Classification](https://mlsanity.com/paper/2204.04952/) (2022)
- [KETM:A Knowledge-Enhanced Text Matching method](https://mlsanity.com/paper/2308.06235/) (2023)

## Abstract (arXiv)

This paper presents a new deep learning architecture for Natural Language Inference (NLI). Firstly, we introduce a new architecture where alignment pairs are compared, compressed and then propagated to upper layers for enhanced representation learning. Secondly, we adopt factorization layers for efficient and expressive compression of alignment vectors into scalar features, which are then used to augment the base word representations. The design of our approach is aimed to be conceptually simple, compact and yet powerful. We conduct experiments on three popular benchmarks, SNLI, MultiNLI and SciTail, achieving competitive performance on all. A lightweight parameterization of our model also enjoys a ≈ 3 times reduction in parameter size compared to the existing state-of-the-art models, e.g., ESIM and DIIN, while maintaining competitive performance. Additionally, visual analysis shows that our propagated features are highly interpretable.