# Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences

arXiv: https://arxiv.org/abs/1810.02938 · HTML: https://mlsanity.com/paper/1810.02938/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2018.

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

- [DABERT: Dual Attention Enhanced BERT for Semantic Matching](https://mlsanity.com/paper/2210.03454/) (2022)
- [Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion](https://mlsanity.com/paper/2210.08471/) (2022)
- [Paraphrase Identification with Deep Learning: A Review of Datasets and Methods](https://mlsanity.com/paper/2212.06933/) (2022)
- [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)
- [Noise Contrastive Estimation-based Matching Framework for Low-Resource Security Attack Pattern Recognition](https://mlsanity.com/paper/2401.10337/) (2024)
- [RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm](https://mlsanity.com/paper/2301.02807/) (2023)
- [LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching](https://mlsanity.com/paper/2108.02915/) (2021)
- [Description-Enhanced Label Embedding Contrastive Learning for Text Classification](https://mlsanity.com/paper/2306.08817/) (2023)
- [Multi-turn Response Selection with Commonsense-enhanced Language Models](https://mlsanity.com/paper/2407.18479/) (2024)

## Abstract (arXiv)

Learning a matching function between two text sequences is a long standing problem in NLP research. This task enables many potential applications such as question answering and paraphrase identification. This paper proposes Co-Stack Residual Affinity Networks (CSRAN), a new and universal neural architecture for this problem. CSRAN is a deep architecture, involving stacked (multi-layered) recurrent encoders. Stacked/Deep architectures are traditionally difficult to train, due to the inherent weaknesses such as difficulty with feature propagation and vanishing gradients. CSRAN incorporates two novel components to take advantage of the stacked architecture. Firstly, it introduces a new bidirectional alignment mechanism that learns affinity weights by fusing sequence pairs across stacked hierarchies. Secondly, it leverages a multi-level attention refinement component between stacked recurrent layers. The key intuition is that, by leveraging information across all network hierarchies, we can not only improve gradient flow but also improve overall performance. We conduct extensive experiments on six well-studied text sequence matching datasets, achieving state-of-the-art performance on all.