# A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations

arXiv: https://arxiv.org/abs/1511.08277 · HTML: https://mlsanity.com/paper/1511.08277/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2015.

## Built on by (most cited first, 30 of 32)

- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities](https://mlsanity.com/paper/2307.16376/) (2023)
- [Streaming Social Event Detection and Evolution Discovery in Heterogeneous Information Networks](https://mlsanity.com/paper/2104.00853/) (2021)
- [DABERT: Dual Attention Enhanced BERT for Semantic Matching](https://mlsanity.com/paper/2210.03454/) (2022)
- [Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges](https://mlsanity.com/paper/2403.00784/) (2024)
- [Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion](https://mlsanity.com/paper/2210.08471/) (2022)
- [Neural ranking models for document retrieval](https://mlsanity.com/paper/2102.11903/) (2021)
- [Learning Fine-grained Fact-Article Correspondence in Legal Cases](https://mlsanity.com/paper/2104.10726/) (2021)
- [A Large Scale Search Dataset for Unbiased Learning to Rank](https://mlsanity.com/paper/2207.03051/) (2022)
- [Paraphrase Identification with Deep Learning: A Review of Datasets and Methods](https://mlsanity.com/paper/2212.06933/) (2022)
- [MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion](https://mlsanity.com/paper/2304.11300/) (2023)
- [Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching](https://mlsanity.com/paper/2101.06423/) (2021)
- [On Length Divergence Bias in Textual Matching Models](https://mlsanity.com/paper/2109.02431/) (2021)
- [Centrality-aware Product Retrieval and Ranking](https://mlsanity.com/paper/2410.15930/) (2024)
- [SPM: Structured Pretraining and Matching Architectures for Relevance Modeling in Meituan Search](https://mlsanity.com/paper/2308.07711/) (2023)
- [Olfactory Label Prediction on Aroma-Chemical Pairs](https://mlsanity.com/paper/2312.16124/) (2023)
- [YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker](https://mlsanity.com/paper/2109.06436/) (2021)
- [TAG: Toward Accurate Social Media Content Tagging with a Concept Graph](https://mlsanity.com/paper/2110.06892/) (2021)
- [Semantic Sentence Composition Reasoning for Multi-Hop Question Answering](https://mlsanity.com/paper/2203.00160/) (2022)
- [TeKo: Text-Rich Graph Neural Networks with External Knowledge](https://mlsanity.com/paper/2206.07253/) (2022)
- [Effective and Efficient Query-aware Snippet Extraction for Web Search](https://mlsanity.com/paper/2210.08809/) (2022)
- [DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection](https://mlsanity.com/paper/2210.13845/) (2022)
- [The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims](https://mlsanity.com/paper/2411.14072/) (2024)
- [Standardization of Weighted Ranking Correlation Coefficients](https://mlsanity.com/paper/2504.08428/) (2025)
- [You Only Forward Once: An Efficient Compositional Judging Paradigm](https://mlsanity.com/paper/2511.16600/) (2025)
- [Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search](https://mlsanity.com/paper/2101.04850/) (2021)
- [Locate Who You Are: Matching Geo-location to Text for User Identity Linkage](https://mlsanity.com/paper/2104.09119/) (2021)
- [Toward the Understanding of Deep Text Matching Models for Information Retrieval](https://mlsanity.com/paper/2108.07081/) (2021)
- [Mirror Matching: Document Matching Approach in Seed-driven Document Ranking for Medical Systematic Reviews](https://mlsanity.com/paper/2112.14318/) (2021)
- [Profiling and Evolution of Intellectual Property](https://mlsanity.com/paper/2204.09333/) (2022)

## Abstract (arXiv)

Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching. However, such methods cannot well capture the contextualized local information in the matching process. To tackle this problem, we present a new deep architecture to match two sentences with multiple positional sentence representations. Specifically, each positional sentence representation is a sentence representation at this position, generated by a bidirectional long short term memory (Bi-LSTM). The matching score is finally produced by aggregating interactions between these different positional sentence representations, through k-Max pooling and a multi-layer perceptron. Our model has several advantages: (1) By using Bi-LSTM, rich context of the whole sentence is leveraged to capture the contextualized local information in each positional sentence representation; (2) By matching with multiple positional sentence representations, it is flexible to aggregate different important contextualized local information in a sentence to support the matching; (3) Experiments on different tasks such as question answering and sentence completion demonstrate the superiority of our model.