# Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling

arXiv: https://arxiv.org/abs/2210.05261 · HTML: https://mlsanity.com/paper/2210.05261/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [SentEval: An Evaluation Toolkit for Universal Sentence Representations](https://mlsanity.com/paper/1803.05449/) (2018)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking](https://mlsanity.com/paper/2110.07367/) (2021)
- [The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems](https://mlsanity.com/paper/1506.08909/) (2015)
- [Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring](https://mlsanity.com/paper/1905.01969/) (2019)
- [Semantic Models for the First-stage Retrieval: A Comprehensive Review](https://mlsanity.com/paper/2103.04831/) (2021)
- [SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval](https://mlsanity.com/paper/2009.13013/) (2020)
- [Efficient Document Re-Ranking for Transformers by Precomputing Term Representations](https://mlsanity.com/paper/2004.14255/) (2020)
- [DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering](https://mlsanity.com/paper/2005.00697/) (2020)
- [DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding](https://mlsanity.com/paper/2002.12591/) (2020)
- [DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling](https://mlsanity.com/paper/2010.03099/) (2020)
- [Context-Aware Interaction Network for Question Matching](https://mlsanity.com/paper/2104.08451/) (2021)

## Built on by (most cited first, 2 of 2)

- [EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction](https://mlsanity.com/paper/2406.06839/) (2024)
- [Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval](https://mlsanity.com/paper/2405.12801/) (2024)

## Abstract (arXiv)

Transformer-based models have achieved great success on sentence pair modeling tasks, such as answer selection and natural language inference (NLI). These models generally perform cross-attention over input pairs, leading to prohibitive computational costs. Recent studies propose dual-encoder and late interaction architectures for faster computation. However, the balance between the expressive of cross-attention and computation speedup still needs better coordinated. To this end, this paper introduces a novel paradigm MixEncoder for efficient sentence pair modeling. MixEncoder involves a light-weight cross-attention mechanism. It conducts query encoding only once while modeling the query-candidate interaction in parallel. Extensive experiments conducted on four tasks demonstrate that our MixEncoder can speed up sentence pairing by over 113x while achieving comparable performance as the more expensive cross-attention models.