Papers › Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective...

Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation

15 Mar 2022Findings (ACL) 2022 5arXiv:2203.07687archive 2025-07-28

Xuandong Zhao, Zhiguo Yu, Ming Wu, Lei LI

How to learn highly compact yet effective sentence representation? Pre-trained language models have been effective in many NLP tasks. However, these models are often huge and produce large sentence embeddings. Moreover, there is a big performance gap between large and small models. In this paper, we propose Homomorphic Projective Distillation (HPD) to learn compressed sentence embeddings. Our method augments a small Transformer encoder model with learnable projection layers to produce compact representations while mimicking a large pre-trained language model to retain the sentence representation quality. We evaluate our method with different model sizes on both semantic textual similarity (STS) and semantic retrieval (SR) tasks. Experiments show that our method achieves 2.7-4.5 points performance gain on STS tasks compared with previous best representations of the same size. In SR tasks, our method improves retrieval speed (8.2×) and memory usage (8.0×) compared with state-of-the-art large models.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xuandongzhao/hpd officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingRetrievalSTSSemantic RetrievalSemantic Textual SimilaritySentenceSentence Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSPEEDSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections