---
title: "From Semantics to Style — paper by Yamauchi and Aizawa (2026)"
description: "Each benchmark defines \"similar\" in its own way, so it is hard to tell how text embedding models judge sentence similarity. 63 references."
authors: ["Yusuke Yamauchi", "Akiko Aizawa"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: EACL 2026"
source: "https://aclanthology.org/2026.findings-eacl.95/"
doi: "10.18653/v1/2026.findings-eacl.95"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yamauchi-2026-semantics-style-cross-dataset-comparative/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yamauchi-2026-semantics-style-cross-dataset-comparative/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/34/) / From Semantics to Style: A Cross-Dataset Comparative Framework for Sentence Similarity Predictions

# From Semantics to Style: A Cross-Dataset Comparative Framework for Sentence Similarity Predictions

**Authors:** [Yusuke Yamauchi](https://md.research.elamur.ai/free/en/authors/yusuke-yamauchi/) and [Akiko Aizawa](https://md.research.elamur.ai/free/en/authors/akiko-aizawa/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: EACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-eacl.95/) · [PDF](https://aclanthology.org/2026.findings-eacl.95.pdf) · [DOI 10.18653/v1/2026.findings-eacl.95](https://doi.org/10.18653/v1/2026.findings-eacl.95) · [OpenAlex](https://openalex.org/W7140092902)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Each benchmark defines "similar" in its own way, so it is hard to tell how text embedding models judge sentence similarity. Few studies compare these notions across datasets or separate meaning from style. Yamauchi and Aizawa propose a unified comparison setup. A frozen bi-encoder is paired with small trainable poolers that share one architecture. Each pooler is fitted to one of 21 English datasets of three kinds: STS (graded scores), Paraphrase Identification (binary labels) and Triplet data, where the anchor shares style with the positive but content with the negative. All poolers output embeddings scored by cosine similarity, so predictions from different training regimes can be compared directly.

Poolers trained on STS and PI data give strongly correlated predictions, which points to a largely shared idea of semantic equivalence. Style, by contrast, behaves as a separate dimension. Procrustes, layer-wise and clustering analyses support this split. The authors argue that embedding models should treat semantics and style as distinct components, both for interpretability and for practical use.

## Key points
- **Datasets:** 21 datasets in three groups.
  - STS: SICK and STSB, together with STS3k and CxC, as well as AFS, Opusparcus, FinSTS, BWS and SemRel2024.
  - PI: APT, PARADE, Webis-CPC-11, AskUbuntu, PAWS-Wiki, QQP.
  - Triplet: ELSA, MTST, Paradetox, APPDIA, WNC, StyleDistance.
- **Data preparation:** Original splits were merged and re-split 80/20 with no sentence overlap between train and test. Training sets were capped at 5,000 samples.
- **Semantic results:** With BERT, pairwise correlations between STS/PI pooler predictions exceed 0.9. Orthogonal Procrustes distances show that pooler weights barely change across semantic datasets, which the authors link to anisotropy of the embedding space.
- **Layers and clustering:** Semantic tasks peak in later encoder layers, while many stylistic cues peak in earlier-to-middle layers. In Ward clustering of Mean Difference vectors, semantic differences merge first, and style and sentiment remain distinct.
- **Weak spots and limitations:** Performance is weak on AFS, BWS, Webis-CPC-11 and WNC, tasks not covered by MTEB. The study uses only two encoders and English-only data. Code is available at github.com/yama11235/SemanticStylePooler.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

## Cite

Cite as: Yusuke Yamauchi and Akiko Aizawa. 2026. From Semantics to Style: A Cross-Dataset Comparative Framework for Sentence Similarity Predictions. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yamauchi2026semantics,
  title = {{From Semantics to Style: A Cross-Dataset Comparative Framework for Sentence Similarity Predictions}},
  author = {Yusuke Yamauchi and Akiko Aizawa},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.95},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.95}
}
```

- [← previous From Script to Semantics: Prompting Strategies for African NLI](https://md.research.elamur.ai/free/en/papers/tiwari-2026-script-semantics-prompting-strategies-african/)
- [next → From Shijing to English and German: Resources and Evaluation for LLM Translation of Early Chinese Poetry](https://md.research.elamur.ai/free/en/papers/jiao-2026-shijing-english-german-resources-evaluation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/34/)

## References

63 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mohamed Abdalla, Krishnapriya Vishnubhotla, and Saif Mohammad. 2023. What makes sentences semantically related? a textual relatedness dataset and empirical study. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 782–796, Dubrovnik,… [find](https://scholar.google.com/scholar?q=Mohamed+Abdalla%2C+Krishnapriya+Vishnubhotla%2C+and+Saif+Mohammad%2E+2023%2E+What+makes+sentences+semantically+related%3F+a+textual+relatedness+dataset+and+empirical+study%2E+In+Proceedings+of+the+17th+Conference)
2. Eneko Agirre, Daniel Cer, Mona Diab, and Aitor Gonzalez-Agirre. 2012. [SemEval-2012 task 6: A pilot on semantic textual similarity](https://md.research.elamur.ai/free/en/papers/agirre-2012-semeval-2012-task-6-pilot/). In *SEM 2012: The First Joint Conference on Lexical and Computational Semantics – Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceed…
3. Eneko Agirre, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, and Weiwei Guo. 2013. [*SEM 2013 shared task: Semantic textual similarity](https://md.research.elamur.ai/free/en/papers/agirre-2013-sem-2013-shared-task-semantic/). In Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarit…
4. Katherine Atwell, Sabit Hassan, and Malihe Alikhani. 2022. APPDIA: A discourse-aware transformer-based style transfer model for offensive social media conversations. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6063–6074, Gyeongju, Republic of Korea. Intern… [find](https://scholar.google.com/scholar?q=Katherine+Atwell%2C+Sabit+Hassan%2C+and+Malihe+Alikhani%2E+2022%2E+APPDIA%3A+A+discourse%2Daware+transformer%2Dbased+style+transfer+model+for+offensive+social+media+conversations%2E+In+Proceedings+of+the+29th+Interna)
5. Steven Burrows, Martin Potthast, and Benno Stein. 2013. Paraphrase Acquisition via Crowdsourcing and Machine Learning. Transactions on Intelligent Systems and Technology (ACM TIST), 4(3):43:1– 43:21. [find](https://scholar.google.com/scholar?q=Steven+Burrows%2C+Martin+Potthast%2C+and+Benno+Stein%2E+2013%2E+Paraphrase+Acquisition+via+Crowdsourcing+and+Machine+Learning%2E+Transactions+on+Intelligent+Systems+and+Technology+%28ACM+TIST%29%2C+4%283%29%3A43%3A1%E2%80%93+43%3A21%2E)
6. Daniel Cer, Mona Diab, Eneko Agirre, Iñigo Lopez-Gazpio, and Lucia Specia. 2017. [SemEval-2017 task 1: Semantic textual similarity multilingual and crosslingual focused evaluation](https://md.research.elamur.ai/free/en/papers/cer-2017-semeval-2017-task-1-semantic/). In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 1–14, Vancouver, Canada.…
7. Alexis Conneau, German Kruszewski, Guillaume Lample, Loïc Barrault, and Marco Baroni. 2018. [What you can cram into a single $&!\#* vector: Probing sentence embeddings for linguistic properties](https://md.research.elamur.ai/free/en/papers/conneau-2018-what-you-can-cram-into/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long…
8. Mathias Creutz. 2018. Open subtitles paraphrase corpus for six languages. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Mathias+Creutz%2E+2018%2E+Open+subtitles+paraphrase+corpus+for+six+languages%2E+In+Proceedings+of+the+Eleventh+International+Conference+on+Language+Resources+and+Evaluation+%28LREC+2018%29%2C+Miyazaki%2C+Japan%2E+Eur)
9. Fahim Dalvi, Abdul Rafae Khan, Firoj Alam, Nadir Durrani, Jia Xu, and Hassan Sajjad. 2022. Discovering latent concepts learned in BERT. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Fahim+Dalvi%2C+Abdul+Rafae+Khan%2C+Firoj+Alam%2C+Nadir+Durrani%2C+Jia+Xu%2C+and+Hassan+Sajjad%2E+2022%2E+Discovering+latent+concepts+learned+in+BERT%2E+In+International+Conference+on+Learning+Representations%2E)
10. Preetam Prabhu Srikar Dammu and Omar Alonso. 2024. Near-duplicate question detection. In Companion Proceedings of the ACM Web Conference 2024, WWW ’24, page 493–496, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Preetam+Prabhu+Srikar+Dammu+and+Omar+Alonso%2E+2024%2E+Near%2Dduplicate+question+detection%2E+In+Companion+Proceedings+of+the+ACM+Web+Conference+2024%2C+WWW+%E2%80%9924%2C+page+493%E2%80%93496%2C+New+York%2C+NY%2C+USA%2E+Association+for)
11. Ameet Deshpande, Carlos Jimenez, Howard Chen, Vishvak Murahari, Victoria Graf, Tanmay Rajpurohit, Ashwin Kalyan, Danqi Chen, and Karthik Narasimhan. 2023. C-STS: Conditional semantic textual similarity. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages… [find](https://scholar.google.com/scholar?q=Ameet+Deshpande%2C+Carlos+Jimenez%2C+Howard+Chen%2C+Vishvak+Murahari%2C+Victoria+Graf%2C+Tanmay+Rajpurohit%2C+Ashwin+Kalyan%2C+Danqi+Chen%2C+and+Karthik+Narasimhan%2E+2023%2E+C%2DSTS%3A+Conditional+semantic+textual+similarit)
12. Kawin Ethayarajh. 2019. How contextual are contextualized word representations? Comparing the geometry of BERT, ELMo, and GPT-2 embeddings. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Process… [find](https://scholar.google.com/scholar?q=Kawin+Ethayarajh%2E+2019%2E+How+contextual+are+contextualized+word+representations%3F+Comparing+the+geometry+of+BERT%2C+ELMo%2C+and+GPT%2D2+embeddings%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+i)
13. Yingchaojie Feng, Yiqun Sun, Yandong Sun, Minfeng Zhu, Qiang Huang, Anthony Kum Hoe Tung, and Wei Chen. 2025. Don’t reinvent the wheel: Efficient instruction-following text embedding based on guided space transformation. In Proceedings of the 63rd Annual Meeting of the Association for Computational… [find](https://scholar.google.com/scholar?q=Yingchaojie+Feng%2C+Yiqun+Sun%2C+Yandong+Sun%2C+Minfeng+Zhu%2C+Qiang+Huang%2C+Anthony+Kum+Hoe+Tung%2C+and+Wei+Chen%2E+2025%2E+Don%E2%80%99t+reinvent+the+wheel%3A+Efficient+instruction%2Dfollowing+text+embedding+based+on+guided+s)
14. James Fodor, Simon De Deyne, and Shinsuke Suzuki. 2025. [Compositionality and sentence meaning: Comparing semantic parsing and transformers on a challenging sentence similarity dataset](https://md.research.elamur.ai/free/en/papers/fodor-2025-compositionality-sentence-meaning-comparing-semantic/). Computational Linguistics, 51(1):139–190.
15. Vishal Gandhi and Sagar Gandhi. 2025. Elsa: A style aligned dataset for emotionally intelligent language generation. Preprint, arXiv:2504.08281. — [arXiv:2504.08281](https://arxiv.org/abs/2504.08281) [find](https://scholar.google.com/scholar?q=Vishal+Gandhi+and+Sagar+Gandhi%2E+2025%2E+Elsa%3A+A+style+aligned+dataset+for+emotionally+intelligent+language+generation%2E+Preprint%2C+arXiv%3A2504%2E08281%2E+%E2%80%94+%5BarXiv%3A2504%2E08281%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2504%2E08281%29)
16. Jun Gao, Di He, Xu Tan, Tao Qin, Liwei Wang, and Tie-Yan Liu. 2019. [Representation degeneration problem in training natural language generation models](https://md.research.elamur.ai/free/en/papers/gao-2019-representation-degeneration-problem-training-natural/). arXiv preprint arXiv:1907.12009.
17. Yun He, Zhuoer Wang, Yin Zhang, Ruihong Huang, and James Caverlee. 2020. PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7572–7582, Online. Associ… [find](https://scholar.google.com/scholar?q=Yun+He%2C+Zhuoer+Wang%2C+Yin+Zhang%2C+Ruihong+Huang%2C+and+James+Caverlee%2E+2020%2E+PARADE%3A+A+New+Dataset+for+Paraphrase+Identification+Requiring+Computer+Science+Domain+Knowledge%2E+In+Proceedings+of+the+2020+Con)
18. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). Preprint, arXiv:2009.03300.
19. Zhiqiang Hu, Roy Ka-Wei Lee, Charu C. Aggarwal, and Aston Zhang. 2023. Text style transfer: A review and experimental evaluation. Preprint, arXiv:2010.12742. [find](https://scholar.google.com/scholar?q=Zhiqiang+Hu%2C+Roy+Ka%2DWei+Lee%2C+Charu+C%2E+Aggarwal%2C+and+Aston+Zhang%2E+2023%2E+Text+style+transfer%3A+A+review+and+experimental+evaluation%2E+Preprint%2C+arXiv%3A2010%2E12742%2E)
20. Hiroki Iida and Naoaki Okazaki. 2021. Incorporating semantic textual similarity and lexical matching for information retrieval. In Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation, pages 582–591, Shanghai, China. Association for Computational Lingustics. [find](https://scholar.google.com/scholar?q=Hiroki+Iida+and+Naoaki+Okazaki%2E+2021%2E+Incorporating+semantic+textual+similarity+and+lexical+matching+for+information+retrieval%2E+In+Proceedings+of+the+35th+Pacific+Asia+Conference+on+Language%2C+Informat)
21. Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, and Rada Mihalcea. 2022. Deep learning for text style transfer: A survey. Computational Linguistics, 48(1):155–205. [find](https://scholar.google.com/scholar?q=Di+Jin%2C+Zhijing+Jin%2C+Zhiting+Hu%2C+Olga+Vechtomova%2C+and+Rada+Mihalcea%2E+2022%2E+Deep+learning+for+text+style+transfer%3A+A+survey%2E+Computational+Linguistics%2C+48%281%29%3A155%E2%80%93205%2E)
22. Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2021. Supervised contrastive learning. Preprint, arXiv:2004.11362. — [arXiv:2004.11362](https://arxiv.org/abs/2004.11362) [find](https://scholar.google.com/scholar?q=Prannay+Khosla%2C+Piotr+Teterwak%2C+Chen+Wang%2C+Aaron+Sarna%2C+Yonglong+Tian%2C+Phillip+Isola%2C+Aaron+Maschinot%2C+Ce+Liu%2C+and+Dilip+Krishnan%2E+2021%2E+Supervised+contrastive+learning%2E+Preprint%2C+arXiv%3A2004%2E11362%2E+%E2%80%94+)
23. Anand Kumar and Hemanth Kumar. 2024. [scaLAR SemEval-2024 task 1: Semantic textual relatednes for English](https://md.research.elamur.ai/free/en/papers/kumar-2024-scalar-semeval-2024-task-1/). In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 902–906, Mexico City, Mexico. Association for Computational Linguistics.
24. Sean Lee, Aamir Shakir, Darius Koenig, and Julius Lipp. 2024. Open source strikes bread - new fluffy embedding model. [find](https://scholar.google.com/scholar?q=Sean+Lee%2C+Aamir+Shakir%2C+Darius+Koenig%2C+and+Julius+Lipp%2E+2024%2E+Open+source+strikes+bread+%2D+new+fluffy+embedding+model%2E)
25. Seonghyeon Lee, Dongha Lee, Seongbo Jang, and Hwanjo Yu. 2022. Toward interpretable semantic textual similarity via optimal transport-based contrastive sentence learning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5969–59… [find](https://scholar.google.com/scholar?q=Seonghyeon+Lee%2C+Dongha+Lee%2C+Seongbo+Jang%2C+and+Hwanjo+Yu%2E+2022%2E+Toward+interpretable+semantic+textual+similarity+via+optimal+transport%2Dbased+contrastive+sentence+learning%2E+In+Proceedings+of+the+60th+An)
26. Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi Jaakkola, Kateryna Tymoshenko, Alessandro Moschitti, and Lluís Màrquez. 2016. Semi-supervised question retrieval with gated convolutions. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguis… [find](https://scholar.google.com/scholar?q=Tao+Lei%2C+Hrishikesh+Joshi%2C+Regina+Barzilay%2C+Tommi+Jaakkola%2C+Kateryna+Tymoshenko%2C+Alessandro+Moschitti%2C+and+Llu%C3%ADs+M%C3%A0rquez%2E+2016%2E+Semi%2Dsupervised+question+retrieval+with+gated+convolutions%2E+In+Proceedin)
27. Varvara Logacheva, Daryna Dementieva, Sergey Ustyantsev, Daniil Moskovskiy, David Dale, Irina Krotova, Nikita Semenov, and Alexander Panchenko. 2022. [ParaDetox: Detoxification with parallel data](https://md.research.elamur.ai/free/en/papers/logacheva-2022-paradetox-detoxification-parallel-data/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo…
28. Xiaofei Ma, Zhiguo Wang, Patrick Ng, Ramesh Nallapati, and Bing Xiang. 2019. Universal text representation from bert: An empirical study. arXiv preprint arXiv:1910.07973. — [arXiv:1910.07973](https://arxiv.org/abs/1910.07973) [find](https://scholar.google.com/scholar?q=Xiaofei+Ma%2C+Zhiguo+Wang%2C+Patrick+Ng%2C+Ramesh+Nallapati%2C+and+Bing+Xiang%2E+2019%2E+Universal+text+representation+from+bert%3A+An+empirical+study%2E+arXiv+preprint+arXiv%3A1910%2E07973%2E+%E2%80%94+%5BarXiv%3A1910%2E07973%5D%28https%3A%2F%2F)
29. Marco Marelli, Stefano Menini, Marco Baroni, Luisa Bentivogli, Raffaella Bernardi, and Roberto Zamparelli. 2014. [A SICK cure for the evaluation of compositional distributional semantic models](https://md.research.elamur.ai/free/en/papers/marelli-2014-sick-cure-evaluation-compositional-distributional/). In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages…
30. David D. McDonald and James D. Pustejovsky. 1985. A computational theory of prose style for natural language generation. In Second Conference of the European Chapter of the Association for Computational Linguistics, Geneva, Switzerland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=David+D%2E+McDonald+and+James+D%2E+Pustejovsky%2E+1985%2E+A+computational+theory+of+prose+style+for+natural+language+generation%2E+In+Second+Conference+of+the+European+Chapter+of+the+Association+for+Computation)
31. Amita Misra, Brian Ecker, and Marilyn Walker. 2016. Measuring the similarity of sentential arguments in dialogue. In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 276–287, Los Angeles. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Amita+Misra%2C+Brian+Ecker%2C+and+Marilyn+Walker%2E+2016%2E+Measuring+the+similarity+of+sentential+arguments+in+dialogue%2E+In+Proceedings+of+the+17th+Annual+Meeting+of+the+Special+Interest+Group+on+Discourse+a)
32. Lucas Moeller, Dmitry Nikolaev, and Sebastian Padó. 2024. Approximate attributions for off-the-shelf Siamese transformers. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2059–2071, St. Julian’s, Malta. Ass… [find](https://scholar.google.com/scholar?q=Lucas+Moeller%2C+Dmitry+Nikolaev%2C+and+Sebastian+Pad%C3%B3%2E+2024%2E+Approximate+attributions+for+off%2Dthe%2Dshelf+Siamese+transformers%2E+In+Proceedings+of+the+18th+Conference+of+the+European+Chapter+of+the+Associat)
33. Niklas Muennighoff, Nouamane Tazi, Loic Magne, and Nils Reimers. 2023. [MTEB: Massive text embedding benchmark](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-mteb-massive-text-embedding-benchmark/). In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2014–2037, Dubrovnik, Croatia. Association for Computational Linguistic…
34. Sourabrata Mukherjee, Akanksha Bansal, Pritha Majumdar, Atul Kr. Ojha, and Ondřej Dušek. 2023. Low-resource text style transfer for Bangla: Data & models. In Proceedings of the First Workshop on Bangla Language Processing (BLP-2023), pages 34–47, Singapore. Association for Computational Linguistics… [find](https://scholar.google.com/scholar?q=Sourabrata+Mukherjee%2C+Akanksha+Bansal%2C+Pritha+Majumdar%2C+Atul+Kr%2E+Ojha%2C+and+Ondr%CC%8Cej+Du%C5%A1ek%2E+2023%2E+Low%2Dresource+text+style+transfer+for+Bangla%3A+Data+%26+models%2E+In+Proceedings+of+the+First+Workshop+on+Bang)
35. Fionn Murtagh and Pierre Legendre. 2014. Ward’s hierarchical agglomerative clustering method: Which algorithms implement ward’s criterion? Journal of Classification, 31(3):274–295. [find](https://scholar.google.com/scholar?q=Fionn+Murtagh+and+Pierre+Legendre%2E+2014%2E+Ward%E2%80%99s+hierarchical+agglomerative+clustering+method%3A+Which+algorithms+implement+ward%E2%80%99s+criterion%3F+Journal+of+Classification%2C+31%283%29%3A274%E2%80%93295%2E)
36. Animesh Nighojkar and John Licato. 2021. Improving paraphrase detection with the adversarial paraphrasing task. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers… [find](https://scholar.google.com/scholar?q=Animesh+Nighojkar+and+John+Licato%2E+2021%2E+Improving+paraphrase+detection+with+the+adversarial+paraphrasing+task%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Linguisti)
37. Dongsuk Oh, Yejin Kim, Hodong Lee, H Howie Huang, and Heuiseok Lim. 2022. Don’t judge a language model by its last layer: Contrastive learning with layer-wise attention pooling. arXiv preprint arXiv:2209.05972. [find](https://scholar.google.com/scholar?q=Dongsuk+Oh%2C+Yejin+Kim%2C+Hodong+Lee%2C+H+Howie+Huang%2C+and+Heuiseok+Lim%2E+2022%2E+Don%E2%80%99t+judge+a+language+model+by+its+last+layer%3A+Contrastive+learning+with+layer%2Dwise+attention+pooling%2E+arXiv+preprint+arXiv%3A2)
38. Juri Opitz and Anette Frank. 2022. SBERT studies meaning representations: Decomposing sentence embeddings into explainable semantic features. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference… [find](https://scholar.google.com/scholar?q=Juri+Opitz+and+Anette+Frank%2E+2022%2E+SBERT+studies+meaning+representations%3A+Decomposing+sentence+embeddings+into+explainable+semantic+features%2E+In+Proceedings+of+the+2nd+Conference+of+the+Asia%2DPacific+C)
39. Juri Opitz, Lucas Möller, Andrianos Michail, and Simon Clematide. 2025. Interpretable text embeddings and text similarity explanation: A primer. Preprint, arXiv:2502.14862. — [arXiv:2502.14862](https://arxiv.org/abs/2502.14862) [find](https://scholar.google.com/scholar?q=Juri+Opitz%2C+Lucas+M%C3%B6ller%2C+Andrianos+Michail%2C+and+Simon+Clematide%2E+2025%2E+Interpretable+text+embeddings+and+text+similarity+explanation%3A+A+primer%2E+Preprint%2C+arXiv%3A2502%2E14862%2E+%E2%80%94+%5BarXiv%3A2502%2E14862%5D%28https%3A)
40. Nedjma Ousidhoum, Shamsuddeen Muhammad, Mohamed Abdalla, Idris Abdulmumin, Ibrahim Ahmad, Sanchit Ahuja, Alham Aji, Vladimir Araujo, Abinew Ayele, Pavan Baswani, Meriem Beloucif, Chris Biemann, Sofia Bourhim, Christine Kock, Genet Dekebo, Oumaima Hourrane, Gopichand Kanumolu, Lokesh Madasu, Samuel R… [find](https://scholar.google.com/scholar?q=Nedjma+Ousidhoum%2C+Shamsuddeen+Muhammad%2C+Mohamed+Abdalla%2C+Idris+Abdulmumin%2C+Ibrahim+Ahmad%2C+Sanchit+Ahuja%2C+Alham+Aji%2C+Vladimir+Araujo%2C+Abinew+Ayele%2C+Pavan+Baswani%2C+Meriem+Beloucif%2C+Chris+Biemann%2C+Sofia+)
41. Zarana Parekh, Jason Baldridge, Daniel Cer, Austin Waters, and Yinfei Yang. 2021. Crisscrossed captions: Extended intramodal and intermodal semantic similarity judgments for MS-COCO. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main… [find](https://scholar.google.com/scholar?q=Zarana+Parekh%2C+Jason+Baldridge%2C+Daniel+Cer%2C+Austin+Waters%2C+and+Yinfei+Yang%2E+2021%2E+Crisscrossed+captions%3A+Extended+intramodal+and+intermodal+semantic+similarity+judgments+for+MS%2DCOCO%2E+In+Proceedings+of)
42. Ajay Patel, Jiacheng Zhu, Justin Qiu, Zachary Horvitz, Marianna Apidianaki, Kathleen McKeown, and Chris Callison-Burch. 2025. StyleDistance: Stronger content-independent style embeddings with synthetic parallel examples. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of… [find](https://scholar.google.com/scholar?q=Ajay+Patel%2C+Jiacheng+Zhu%2C+Justin+Qiu%2C+Zachary+Horvitz%2C+Marianna+Apidianaki%2C+Kathleen+McKeown%2C+and+Chris+Callison%2DBurch%2E+2025%2E+StyleDistance%3A+Stronger+content%2Dindependent+style+embeddings+with+syntheti)
43. Reid Pryzant, Richard Diehl Martinez, Nathan Dass, Sadao Kurohashi, Dan Jurafsky, and Diyi Yang. 2020. [find](https://scholar.google.com/scholar?q=Reid+Pryzant%2C+Richard+Diehl+Martinez%2C+Nathan+Dass%2C+Sadao+Kurohashi%2C+Dan+Jurafsky%2C+and+Diyi+Yang%2E+2020%2E)
44. Automatically neutralizing subjective bias in text. Proceedings of the AAAI Conference on Artificial Intelligence, 34(01):480–489. [find](https://scholar.google.com/scholar?q=Automatically+neutralizing+subjective+bias+in+text%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+34%2801%29%3A480%E2%80%93489%2E)
45. Quora. 2017. Quora question pairs. //www.kaggle.com/datasets/quora/ question-pairs-dataset. https: [find](https://scholar.google.com/scholar?q=Quora%2E+2017%2E+Quora+question+pairs%2E+%2F%2Fwww%2Ekaggle%2Ecom%2Fdatasets%2Fquora%2F+question%2Dpairs%2Ddataset%2E+https%3A)
46. Muhammad Rafi and Mohammad Shahid Shaikh. 2013. An improved semantic similarity measure for document clustering based on topic maps. Preprint, arXiv:1303.4087. — [arXiv:1303.4087](https://arxiv.org/abs/1303.4087) [find](https://scholar.google.com/scholar?q=Muhammad+Rafi+and+Mohammad+Shahid+Shaikh%2E+2013%2E+An+improved+semantic+similarity+measure+for+document+clustering+based+on+topic+maps%2E+Preprint%2C+arXiv%3A1303%2E4087%2E+%E2%80%94+%5BarXiv%3A1303%2E4087%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
47. Tharindu Ranasinghe, Hansi Hettiarachchi, Constantin Orasan, and Ruslan Mitkov. 2025. Musts: Multilingual semantic textual similarity benchmark. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 331–353. [find](https://scholar.google.com/scholar?q=Tharindu+Ranasinghe%2C+Hansi+Hettiarachchi%2C+Constantin+Orasan%2C+and+Ruslan+Mitkov%2E+2025%2E+Musts%3A+Multilingual+semantic+textual+similarity+benchmark%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Associ)
48. Nils Reimers and Iryna Gurevych. 2019. [Sentence-BERT: Sentence embeddings using Siamese BERT-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,…
49. Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, and Alexander Turner. 2024. Steering llama 2 via contrastive activation addition. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15504–15522, Bangkok, Thaila… [find](https://scholar.google.com/scholar?q=Nina+Rimsky%2C+Nick+Gabrieli%2C+Julian+Schulz%2C+Meg+Tong%2C+Evan+Hubinger%2C+and+Alexander+Turner%2E+2024%2E+Steering+llama+2+via+contrastive+activation+addition%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+A)
50. Tim Schopf, Emanuel Gerber, Malte Ostendorff, and Florian Matthes. 2023. AspectCSE: Sentence embeddings for aspect-based semantic textual similarity using contrastive learning and structured knowledge. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Process… [find](https://scholar.google.com/scholar?q=Tim+Schopf%2C+Emanuel+Gerber%2C+Malte+Ostendorff%2C+and+Florian+Matthes%2E+2023%2E+AspectCSE%3A+Sentence+embeddings+for+aspect%2Dbased+semantic+textual+similarity+using+contrastive+learning+and+structured+knowledge)
51. Yiqun Sun, Qiang Huang, Yixuan Tang, Anthony Kum Hoe Tung, and Jun Yu. 2024. A general framework for producing interpretable semantic text embeddings. ArXiv, abs/2410.03435. — [arXiv:2410.03435](https://arxiv.org/abs/2410.03435) [find](https://scholar.google.com/scholar?q=Yiqun+Sun%2C+Qiang+Huang%2C+Yixuan+Tang%2C+Anthony+Kum+Hoe+Tung%2C+and+Jun+Yu%2E+2024%2E+A+general+framework+for+producing+interpretable+semantic+text+embeddings%2E+ArXiv%2C+abs%2F2410%2E03435%2E+%E2%80%94+%5BarXiv%3A2410%2E03435%5D%28https)
52. Yiqun Sun, Qiang Huang, Anthony KH Tung, and Jun Yu. 2025. Text embeddings should capture implicit semantics, not just surface meaning. arXiv preprint arXiv:2506.08354. — [arXiv:2506.08354](https://arxiv.org/abs/2506.08354) [find](https://scholar.google.com/scholar?q=Yiqun+Sun%2C+Qiang+Huang%2C+Anthony+KH+Tung%2C+and+Jun+Yu%2E+2025%2E+Text+embeddings+should+capture+implicit+semantics%2C+not+just+surface+meaning%2E+arXiv+preprint+arXiv%3A2506%2E08354%2E+%E2%80%94+%5BarXiv%3A2506%2E08354%5D%28https%3A%2F%2Far)
53. Matthieu Tehenan, Vikram Natarajan, Jonathan Michala, Milton Lin, and Juri Opitz. 2025. Mechanistic decomposition of sentence representations. Preprint, arXiv:2506.04373. — [arXiv:2506.04373](https://arxiv.org/abs/2506.04373) [find](https://scholar.google.com/scholar?q=Matthieu+Tehenan%2C+Vikram+Natarajan%2C+Jonathan+Michala%2C+Milton+Lin%2C+and+Juri+Opitz%2E+2025%2E+Mechanistic+decomposition+of+sentence+representations%2E+Preprint%2C+arXiv%3A2506%2E04373%2E+%E2%80%94+%5BarXiv%3A2506%2E04373%5D%28https%3A%2F%2F)
54. Ian Tenney, Dipanjan Das, and Ellie Pavlick. 2019. [BERT rediscovers the classical NLP pipeline](https://md.research.elamur.ai/free/en/papers/tenney-2019-bert-rediscovers-classical-nlp-pipeline/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4593– 4601, Florence, Italy. Association for Computational Linguistics.
55. Nandan Thakur, Nils Reimers, Johannes Daxenberger, and Iryna Gurevych. 2021. [Augmented SBERT: Data augmentation method for improving bi-encoders for pairwise sentence scoring tasks](https://md.research.elamur.ai/free/en/papers/thakur-2021-augmented-sbert-data-augmentation-method/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics:…
56. Jacob Turton, Robert Elliott Smith, and David Vinson. 2021. Deriving contextualised semantic features from BERT (and other transformer model) embeddings. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 248–262, Online. Association for Computational Lingui… [find](https://scholar.google.com/scholar?q=Jacob+Turton%2C+Robert+Elliott+Smith%2C+and+David+Vinson%2E+2021%2E+Deriving+contextualised+semantic+features+from+BERT+%28and+other+transformer+model%29+embeddings%2E+In+Proceedings+of+the+6th+Workshop+on+Represen)
57. Alexandros Vasileiou and Oliver Eberle. 2024. Explaining text similarity in transformer models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 7859–7873, Mexico City, Mex… [find](https://scholar.google.com/scholar?q=Alexandros+Vasileiou+and+Oliver+Eberle%2E+2024%2E+Explaining+text+similarity+in+transformer+models%2E+In+Proceedings+of+the+2024+Conference+of+the+North+American+Chapter+of+the+Association+for+Computational)
58. Hongwei Wang, Hongming Zhang, and Dong Yu. 2023. On the dimensionality of sentence embeddings. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10344–10354, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hongwei+Wang%2C+Hongming+Zhang%2C+and+Dong+Yu%2E+2023%2E+On+the+dimensionality+of+sentence+embeddings%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2023%2C+pages+10344%E2%80%9310354%2C+Singapore%2E+A)
59. Zhengxuan Wu, Aryaman Arora, Atticus Geiger, Zheng Wang, Jing Huang, Dan Jurafsky, Christopher D Manning, and Christopher Potts. 2025. Axbench: Steering LLMs? even simple baselines outperform sparse autoencoders. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Zhengxuan+Wu%2C+Aryaman+Arora%2C+Atticus+Geiger%2C+Zheng+Wang%2C+Jing+Huang%2C+Dan+Jurafsky%2C+Christopher+D+Manning%2C+and+Christopher+Potts%2E+2025%2E+Axbench%3A+Steering+LLMs%3F+even+simple+baselines+outperform+sparse+a)
60. Shanshan Yang, Steve Yang, and Feng Mai. 2024. Financial semantic textual similarity: A new dataset and model. In 2024 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), pages 1–8. [find](https://scholar.google.com/scholar?q=Shanshan+Yang%2C+Steve+Yang%2C+and+Feng+Mai%2E+2024%2E+Financial+semantic+textual+similarity%3A+A+new+dataset+and+model%2E+In+2024+IEEE+Symposium+on+Computational+Intelligence+for+Financial+Engineering+and+Econom)
61. Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, Fei Huang, and Jingren Zhou. 2025. [Qwen3 embedding: Advancing text embedding and reranking through foundation models](https://md.research.elamur.ai/free/en/papers/zhang-2025-qwen3-embedding-advancing-text/). arXiv preprint arXiv:2506.05176.
62. Yuan Zhang, Jason Baldridge, and Luheng He. 2019. [PAWS: Paraphrase adversaries from word scrambling](https://md.research.elamur.ai/free/en/papers/zhang-2019-paws-paraphrase-adversaries-word-scrambling/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1298–1308, M…
63. Yuhao Zhang, Hongji Zhu, Yongliang Wang, Nan Xu, Xiaobo Li, and Binqiang Zhao. 2022. A contrastive framework for learning sentence representations from pairwise and triple-wise perspective in angular space. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (V… [find](https://scholar.google.com/scholar?q=Yuhao+Zhang%2C+Hongji+Zhu%2C+Yongliang+Wang%2C+Nan+Xu%2C+Xiaobo+Li%2C+and+Binqiang+Zhao%2E+2022%2E+A+contrastive+framework+for+learning+sentence+representations+from+pairwise+and+triple%2Dwise+perspective+in+angular+)

*Updated 2 November 2026*