--- title: "Nils Reimers — author profile and papers" description: "Nils Reimers, Cohere: 11 papers on Elamur Research (2017–2022), h-index 22 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/nils-reimers/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/nils-reimers/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Nils Reimers # Nils Reimers Nils Reimers works on representing sentences and passages as vectors, and on using those representations for semantic similarity, search and clustering. The papers here cover multilingual sentence embeddings, dense retrieval and its transfer to new domains, the cost of fine-tuning transformers, argument search, and cross-document coreference. Evaluation is a recurring concern: whether benchmark numbers and single test scores really show how well a model works. The most cited paper here, [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://md.research.elamur.ai/free/en/papers/reimers-2020-making-monolingual-sentence-embeddings-multilingual/) (2020), extends an English sentence encoder to other languages. A student model is trained so that an English sentence and its translation both fall near the vector the English teacher produces. [MTEB](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-mteb-massive-text-embedding-benchmark/) (2022) gathers 58 datasets in eight task types and 112 languages into one benchmark for text embeddings. An earlier study, [Reporting Score Distributions Makes a Difference](https://md.research.elamur.ai/free/en/papers/reimers-2017-reporting-score-distributions-makes-difference/) (2017), retrained sequence taggers many times while changing only the random seed. It argued that comparing systems by one score is unreliable. Augmented SBERT (2021) uses a cross-encoder to label extra sentence pairs, which then help train faster bi-encoders. The newest work turns to retrieval outside the domains where labelled data exists. [GPL](https://md.research.elamur.ai/free/en/papers/wang-2022-gpl-generative-pseudo-labeling-unsupervised/) (2022) adapts a dense retriever using only unlabelled target passages. It generates synthetic queries for them and learns from graded cross-encoder scores. The related [BEIR](https://md.research.elamur.ai/free/en/papers/thakur-2021-beir-heterogenous-benchmark-zero/) benchmark (2021) tests retrieval models zero-shot across varied collections. AdapterDrop (2021) measured the training and inference cost of adapters against full fine-tuning. Reimers is currently at [Cohere](https://md.research.elamur.ai/free/en/companies/cohere/). Most earlier papers come from [Technische Universität Darmstadt](https://md.research.elamur.ai/free/en/universities/technische-universitat-darmstadt/), with a few from [Hugging Face](https://md.research.elamur.ai/free/en/companies/hugging-face/) in 2021–2022. The most frequent co-author on these papers is [Iryna Gurevych](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/), followed by [Nandan Thakur](https://md.research.elamur.ai/free/en/authors/nandan-thakur/) and Andreas Rücklé. The topics include [information retrieval and search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) and [evaluation and benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/). Nils Reimers has 11 papers in our library, in 2017–2022, most of them on [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/), [Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/); often with [Iryna Gurevych](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/), [Nandan Thakur](https://md.research.elamur.ai/free/en/authors/nandan-thakur/), [Andreas Rücklé](https://md.research.elamur.ai/free/en/authors/andreas-ruckle/). 11 papers in our library · 2017–2022 [OpenAlex](https://openalex.org/A5110592354) · [**h-index 22**](https://openalex.org/authors/A5110592354) · [55 works](https://openalex.org/works?filter=author.id:A5110592354) · [15,596 citations](https://openalex.org/works?filter=author.id:A5110592354&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 11 works in our library](https://md.research.elamur.ai/free/en/authors/nils-reimers/#papers) · [🔗 6,745 citations in our library](https://md.research.elamur.ai/free/en/authors/nils-reimers/cited-by/) · [⭐ Paper Star rank #236](https://md.research.elamur.ai/free/en/paper-stars/page/3/#star-236) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Nils+Reimers) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Nils+Reimers) · [dblp](https://dblp.org/search?q=Nils+Reimers) · [ACL Anthology](https://aclanthology.org/search/?q=Nils+Reimers) ## Affiliations [🏢**Cohere** San Francisco 2020–2026 · 15 papers*current*](https://md.research.elamur.ai/free/en/companies/cohere/) · [🎓**Technische Universität Darmstadt** Darmstadt · Germany 2013–2022 · 20 papers](https://md.research.elamur.ai/free/en/universities/technische-universitat-darmstadt/) · [🏢**Hugging Face** New York · United States 2021–2022 · 4 papers](https://md.research.elamur.ai/free/en/companies/hugging-face/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed. ## Topics [Coreference resolution (2)](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) · [Evaluation & benchmarks (2)](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Information retrieval & search (2)](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · [Multilingual & cross-lingual NLP (1)](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) ## Works by year ### 2020s [**2022** 2 papers](https://md.research.elamur.ai/free/en/authors/nils-reimers/year/2022/) · [**2021** 4 papers](https://md.research.elamur.ai/free/en/authors/nils-reimers/year/2021/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/reimers-2020-making-monolingual-sentence-embeddings-multilingual/) ### 2010s [**2019** 3 papers](https://md.research.elamur.ai/free/en/authors/nils-reimers/year/2019/) · [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/reimers-2017-reporting-score-distributions-makes-difference/) ## Papers The most cited first (OpenAlex and our library). 1. **[Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/)** *(2019 · 4,838 citations)* BERT and RoBERTa perform well at estimating the semantic similarity of sentence pairs, but they operate as a cross-encoder: the model receives both sentences together. 2. **[Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://md.research.elamur.ai/free/en/papers/reimers-2020-making-monolingual-sentence-embeddings-multilingual/)** *(2020 · 1,320 citations)* Most strong sentence embedding models exist only for English, because training data for other languages is scarce. 3. **[MTEB: Massive Text Embedding Benchmark](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-mteb-massive-text-embedding-benchmark/)** *(2022 · 1,021 citations)* Text embedding models are usually tested on only a few datasets, most often semantic textual similarity (STS). 4. **[Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging](https://md.research.elamur.ai/free/en/papers/reimers-2017-reporting-score-distributions-makes-difference/)** *(2017 · 648 citations)* Neural sequence taggers train non-deterministically, so the random seed alone can push a model into local minima that generalize differently. 5. **[AdapterDrop: On the Efficiency of Adapters in Transformers](https://md.research.elamur.ai/free/en/papers/ruckle-2021-adapterdrop-efficiency-adapters-transformers/)** *(2021 · 294 citations)* Adapters are usually valued for their small parameter footprint, but their actual compute cost had not been measured carefully. 6. **[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/)** *(2021 · 275 citations)* Cross-encoders such as BERT read both sentences of a pair jointly and score pairs accurately. They are too slow for large-scale clustering or retrieval and produce no indexable embeddings. Bi-encoders such as SBERT embed each sentence separately and are fast, but they trail cross-encoders, most of all when labeled… 7. **[BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://md.research.elamur.ai/free/en/papers/thakur-2021-beir-heterogenous-benchmark-zero/)** *(2021 · 262 citations)* Neural retrievers are usually trained and tested on the same large collection, such as MS MARCO or Natural Questions. 8. **[Classification and Clustering of Arguments with Contextualized Word Embeddings](https://md.research.elamur.ai/free/en/papers/reimers-2019-classification-clustering-arguments-contextualized-word/)** *(2019 · 239 citations)* The paper addresses open-domain argument search: retrieving arguments about arbitrary, previously unseen topics from heterogeneous sources and then grouping arguments that make the same point. 9. **[Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution](https://md.research.elamur.ai/free/en/papers/barhom-2019-revisiting-joint-modeling-cross-document/)** *(2019 · 164 citations)* The paper addresses cross-document coreference resolution (CDCR), meaning the grouping of mentions of the same entities and events across a collection of texts. 10. **[GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://md.research.elamur.ai/free/en/papers/wang-2022-gpl-generative-pseudo-labeling-unsupervised/)** *(2022 · 155 citations)* Dense retrievers trained on large labeled collections such as MS MARCO lose much of their quality on specialized domains, where labeled data is rarely available. 11. **[Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora](https://md.research.elamur.ai/free/en/papers/bugert-2021-generalizing-cross-document-event-coreference/)** *(2021 · 33 citations)* Cross-document event coreference resolution (CDCR) requires a system to find event mentions across a document collection and group those that denote the same real-world event. ## Co-authors here 12 of 14 co-authors with a page, the most papers together first. - [Iryna Gurevych](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/) ×9 - [Nandan Thakur](https://md.research.elamur.ai/free/en/authors/nandan-thakur/) ×3 - [Andreas Rücklé](https://md.research.elamur.ai/free/en/authors/andreas-ruckle/) ×2 - [Johannes Daxenberger](https://md.research.elamur.ai/free/en/authors/johannes-daxenberger/) ×2 - [Michael Bugert](https://md.research.elamur.ai/free/en/authors/michael-bugert/) ×2 - [Tilman Beck](https://md.research.elamur.ai/free/en/authors/tilman-beck/) ×2 - [Alon Eirew](https://md.research.elamur.ai/free/en/authors/alon-eirew/) - [Benjamin Schiller](https://md.research.elamur.ai/free/en/authors/benjamin-schiller/) - [Christian Stab](https://md.research.elamur.ai/free/en/authors/christian-stab/) - [Ido Dagan](https://md.research.elamur.ai/free/en/authors/ido-dagan/) - [Jonas Pfeiffer](https://md.research.elamur.ai/free/en/authors/jonas-pfeiffer/) - [Max Glockner](https://md.research.elamur.ai/free/en/authors/max-glockner/) ## Cited by Papers of our library cite their works 6,745 times (of the 140,884 papers whose bibliographies we read); [316 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/nils-reimers/cited-by/).