--- title: "Vitaly Nikolaev — author profile and papers" description: "Vitaly Nikolaev: 3 papers on Elamur Research (2020–2023), h-index 7 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/vitaly-nikolaev/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/vitaly-nikolaev/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Vitaly Nikolaev # Vitaly Nikolaev Vitaly Nikolaev works in natural language processing. The papers here span question answering, summarization and text generation. A recurring question is how well system behaviour holds up against real needs and real sources: whether a benchmark reflects what people in many languages actually want to know, and whether generated text stays faithful to the material it claims to draw on. The methods include building human-annotated datasets, designing evaluation frameworks, and adding explicit planning steps to neural generators. The most cited of these papers is [TyDi QA](https://md.research.elamur.ai/free/en/papers/clark-2020-tydi-qa-benchmark-information-seeking/) (2020). It is a question answering benchmark covering typologically diverse languages. Annotators read brief Wikipedia openings and posed questions they genuinely could not answer from them, rather than translating English data. This avoids translation artifacts and the easy word overlap between questions and answers. [Measuring Attribution in Natural Language Generation Models](https://md.research.elamur.ai/free/en/papers/rashkin-2023-measuring-attribution-natural-language-generation/) (2023) introduced AIS, a framework for judging whether generated statements about the world are supported by an identified source. It first recovers each utterance's full standalone meaning and then asks whether that meaning holds according to the source. [Planning with Learned Entity Prompts](https://md.research.elamur.ai/free/en/papers/narayan-2021-planning-learned-entity-prompts-abstractive/) (2021) has a summarizer first produce an ordered chain of entities, dates and numbers. It then writes the summary conditioned on that plan, aiming to cut down unsupported content. Across 2020–2023, the work moves from [multilingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) and benchmark construction toward faithfulness in [text generation](https://md.research.elamur.ai/free/en/topics/text-generation/). The two later papers share a concern with hallucination, and both treat the source document as the standard that output must meet. Throughout, the papers here return to [evaluation and benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) as a central concern. Paper bylines list [Google](https://md.research.elamur.ai/free/en/companies/google/) in Mountain View from 2018 to 2023 and [Google DeepMind](https://md.research.elamur.ai/free/en/companies/google-deepmind/) in London in 2023. Co-authors include [Michael Collins](https://md.research.elamur.ai/free/en/authors/michael-collins/), with two shared papers, along with [Hannah Rashkin](https://md.research.elamur.ai/free/en/authors/hannah-rashkin/), [Shashi Narayan](https://md.research.elamur.ai/free/en/authors/shashi-narayan/), Jonathan H. Clark and Dipanjan Das. Vitaly Nikolaev has 3 papers in our library, in 2020–2023, most of them on [Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/), [Summarization](https://md.research.elamur.ai/free/en/topics/summarization/), [Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/); often with [Michael Collins](https://md.research.elamur.ai/free/en/authors/michael-collins/), [Dan Garrette](https://md.research.elamur.ai/free/en/authors/dan-garrette/), [Dipanjan Das](https://md.research.elamur.ai/free/en/authors/dipanjan-das/). 3 papers in our library · 2020–2023 [OpenAlex](https://openalex.org/A5047882489) · [**h-index 7**](https://openalex.org/authors/A5047882489) · [18 works](https://openalex.org/works?filter=author.id:A5047882489) · [734 citations](https://openalex.org/works?filter=author.id:A5047882489&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works in our library](https://md.research.elamur.ai/free/en/authors/vitaly-nikolaev/#papers) · [558 citations in our library](https://md.research.elamur.ai/free/en/authors/vitaly-nikolaev/cited-by/) · 1 more work in our library · [⭐ Paper Star rank #1905](https://md.research.elamur.ai/free/en/paper-stars/page/20/#star-1905) 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=Vitaly+Nikolaev) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Vitaly+Nikolaev) · [dblp](https://dblp.org/search?q=Vitaly+Nikolaev) · [ACL Anthology](https://aclanthology.org/search/?q=Vitaly+Nikolaev) ## Affiliations [🏢**Google** Mountain View · United States 2018–2023 · 12 papers](https://md.research.elamur.ai/free/en/companies/google/) · [🏢**Google DeepMind** London · United Kingdom 2023 · 2 papers](https://md.research.elamur.ai/free/en/companies/google-deepmind/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed. ## Topics [Question answering 1](https://md.research.elamur.ai/free/en/topics/question-answering/) · [Summarization 1](https://md.research.elamur.ai/free/en/topics/summarization/) · [Text generation 1](https://md.research.elamur.ai/free/en/topics/text-generation/) · [Multilingual & cross-lingual NLP 1](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Evaluation & benchmarks 1](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) ## Works by year ### 2020s [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/rashkin-2023-measuring-attribution-natural-language-generation/) · [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/narayan-2021-planning-learned-entity-prompts-abstractive/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/clark-2020-tydi-qa-benchmark-information-seeking/) ## Papers The most cited first (OpenAlex and our library). 1. **[TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://md.research.elamur.ai/free/en/papers/clark-2020-tydi-qa-benchmark-information-seeking/)** *(2020 · 691 citations)* TyDi QA is a multilingual question answering benchmark built from real information-seeking questions. It addresses a gap in multilingual evaluation: most QA datasets are English-only, and multilingual ones like MLQA and XQuAD are mostly translated from English. Translation leaves artifacts ("Translationese") and… 2. **[Measuring Attribution in Natural Language Generation Models](https://md.research.elamur.ai/free/en/papers/rashkin-2023-measuring-attribution-natural-language-generation/)** *(2023 · 198 citations)* Neural text generators often produce fluent statements that their underlying sources do not support. Prior work on hallucination and faithfulness lacked a shared, formally grounded way to measure this. The authors propose Attributable to Identified Sources (AIS), a framework that judges whether generated text about… 3. **[Planning with Learned Entity Prompts for Abstractive Summarization](https://md.research.elamur.ai/free/en/papers/narayan-2021-planning-learned-entity-prompts-abstractive/)** *(2021 · 180 citations)* Neural abstractive summarizers usually generate text end to end, with no explicit intermediate plan. This makes them prone to hallucinations, meaning content that the source does not support. The authors bring back the classic idea of planning before writing. A Transformer encoder-decoder first outputs an entity… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 12 of 15 co-authors with a page, the most papers together first. - [Michael Collins](https://md.research.elamur.ai/free/en/authors/michael-collins/) ×2 - [Dan Garrette](https://md.research.elamur.ai/free/en/authors/dan-garrette/) - [Dipanjan Das](https://md.research.elamur.ai/free/en/authors/dipanjan-das/) - [Eunsol Choi](https://md.research.elamur.ai/free/en/authors/eunsol-choi/) - [Hannah Rashkin](https://md.research.elamur.ai/free/en/authors/hannah-rashkin/) - [Iulia Turc](https://md.research.elamur.ai/free/en/authors/iulia-turc/) - [Jennimaria Palomaki](https://md.research.elamur.ai/free/en/authors/jennimaria-palomaki/) - [Jonathan H. Clark](https://md.research.elamur.ai/free/en/authors/jonathan-h-clark/) - [Lora Aroyo](https://md.research.elamur.ai/free/en/authors/lora-aroyo/) - [Matthew Lamm](https://md.research.elamur.ai/free/en/authors/matthew-lamm/) - [Ryan McDonald](https://md.research.elamur.ai/free/en/authors/ryan-mcdonald/) - [Shashi Narayan](https://md.research.elamur.ai/free/en/authors/shashi-narayan/) ## Cited by Papers of our library cite their works 558 times (of the 140,884 papers whose bibliographies we read); [66 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/vitaly-nikolaev/cited-by/).