--- title: "Harish Tayyar Madabushi — author profile and papers" description: "Harish Tayyar Madabushi, University of Bath: 6 papers on Elamur Research (2020–2025), h-index 11 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/harish-tayyar-madabushi/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/harish-tayyar-madabushi/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Harish Tayyar Madabushi # Harish Tayyar Madabushi 6 papers on this site · 2020–2025 current affiliation [University of Bath](https://ror.org/002h8g185), Bath, United Kingdom Harish Tayyar Madabushi has 6 papers on this site, in 2020–2025, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Idioms & multiword expressions](https://md.research.elamur.ai/free/en/topics/multiword-expressions/), [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/); often with [Aline Villavicencio](https://md.research.elamur.ai/free/en/authors/aline-villavicencio/), [Carolina Scarton](https://md.research.elamur.ai/free/en/authors/carolina-scarton/), [Claire Bonial](https://md.research.elamur.ai/free/en/authors/claire-bonial/). [OpenAlex](https://openalex.org/A5070941491) · [ORCID](https://orcid.org/0000-0001-5260-3653) · [**h-index 11**](https://openalex.org/authors/A5070941491) · [91 works](https://openalex.org/works?filter=author.id:A5070941491) · [493 citations](https://openalex.org/works?filter=author.id:A5070941491&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [6 works on this site](https://md.research.elamur.ai/free/en/authors/harish-tayyar-madabushi/#papers) · [214 citations in our library](https://md.research.elamur.ai/free/en/authors/harish-tayyar-madabushi/cited-by/) · 5 more works in our library · [⭐ Paper Star rank #3640](https://md.research.elamur.ai/free/en/paper-stars/page/37/#star-3640) 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=Harish+Tayyar+Madabushi) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Harish+Tayyar+Madabushi) · [dblp](https://dblp.org/search?q=Harish+Tayyar+Madabushi) · [ACL Anthology](https://aclanthology.org/search/?q=Harish+Tayyar+Madabushi) ## Affiliations - [University of Bath](https://ror.org/002h8g185) · Bath, United Kingdom —current · 2022–2026 on 35 papers - [National Research Center for Applied Cybersecurity ATHENE](https://ror.org/0378v2g76) · Darmstadt, Germany —2024–2025 on 2 papers - [University of Birmingham](https://md.research.elamur.ai/free/en/universities/university-of-birmingham/) · Birmingham, United Kingdom —2016–2022 on 20 papers - [University of Sheffield](https://md.research.elamur.ai/free/en/universities/university-of-sheffield/) · Sheffield, United Kingdom —2021–2022 on 8 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed. ## Topics [Language models & pretraining 3](https://md.research.elamur.ai/free/en/topics/language-models/) · [Idioms & multiword expressions 2](https://md.research.elamur.ai/free/en/topics/multiword-expressions/) · [Multilingual & cross-lingual NLP 1](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) ## Works by year ### 2020s [**2025** 1 paper](https://md.research.elamur.ai/free/en/papers/madabushi-2025-construction-grammar-evidence-how-llms/) · [**2024** 1 paper](https://md.research.elamur.ai/free/en/papers/bonial-2024-construction-grammar-corpus-varying-schematicity/) · [**2022** 1 paper](https://md.research.elamur.ai/free/en/papers/madabushi-2022-semeval-2022-task-2-multilingual/) · [**2021** 2 papers](https://md.research.elamur.ai/free/en/authors/harish-tayyar-madabushi/year/2021/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/madabushi-2020-cxgbert-bert-meets-construction-grammar/) ## Papers The most cited first (OpenAlex and our library). 1. **[SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding](https://md.research.elamur.ai/free/en/papers/madabushi-2022-semeval-2022-task-2-multilingual/)** *(2022 · 108 citations)* Idiomatic multiword expressions, such as noun compounds whose meaning cannot be derived from their parts, remain difficult for language models. 2. **[AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models](https://md.research.elamur.ai/free/en/papers/madabushi-2021-astitchinlanguagemodels-dataset-methods-exploration-idiomaticity/)** *(2021 · 86 citations)* Pre-trained language models such as BERT build meaning largely by composing words and sub-words. This makes them weak at handling idiomatic multiword expressions (MWEs). Earlier resources mostly list isolated phrases with compositionality scores, or attach context only to expressions that are always literal or always… 3. **[CxGBERT: BERT meets Construction Grammar](https://md.research.elamur.ai/free/en/papers/madabushi-2020-cxgbert-bert-meets-construction-grammar/)** *(2020 · 43 citations)* The authors test whether BERT has access to information that Construction Grammar (CxG) considers distinct from lexical semantics. 4. **[A Construction Grammar Corpus of Varying Schematicity: A Dataset for the Evaluation of Abstractions in Language Models](https://md.research.elamur.ai/free/en/papers/bonial-2024-construction-grammar-corpus-varying-schematicity/)** *(2024 · 12 citations)* The authors test whether large language models (LLMs) acquire abstract grammatical generalizations. To do so, they draw on Construction Grammar (CxG). The key concept of the paper is schematicity. It indicates whether the slots of a construction require specific fixed words or can be filled by any element with the… 5. **[Learned Construction Grammars Converge Across Registers Given Increased Exposure](https://md.research.elamur.ai/free/en/papers/dunn-2021-learned-construction-grammars-converge-across/)** *(2021 · 11 citations)* The authors test whether construction grammars (CxG) learned from texts of different registers become more similar as the model receives more data. 6. **[Construction Grammar Evidence for How LLMs Use Context-Directed Extrapolation to Solve Tasks](https://md.research.elamur.ai/free/en/papers/madabushi-2025-construction-grammar-evidence-how-llms/)** *(2025 · 1 citation)* This is a position paper on how large language models (LLMs) solve tasks. The authors seek an explanation between two extremes: models as "stochastic parrots" and models as "sparks of AGI". They develop their earlier framework. According to it, both the successful and the erroneous answers of LLMs arise from… ## Also in our library 5 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 7 co-authors with a page, the most papers together first. - [Aline Villavicencio](https://md.research.elamur.ai/free/en/authors/aline-villavicencio/) ×2 - [Carolina Scarton](https://md.research.elamur.ai/free/en/authors/carolina-scarton/) ×2 - [Claire Bonial](https://md.research.elamur.ai/free/en/authors/claire-bonial/) ×2 - [Edward Gow-Smith](https://md.research.elamur.ai/free/en/authors/edward-gow-smith/) ×2 - [Jonathan Dunn](https://md.research.elamur.ai/free/en/authors/jonathan-dunn/) - [Marco Idiart](https://md.research.elamur.ai/free/en/authors/marco-idiart/) - [Marcos Garcia](https://md.research.elamur.ai/free/en/authors/marcos-garcia/) ## Cited by Papers of our library cite their works 214 times (of the 140 884 papers whose bibliographies we read); [30 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/harish-tayyar-madabushi/cited-by/).