--- title: "Kristina Gulordava — author profile and papers" description: "Kristina Gulordava: 2 papers on Elamur Research (2011–2018), h-index 10 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/kristina-gulordava/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/kristina-gulordava/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Kristina Gulordava # Kristina Gulordava Kristina Gulordava works in computational linguistics, on the question of what statistical models of language actually pick up from text. Their papers here span 2011 to 2018 and move between two concerns: how word meaning can be read off co-occurrence patterns in large corpora, and whether neural language models learn grammatical structure rather than surface regularities. The methods are empirical and corpus-based, from context vectors built on n-gram counts to recurrent networks tested on sentences drawn from dependency treebanks in several languages. One strand of the work falls under [Historical linguistics & language change](https://md.research.elamur.ai/free/en/topics/language-change/). The most cited of the papers here is [Colorless Green Recurrent Networks Dream Hierarchically](https://md.research.elamur.ai/free/en/papers/gulordava-2018-colorless-green-recurrent-networks-dream/) (2018). It challenges an earlier finding that LSTMs cannot manage long-distance agreement without being explicitly supervised for it. It tests models trained only on next-word prediction against number-agreement cases in Italian, English, Hebrew and Russian. Each test sentence also gets a "nonce" counterpart in which content words are replaced by random words of matching morphology, so the sentence stays grammatical but loses its meaning. The earlier paper, [A distributional similarity approach to the detection of semantic change](https://md.research.elamur.ai/free/en/papers/gulordava-2011-distributional-similarity-approach-detection-semantic/) (2011), compares vectors for the same word in the early 1960s and late 1990s using American English bigrams from Google Books. The vectors share one set of context dimensions, a low cosine between them signals a shift in meaning, and the scores are judged against human ratings and against a frequency-change baseline. Taken in order, the papers move from lexical semantics and diachronic change toward probing the syntactic abilities of neural networks. Bylines on Gulordava's papers include the [University of Geneva](https://md.research.elamur.ai/free/en/universities/university-of-geneva/) (2015–2020) and [Universitat Pompeu Fabra](https://md.research.elamur.ai/free/en/universities/universitat-pompeu-fabra/) in Barcelona (2018–2020), with earlier papers from the [University of Trento](https://md.research.elamur.ai/free/en/universities/university-of-trento/). [Marco Baroni](https://md.research.elamur.ai/free/en/authors/marco-baroni/) co-authored both works here. Other co-authors include [Tal Linzen](https://md.research.elamur.ai/free/en/authors/tal-linzen/), [Edouard Grave](https://md.research.elamur.ai/free/en/authors/edouard-grave/) and [Piotr Bojanowski](https://md.research.elamur.ai/free/en/authors/piotr-bojanowski/). Kristina Gulordava has 2 papers in our library, in 2011–2018, most of them on [Historical linguistics & language change](https://md.research.elamur.ai/free/en/topics/language-change/); often with [Marco Baroni](https://md.research.elamur.ai/free/en/authors/marco-baroni/), [Edouard Grave](https://md.research.elamur.ai/free/en/authors/edouard-grave/), [Piotr Bojanowski](https://md.research.elamur.ai/free/en/authors/piotr-bojanowski/). 2 papers in our library · 2011–2018 [OpenAlex](https://openalex.org/A5043347279) · [**h-index 10**](https://openalex.org/authors/A5043347279) · [19 works](https://openalex.org/works?filter=author.id:A5043347279) · [832 citations](https://openalex.org/works?filter=author.id:A5043347279&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/kristina-gulordava/#papers) · [398 citations in our library](https://md.research.elamur.ai/free/en/authors/kristina-gulordava/cited-by/) · 3 more works in our library · [⭐ Paper Star rank #1997](https://md.research.elamur.ai/free/en/paper-stars/page/20/#star-1997) 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=Kristina+Gulordava) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Kristina+Gulordava) · [dblp](https://dblp.org/search?q=Kristina+Gulordava) · [ACL Anthology](https://aclanthology.org/search/?q=Kristina+Gulordava) ## Affiliations [🎓**University of Geneva** Geneva · Switzerland 2015–2020 · 8 papers](https://md.research.elamur.ai/free/en/universities/university-of-geneva/) · [🎓**Universitat Pompeu Fabra** Barcelona · Spain 2018–2020 · 5 papers](https://md.research.elamur.ai/free/en/universities/universitat-pompeu-fabra/) · [🎓**University of Trento** Trento · Italy 2011–2019 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-trento/) 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 [Historical linguistics & language change 1](https://md.research.elamur.ai/free/en/topics/language-change/) ## Works by year ### 2010s [**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/gulordava-2018-colorless-green-recurrent-networks-dream/) · [**2011** 1 paper](https://md.research.elamur.ai/free/en/papers/gulordava-2011-distributional-similarity-approach-detection-semantic/) ## Papers The most cited first (OpenAlex and our library). 1. **[Colorless Green Recurrent Networks Dream Hierarchically](https://md.research.elamur.ai/free/en/papers/gulordava-2018-colorless-green-recurrent-networks-dream/)** *(2018 · 759 citations)* The paper asks whether recurrent networks trained only for next-word prediction learn abstract syntactic structure, or whether they mostly rely on surface patterns. 2. **[A distributional similarity approach to the detection of semantic change in the Google Books Ngram corpus.](https://md.research.elamur.ai/free/en/papers/gulordava-2011-distributional-similarity-approach-detection-semantic/)** *(2011 · 240 citations)* The paper asks whether distributional semantics can automatically flag English words whose meaning shifted between the 1960s and the 1990s, and whether it does better than a plain frequency-change signal. ## Also in our library 3 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 4 co-authors with a page, the most papers together first. - [Marco Baroni](https://md.research.elamur.ai/free/en/authors/marco-baroni/) ×2 - [Edouard Grave](https://md.research.elamur.ai/free/en/authors/edouard-grave/) - [Piotr Bojanowski](https://md.research.elamur.ai/free/en/authors/piotr-bojanowski/) - [Tal Linzen](https://md.research.elamur.ai/free/en/authors/tal-linzen/) ## Cited by Papers of our library cite their works 398 times (of the 140 884 papers whose bibliographies we read); [57 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/kristina-gulordava/cited-by/).