Iryna Gurevych
Iryna Gurevych wrote 7 of the papers Mova reads, in 2010–2023, most of them on Machine translation, Dependency parsing, Semantic role labeling; often with Bonnie Webber, Christian M. Meyer, Delphine Bernhard.
OpenAlex · ORCID · h-index 73 · 34089 citations · 861 works — openalex, 2026-10-18
Topics: Machine translation 2 · Dependency parsing 1 · Semantic role labeling 1
Papers
- Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future (2023)
The authors survey methods for finding annotation errors, reimplement 18 of them, and test them on 9 English datasets for text classification, token labelling and span labelling. - IMPLI: Investigating NLI Models' Performance on Figurative Language (2022)
IMPLI pairs sentences containing an idiom or metaphor with a literal sentence that is or is not entailed by it: 24,029 silver pairs and 1,831 hand-written gold pairs. - BinLin: A Simple Method of Dependency Tree Linearization (2018)
The paper is a system report for the shallow track of SR'18. The input is a bag of lemmatised UD nodes with their tags and morphology. The system works in two stages: it first orders the lemmas, and then it conjugates and inflects each word. The contribution is a sequential way of ordering lemmas. It is simple and it… - Out-of-domain FrameNet Semantic Role Labeling (2017)
FrameNet role labeling is usually tested on one in-domain set (das-test). The authors test how it generalises. They build YAGS, a new test set of 1,415 sentences from Yahoo! Answers with 3,091 frame and 6,081 role annotations. Inter-rater agreement is Krippendorff's alpha 0.76 for frames and 0.62 for roles given… - WordNet—Wikipedia—Wiktionary: Construction of a Three-way Alignment (2014)
The paper builds a three-way alignment of senses from existing pairwise alignments of WordNet with Wikipedia and with Wiktionary. - To Exhibit is not to Loiter: A Multilingual, Sense-Disambiguated Wiktionary for Measuring Verb Similarity (2012)
The paper turns Wiktionary's semantic relations and translations into a sense-disambiguated resource. Each relation or translation is linked to one sense of its target word by a method that combines features such as a monolingual-only candidate, a source-overlap score, a lexical-expansion score, a relation score and… - A Monolingual Tree-based Translation Model for Sentence Simplification (2010)
The paper treats sentence simplification as translation from complex to simple sentences, with the complex parse tree as the source.
Co-authors (12)
- Bonnie Webber
- Christian M. Meyer
- Delphine Bernhard
- Ilia Kuznetsov
- Jan-Christoph Klie
- Kevin Stowe
- Prasetya Utama
- Silvana Hartmann
- Teresa Martin
- Tristan Miller
- Yevgeniy Puzikov
- Zhemin Zhu
This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/iryna-gurevych/