SOTAVerified

Lemmatization

Lemmatization is a process of determining a base or dictionary form (lemma) for a given surface form. Especially for languages with rich morphology it is important to be able to normalize words into their base forms to better support for example search engines and linguistic studies. Main difficulties in Lemmatization arise from encountering previously unseen words during inference time as well as disambiguating ambiguous surface forms which can be inflected variants of several different base forms depending on the context.

Source: Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks

Papers

Showing 111120 of 351 papers

TitleStatusHype
Enhancing Lemmatization for Mongolian and its Application to Statistical Machine Translation0
Developing New Linguistic Resources and Tools for the Galician Language0
Automatic Extraction of Synonyms for German Particle Verbs from Parallel Data with Distributional Similarity as a Re-Ranking Feature0
ENIAM: Categorial Syntactic-Semantic Parser for Polish0
Enrichir et raisonner sur des espaces s\'emantiques pour l'attribution de mots-cl\'es (Enriching and reasoning on semantic spaces for keyword extraction) [in French]0
Evaluating Contextualized Embeddings on 54 Languages in POS Tagging, Lemmatization and Dependency Parsing0
Evaluating Diversity of Multiword Expressions in Annotated Text0
Evaluating Lemmatization Models for Machine-Assisted Corpus-Dictionary Linkage0
Describing Language Variation in the Colophons of Armenian Manuscripts0
DerivBase.hr: A High-Coverage Derivational Morphology Resource for Croatian0
Show:102550
← PrevPage 12 of 36Next →

No leaderboard results yet.