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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–175 of 351 papers

TitleStatusHype
Attention-free encoder decoder for morphological processing—0
NLP-Cube: End-to-End Raw Text Processing With Neural NetworksCode0
LemmaTag: Jointly Tagging and Lemmatizing for Morphologically Rich Languages with BRNNsCode0
Building a Lemmatizer and a Spell-checker for Sorani Kurdish—0
Towards JointUD: Part-of-speech Tagging and Lemmatization using Recurrent Neural NetworksCode0
Imitation Learning for Neural Morphological String TransductionCode0
LemmaTag: Jointly Tagging and Lemmatizing for Morphologically-Rich Languages with BRNNsCode0
Neural Transition-based String Transduction for Limited-Resource Setting in MorphologyCode0
From Text to Lexicon: Bridging the Gap between Word Embeddings and Lexical ResourcesCode0
Local String Transduction as Sequence Labeling—0
An Evaluation of Lexicon-based Sentiment Analysis Techniques for the Plays of Gotthold Ephraim Lessing—0
Resource-Size matters: Improving Neural Named Entity Recognition with Optimized Large CorporaCode0
Character-level Supervision for Low-resource POS Tagging—0
Fast Query Expansion on an Accounting Corpus using Sub-Word Embeddings—0
IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge SourceCode0
Context Sensitive Neural Lemmatization with Lematus—0
Tw-StAR at SemEval-2018 Task 1: Preprocessing Impact on Multi-label Emotion Classification—0
Robustness of sentence length measures in written texts—0
The Use of Text Alignment in Semi-Automatic Error Analysis: Use Case in the Development of the Corpus of the Latvian Language Learners—0
Parser combinators for Tigrinya and Oromo morphology—0
Universal Morphologies for the Caucasus region—0
Developing New Linguistic Resources and Tools for the Galician Language—0
Moving TIGER beyond Sentence-Level—0
Sudachi: a Japanese Tokenizer for BusinessCode0
Generating a Gold Standard for a Swedish Sentiment Lexicon—0
Show:102550
← PrevPage 7 of 15Next →

No leaderboard results yet.