Papers by Thomas Troelsgård

3 papers
A Thesaurus-based Sentiment Lexicon for Danish: The Danish Sentiment Lexicon (2022.lrec-1)

Copied to clipboard

Challenge: a newly published Danish sentiment lexicon with a high lexical coverage was compiled using lexicographic methods and linked data.
Approach: They propose to use lexicographic methods to compile a Danish sentiment lexicon with a high lexical coverage by linking words from a thesaurus to a comprehensive monolingual dictionary.
Outcome: The proposed lexicon contains 13,859 Danish polarity lemmas and includes morphological information.
Compiling a Suitable Level of Sense Granularity in a Lexicon for AI Purposes: The Open Source COR Lexicon (2022.lrec-1)

Copied to clipboard

Challenge: The central word register for Danish is an open source lexicon project for general AI purposes funded and initiated by the Danish Agency for Digitisation in 2020.
Approach: They propose to use existing fine-grained sense inventory to compile a more AI-appropriate sense granularity level of the vocabulary.
Outcome: The proposed lexical resource is based on the fine-grained sense inventory from Den Danske Ordbog (DDO) it is designed to be more practical and suitable for AI, omitting outdated language and slang, merging subtle and rare sub-senses with their main sense, disregarding sub-domains, etc.
A Multilingual Evaluation Dataset for Monolingual Word Sense Alignment (2020.lrec-1)

Copied to clipboard

Challenge: a new dataset aims to align monolingual dictionaries with a single sense level for 15 languages . this dataset covers a wide range of languages and resources .
Approach: They propose to manually align monolingual dictionaries with possible semantic relationships . they use 15 languages to create a new baseline for the task of monolingual word sense alignment .
Outcome: The proposed dataset covers 15 languages and covers the more challenging task of linking general-purpose language.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations