2026-07-23T05:05:01Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:9271 2024-03-06T10:30:19Z ddc:004 open_access

Evaluation of Distributional Models with the Outlier Detection Task Gamallo, Pablo distributional semantics dependency analysis outlier detection similarity In this article, we define the outlier detection task and use it to compare neural-based word embeddings with transparent count-based distributional representations. Using the English Wikipedia as text source to train the models, we observed that embeddings outperform count-based representations when their contexts are made up of bag-of-words. However, there are no sharp differences between the two models if the word contexts are defined as syntactic dependencies. In general, syntax-based models tend to perform better than those based on bag-of-words for this specific task. Similar experiments were carried out for Portuguese with similar results. The test datasets we have created for outlier detection task in English and Portuguese are released. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Pablo Gamallo 2018 Is Part Of OASIcs, Volume 62, 7th Symposium on Languages, Applications and Technologies (SLATE 2018) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.SLATE.2018.13 urn:nbn:de:0030-drops-92717 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.SLATE.2018.13 eng https://creativecommons.org/licenses/by/3.0/legalcode