Conference paper Open Access
Elaine Zosa; Mark Granroth-Wilding
{ "inLanguage": { "alternateName": "eng", "@type": "Language", "name": "English" }, "description": "<p>Dynamic topic models (DTMs) capture the evolution of topics and trends in time series data.<br>\nCurrent DTMs are applicable only to monolingual datasets. In this paper we present the multilingual<br>\ndynamic topic model (ML-DTM), a novel topic model that combines DTM with an existing multilingual<br>\ntopic modeling method to capture crosslingual topics that evolve across time. We present<br>\nresults of this model on a parallel German-English corpus of news articles and a comparable corpus<br>\nof Finnish and Swedish news articles. We demonstrate the capability of ML-DTM to track significant<br>\nevents related to a topic and show that it finds distinct topics and performs as well as existing<br>\nmultilingual topic models in aligning cross-lingual topics.</p>", "license": "https://creativecommons.org/licenses/by/4.0/legalcode", "creator": [ { "affiliation": "University of Helsinki", "@type": "Person", "name": "Elaine Zosa" }, { "affiliation": "University of Helsinki", "@type": "Person", "name": "Mark Granroth-Wilding" } ], "headline": "Multilingual Dynamic Topic Model", "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", "datePublished": "2019-09-02", "url": "https://zenodo.org/record/3402878", "@type": "ScholarlyArticle", "keywords": [ "Topic modeling" ], "@context": "https://schema.org/", "identifier": "https://doi.org/10.5281/zenodo.3402878", "@id": "https://doi.org/10.5281/zenodo.3402878", "workFeatured": { "url": "http://lml.bas.bg/ranlp2019/start.php", "alternateName": "RANLP", "location": "Bulgaria", "@type": "Event", "name": "Recent Advances in Natural Language Processing" }, "name": "Multilingual Dynamic Topic Model" }
All versions | This version | |
---|---|---|
Views | 365 | 365 |
Downloads | 444 | 444 |
Data volume | 176.8 MB | 176.8 MB |
Unique views | 321 | 321 |
Unique downloads | 429 | 429 |