Conference paper Open Access
Elaine Zosa; Mark Granroth-Wilding
{ "publisher": "Zenodo", "DOI": "10.5281/zenodo.3402878", "language": "eng", "title": "Multilingual Dynamic Topic Model", "issued": { "date-parts": [ [ 2019, 9, 2 ] ] }, "abstract": "<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>", "author": [ { "family": "Elaine Zosa" }, { "family": "Mark Granroth-Wilding" } ], "id": "3402878", "event-place": "Bulgaria", "type": "paper-conference", "event": "Recent Advances in Natural Language Processing (RANLP)" }
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 |