Skip to yearly menu bar Skip to main content


Poster

Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages

Michelle Yuan · Benjamin Van Durme · Jordan Boyd-Graber

Room 210 #14

Keywords: [ Spectral Methods ] [ Natural Language Processing ] [ Fairness, Accountability, and Transparency ] [ Topic Models ]


Abstract:

Multilingual topic models can reveal patterns in cross-lingual document collections. However, existing models lack speed and interactivity, which prevents adoption in everyday corpora exploration or quick moving situations (e.g., natural disasters, political instability). First, we propose a multilingual anchoring algorithm that builds an anchor-based topic model for documents in different languages. Then, we incorporate interactivity to develop MTAnchor (Multilingual Topic Anchors), a system that allows users to refine the topic model. We test our algorithms on labeled English, Chinese, and Sinhalese documents. Within minutes, our methods can produce interpretable topics that are useful for specific classification tasks.

Live content is unavailable. Log in and register to view live content