#4: Spoken Language Corpora & Paraphrase Learning

The fourth Natural Language Processing & Text Analytics Meetup will take place at the University of Zurich. Thanks to Martin Volk and the Institute of Computational Linguistics for hosting this session. Martin will give an overview of the NLP research carried out at the institute. Dolores Batinić will present her current research at the Department of Lexical Studies at the Institute for the German Language in Mannheim, and Mark Fishel will talk about paraphrase learning.

Each presentation is 20−30 minutes followed by a short discussion time. Please RSVP on the meetup site. See you soon!

Agenda

18:30 Welcome

18:40 Martin Volk (UZH): NLP Research at the Institute of Computational Linguistics

19:00 Dolores Batinić (IDS): Requirements for Spoken Language Corpora for Linguistic Purposes

19:30 Mark Fishel (University of Tartu): Open-Vocabulary N-gram Embeddings

20:00 Networking

Information

Dolores Batinić: Requirements for Spoken Language Corpora for Linguistic Purposes

Abstract: I am going to present current work at the department of pragmatics and lexical studies at the Institute for the German Language in Mannheim, mainly focusing on creation and use of spoken language corpora.

Bio:

• Research assistant at the Institute for the German Language in Mannheim, Germany
• Background: Study of Multilingual text analysis and Slavonic languages and literature at the University of Zurich
• Interests: Digital Humanities, Spoken Language Processing, Interactional Linguistics

Mark Fishel: Open-Vocabulary N-gram Embeddings

Abstract: We present an approach to learning continuous vector space representations for n-grams. As a result, one can automatically discover synonymous phrase pairs like "hates" ~= "does not like". We will present the approach itself and its applications to evaluating translation quality and automatic paraphrasing.

Bio: Mark is the head of chair of NLP at the University of Tartu. Before that, he was a post-doctoral researcher at the Institute of Computational Linguistics, University of Zurich, working on machine translation. His topics of interest include machine translation and computational language learning with minimal supervision.

Location

University of Zurich, Room 2.A.01, Binzmühlestrasse 14, Zurich Oerlikon 8050

Sponsors

University of Zurich, Institute of Computational Linguistics (http://www.cl.uzh.ch/)

Swiss Re