I'm looking for...

Courses Research People Something else

Unable to find any suggestions for your query...

Prefer to see our subject areas?

Browse courses by subject

Unable to find any suggestions for your query...

Looking for funded postgraduate opportunities?

View doctoral training partnerships Browse postgraduate research opportunities

Unable to find any suggestions for your query...

We are different and we are the same. #WeAreEssex

Read our stories

Unable to find any suggestions for your query...

Looking for student or staff information?

Student Directory Staff Directory

Courses

Unable to find any suggestions for your query...

Prefer to see our subject areas?

Browse courses by subject

Research

Unable to find any suggestions for your query...

Looking for funded postgraduate opportunities?

View doctoral training partnerships Browse postgraduate research opportunities

People

Unable to find any suggestions for your query...

We are different and we are the same. #WeAreEssex

Read our stories

Something else

Unable to find any suggestions for your query...

Looking for student or staff information?

Student Directory Staff Directory

Event

CSEE Seminar Series - Multilingual Dependency Parsing for Low-Resource Languages

Wed 15 Nov 17

16:00 - 18:00
Colchester Campus

1N1.4.1
Event speaker

Professor Thierry Poibeau
Event type

Lectures, talks and seminars
CSEE Seminar Series
Event organiser

Computer Science and Electronic Engineering, School of
Contact details

csee-schooloffice@essex.ac.uk

Thierry Poibeau is a CNRS Director of Research and head of the LATTICE laboratory (Langues, Textes, Traitements informatiques et Cognition) since 2012. He is also an Affiliated Lecturer at the Department of Theoretical and Applied Linguistics (DTAL) of the University of Cambridge. He mainly works on Natural Language Processing (NLP) and linguistics, especially on the following topics: Information Extraction, Question Answering, Semantic Zoning, Knowledge Acquisition from text and Named Entity tagging.

I will present a method for dependency parsing using multilingual word embeddings. I will detail two main contributions. First, we propose a simple approach to building a bilingual dictionary and multilingual word embeddings for low-resource languages. Second, we show a model transfer parsing approach by using high-resource languages as a base model for parsing very low-resource languages. The multilingual approach outperforms the monolingual approach for resource-rich languages, but is especially useful for low resource languages. I will show some results for Finno-Ugric languages like North Saami and Komi. Joint work with KyungTae Lim and Niko Partanen (both at LATTICE, Paris)

Related events

Fri 13 May - Wed 6 Jul 22

Why won’t they behave? Why can’t they learn?

16:30

Online

Thu 23 Jun - Thu 22 Sep 22

Offer holder briefing and pre-departure webinar sessions

09:00

Online