Full Seminar Details

Dr. Goran Glavaš

University of Mannheim

Dr. Goran Glavaš
Projection-Based Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Evaluation, and Some Misconceptions
This event took place on Thursday 10 October 2019 at 15:15


Cross-lingual word embeddings (CLEs) hold promise of multilingual modeling of meaning and cross-lingual transfer of NLP models. Early models for inducing cross-lingual word vector spaces, requiring sentence- or document-level bilingual signal (i.e., parallel or comparable corpora) have recently been replaced by resource-leaner projection-based CLE models, which require cheap word-level bilingual supervision or even no supervision as all. Despite the ubiquitous usage of CLEs in downstream tasks, they are almost exclusively evaluated intrinsically only on the task of bilingual lexicon induction (BLI). Even BLI evaluations vary greatly, preventing us from correctly interpreting performance and behavior of different CLE models. In this talk, I will present initial steps towards a comprehensive evaluation of cross-lingual word embeddings. I will present results of a systemmatic comparative evaluation of both supervised and unsupervised projection-based CLE models on a large number of language pairs, both in BLI and three diverse downstream tasks, and provide new insights about the ability of cutting-edge CLE models to support cross-lingual NLP. Our study shows that performance of CLE models largely depends on the downstream task and that overfitting CLE models to BLI can severely hurt downstream performance. Finally, I will indicate the most robust supervised and unsupervised CLE models and emphasize the need to reassess simple baselines, which display competitive performance in many settings.

Watch the webcast replay >>

Jobs

Software Developer (Grade 6)

Knowledge Media Institute (KMi)
£27,511 - £32,817
Based in Milton Keynes
Permanent Appointment

The Open University is the UK's largest university, a world leader in flexible part-time education combining a mission to widen access to higher education with research excellence, transforming lives through education. The role This position is...

CONTACT US

Knowledge Media Institute
The Open University
Walton Hall
Milton Keynes
MK7 6AA
United Kingdom

Tel: +44 (0)1908 653800

Fax: +44 (0)1908 653169

Email: KMi Support

COMMENT

If you have any comments, suggestions or general feedback regarding our website, please email us at the address below.

Email: KMi Development Team