COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Language Technology Lab Seminars > Pitfalls in Evaluation of Multilingual Text Representations
Pitfalls in Evaluation of Multilingual Text RepresentationsAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Marinela Parovic. Multilingual representation spaces, spanned by multilingual word embeddings or massively multilingual transformers, conceptually enable modeling of meaning across a wide range of languages and language transfer of task-specific NLP models from resource-rich to resource-lean languages. It is not yet clear, however, to which extent this conceptual promise holds in practice. Recent models, both cross-lingual word embedding models and multilingual transformers, have been praised for being able to induce multilingual representation spaces without any explicit supervision (i.e., without any word-level alignments or parallel corpora). In this talk, I will point to some prominent shortcomings and pitfalls of existing evaluations of multilingual representation spaces, which mask important limitations of state-of-the-art multilingual representation models. Remedying for some of these evaluation shortcomings, portrays meaning representation and language transfer capabilities of current state-of-the-art multilingual representation spaces in a less favorable light. This talk is part of the Language Technology Lab Seminars series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsArts, Culture and Education University of Cambridge - Politecnico di Torino Coercion Lecture SeriesOther talksExperiencing Republican Texts Nominalism in the social sciences: promises and pitfalls Title: The Long and Winding Road “It’s how you think, not what you think about”: a Career Spent at Interfaces Thucydides’ Tragic Science of Democratic Defeat |