Title: Natural Language Inference with Multilingual Supervision
Natural Language Inference (NLI) is the task of identifying
inferential relationships between a premise p and a given hypothesis
h. Both, p and h are expressed in natural language, typically as a
pair of sentences with a specific relationship between them coming
from a limited set of inferential relations (e.g. entailment,
contradiction, neutral). NLI requires semantic analyses and,
therefore, can be seen as a test of text understanding capabilities of
a system. Modern NLI models are based on deep neural nets and either
cross-sentential encoding or independent sentence embeddings. In this
talk, I will present our work on sentence representation learning and
its appliction to common NLI benchmarks. I will start with the
introduction of a state-of-the-art supervised NLI model with
hierarchical bi-LSTM architectures and, after that, discuss our
research in multilingual supervision for representation learning. The
latter is motivated by the use of translations as semantic mirrors and
the idea of applying highly multilingual data sets in neural machine
translation to learn language-independent meaning representations.
Jörg Tiedemann is a professor of language technology at the Department of Modern Languages at the University of Helsinki. His main research interest is in cross-lingual NLP and machine translation.
This particular meetup is part of a seminar series on Natural Language Processing funded by the Centre for Communication and Computing (CCC) at the University of Copenhagen. There will be refreshments from 16:30, the talk will start at 17:00.