Till startsida
University of Gothenburg
To content Read more about how we use cookies on gu.se

CLASP seminar with Aarne Talman, "Neural Network models of NLI fail to capture the general notion of inference"

Research profile seminar

CLASP seminar with Aarne Talman, "Neural Network models of NLI fail to capture the general notion of inference".

Natural language inference (NLI), the task of determining if a sentence is entailed by one or more given sentences, has been a very popular line of research in the NLP community. Due to the popularity and recent advances in neural network architectures, significant progress has been made in NLI research, especially with the introduction of various pre-trained contextual language models, like ELMo and BERT. However there are number of concerns also raised about the current NLI research mostly due to the shortcomings of the current NLI datasets.

In my talk I will introduce the neural network approaches used in NLI and describe our sentence representation architecture, Hierarchical BiLSTMs (HBMP), which has been successful in many NLI tasks. I will give an overview of some of the criticism and negative results in NLI and show how in our most recent experiments even the pre-trained language models fail to generalise across different NLI datasets.

Lecturer: Aarne Talman

Date: 3/8/2019

Time: 1:15 PM - 3:00 PM

Categories: Linguistics

Location: Olof Wijksgatan 6, T304

Contact person: Stergios chatzikyriakidis


To the calendar

Page Manager: Stergios Chatzikyriakidis|Last update: 5/23/2016

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?

Denna text är utskriven från följande webbsida:
Utskriftsdatum: 2019-07-21