We introduce a novel semi-supervised procedure that bootstraps an NLI dataset from existing biomedical dataset that pairs mechanisms with experimental evidence in abstracts.
Ranked #1 on Natural Language Inference on BioNLI
We leverage this structure and create a summarization task, where the input is a collection of sentences and the main entities in an abstract, and the output includes the relationship and a sentence that summarizes the mechanism.
Neural Machine Translation (NMT) models are strong enough to convey semantic and syntactic information from the source language to the target language.
We introduce PerSenT, a dataset of crowd-sourced annotations of the sentiment expressed by the authors towards the main entities in news articles.
Predicting how events induce emotions in the characters of a story is typically seen as a standard multi-label classification task, which usually treats labels as anonymous classes to predict.
Ranked #1 on Emotion Classification on ROCStories
This new loss function yields a total of 1. 87 point improvements in terms of BLEU score in the translation quality.