Papers by Paolo Pedinotti

2 papers
Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge (2021.starsem-1)

Copied to clipboard

Challenge: Prior work has explored the ability of computational models to predict word semantic fit with a given predicate.
Approach: They compare Transformers Language Models to SDM to assess their performance . they found that TLMs do not capture important aspects of event knowledge . people can discriminate between typical and atypical events, they say .
Outcome: The proposed models can achieve comparable performance to SDM, but they lack important aspects of event knowledge.
Don’t Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations (2020.coling-main)

Copied to clipboard

Challenge: a recent study has shown that metonymy is a productive and systematic process . linguistic and psycholinguistic studies support the idea that metnomic interpretations are based on lexical ambiguity .
Approach: They compare BERT to a generalized event knowledge model to capture the meaning shift associated with metonymy.
Outcome: The proposed model is good at predicting the meaning of metonymic expressions, the authors say . they show that the model can capture the meaning shift associated with metonymy .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations