Marie-Catherine de Marneffe — Identifying speaker commitment for natural language understanding

CENTAL Louvain-La-Neuve

06 mai 2021

14h00 - 15h00

Marie-Catherine de Marneffe - Professeure associée au département de linguistique à The Ohio State University, CENTAL


When we communicate, we infer a lot beyond the literal meaning of the words we hear or read. In particular, our understanding of an utterance depends on assessing the extent to which the speaker stands by the event she describes. An unadorned declarative like “The cancer has spread” conveys firm speaker commitment of the cancer having spread, whereas “There are some indicators that the cancer has spread” imbues the claim with uncertainty. It is not only the absence vs. presence of embedding material th at determines whether or not a speaker is committed to the event described: from (1) we will infer that the speaker is committed to there being war, whereas in (2) we will infer the speaker is committed to relocating species not being a panacea, even though the clauses that describe the events in (1) and (2) are both embedded under “(s)he doesn’t believe”.

 (1) The problem, I’m afraid, with my colleague here, he really doesn’t believe that it’s war.

 (2) Transplanting an ecosystem can be risky, as history shows. Hellmann doesn’t believe that relocating species threatened by climate change is a panacea.

In this talk, I will first illustrate how looking at pragmatic information of what speakers are committed to can improve NLP applications. Previous work has tried to predict the outcome of contests (such as the Oscars or elections) from tweets. I will show that by distinguishing tweets that convey firm speaker commitment toward a given outcome (e.g., “Dunkirk will win Best Picture in 2018”) from ones that only suggest the outcome (e.g., “Dunkirk might have a shot at the 2018 Oscars”) or tweets that convey the negation of the event (“Dunkirk is good but not academy level good for the Oscars”), we can outperform previous methods. Second, I will evaluate current models of speaker commitment, using the CommitmentBank, a dataset of naturally occurring discourses developed to deepen our understanding of the factors at play in identifying speaker commitment. I will show that current models fail on items that necessitate pragmatic knowledge, highlighting directions for improvement.

Date et heure : Le 06 mai 2021 de 14h00 à 15h00

Lieu : Afin de respecter les mesures sanitaires en vigueur, la conférence se tiendra en visioconférence. Elle est accessible via la lien suivant : Marie-Catherine de Marneffe - 06 mai 2021Si vous rencontrez des problèmes pour vous connecter, n'hésitez pas à contacter Erika Lombart ( 

Categories Events: