Assistant Professor Marine Carpuat and PhD student Yogarshi Vyas awarded best paper

Assistant Professor Marine Carpuat and PhD Student Yogarshi Vyas were awarded the Adam Kilgarriff Best Paper Award at the SEM conference (Joint Conference on Lexical and Computational Semantics) in August. Their  paper is entitled "Detecting Asymmetric Semantic Relations in Context : A Case Study on Hypernymy Detection."

Vyas explained that the paper address a key challenge in natural language understanding, which is the building of models that can understand the meaning of words and the relations that exist between them. One such relation is hypernymy, which can be defined as an “is-a” relation.  For example, the word game in “The championship game was played in NYC” is a hypernym of the word chess in “Anand is a chess champion” because chess is a (type of) game.

Vyas said that "Our paper introduces a new dataset for the problem of hypernymy detection that requires taking into account the context in which words are used. A major strength of our dataset is that it allows us to identify how models for this task behave in two aspects 1) The sensitivity of models to changes in context and 2) The ability of models to accurately detect the direction of hypernymy. This detailed analysis allows us to separate the impact of these factors, paving the way for better models of word meaning in the future."

Carpuat was also invited to give a keynote talk at the Machine Translation Summit XVI in Nagoya, Japan, on September 20 where she spoke about her work on semantic and stylistic divergences in machine translation.