no code implementations • 7 Dec 2023 • Zijie Huang, Baolin Li, Hafez Asgharzadeh, Anne Cocos, Lingyi Liu, Evan Cox, Colby Wise, Sudarshan Lamkhede
Given a set of candidate entities (e. g. movie titles), the ability to identify similar entities is a core capability of many recommender systems.
no code implementations • WS 2019 • Aina Gar{\'\i} Soler, Anne Cocos, Marianna Apidianaki, Chris Callison-Burch
Word embedding representations provide good estimates of word meaning and give state-of-the art performance in semantic tasks.
no code implementations • TACL 2019 • Anne Cocos, Chris Callison-Burch
Many natural language processing tasks require discriminating the particular meaning of a word in context, but building corpora for developing sense-aware models can be a challenge.
no code implementations • EMNLP 2018 • Anne Cocos, Skyler Wharton, Ellie Pavlick, Marianna Apidianaki, Chris Callison-Burch
Adjectives like {``}warm{''}, {``}hot{''}, and {``}scalding{''} all describe temperature but differ in intensity.
no code implementations • NAACL 2018 • Anne Cocos, Marianna Apidianaki, Chris Callison-Burch
In this paper, we present a head-to-head comparison of six taxonomic organization algorithms that vary with respect to their structural and transitivity constraints, and treatment of synonymy.
no code implementations • NAACL 2018 • Marianna Apidianaki, Guillaume Wisniewski, Anne Cocos, Chris Callison-Burch
We propose a variant of a well-known machine translation (MT) evaluation metric, HyTER (Dreyer and Marcu, 2012), which exploits reference translations enriched with meaning equivalent expressions.
no code implementations • EMNLP 2017 • Ross Mechanic, Dean Fulgoni, Hannah Cutler, Sneha Rajana, Zheyuan Liu, Bradley Jackson, Anne Cocos, Chris Callison-Burch, Marianna Apidianaki
Semantic relation knowledge is crucial for natural language understanding.
no code implementations • SEMEVAL 2017 • Anne Cocos, Marianna Apidianaki, Chris Callison-Burch
WordNet has facilitated important research in natural language processing but its usefulness is somewhat limited by its relatively small lexical coverage.
no code implementations • WS 2017 • Anne Cocos, Marianna Apidianaki, Chris Callison-Burch
The role of word sense disambiguation in lexical substitution has been questioned due to the high performance of vector space models which propose good substitutes without explicitly accounting for sense.
no code implementations • EACL 2017 • Anne Cocos, Chris Callison-Burch
There is a relationship between what we say and where we say it.