Zobrazeno 1 - 10
of 255
pro vyhledávání: '"Romeo, Salvatore"'
Autor:
Davidson, Sam, Romeo, Salvatore, Shu, Raphael, Gung, James, Gupta, Arshit, Mansour, Saab, Zhang, Yi
One of the major impediments to the development of new task-oriented dialogue (TOD) systems is the need for human evaluation at multiple stages and iterations of the development process. In an effort to move toward automated evaluation of TOD, we pro
Externí odkaz:
http://arxiv.org/abs/2309.13233
Autor:
Sung, Mujeen, Gung, James, Mansimov, Elman, Pappas, Nikolaos, Shu, Raphael, Romeo, Salvatore, Zhang, Yi, Castelli, Vittorio
Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples for each user intent. We propose a novel pre-training method for text
Externí odkaz:
http://arxiv.org/abs/2305.14827
Autor:
Gung, James, Shu, Raphael, Moeng, Emily, Rose, Wesley, Romeo, Salvatore, Benajiba, Yassine, Gupta, Arshit, Mansour, Saab, Zhang, Yi
With increasing demand for and adoption of virtual assistants, recent work has investigated ways to accelerate bot schema design through the automatic induction of intents or the induction of slots and dialogue states. However, a lack of dedicated be
Externí odkaz:
http://arxiv.org/abs/2304.12982
Autor:
Shu, Raphael, Mansimov, Elman, Alkhouli, Tamer, Pappas, Nikolaos, Romeo, Salvatore, Gupta, Arshit, Mansour, Saab, Zhang, Yi, Roth, Dan
Functionality and dialogue experience are two important factors of task-oriented dialogue systems. Conventional approaches with closed schema (e.g., conversational semantic parsing) often fail as both the functionality and dialogue experience are str
Externí odkaz:
http://arxiv.org/abs/2212.09946
Autor:
Mueller, Aaron, Krone, Jason, Romeo, Salvatore, Mansour, Saab, Mansimov, Elman, Zhang, Yi, Roth, Dan
In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of label-semanti
Externí odkaz:
http://arxiv.org/abs/2204.07128
Publikováno v:
EMNLP 2021
Recent studies have proposed different methods to improve multilingual word representations in contextualized settings including techniques that align between source and target embedding spaces. For contextualized embeddings, alignment becomes more c
Externí odkaz:
http://arxiv.org/abs/2110.02887
Autor:
Romeo, Salvatore
Publikováno v:
Meridiana, 2023 Jan 01(108), 39-60.
Externí odkaz:
https://www.jstor.org/stable/27307054
Autor:
Romeo, Salvatore
Publikováno v:
Meridiana, 2023 Jan 01(106), 15-38.
Externí odkaz:
https://www.jstor.org/stable/27225173
Autor:
Zhang, Yifan, Martino, Giovanni Da San, Barrón-Cedeño, Alberto, Romeo, Salvatore, An, Jisun, Kwak, Haewoon, Staykovski, Todor, Jaradat, Israa, Karadzhov, Georgi, Baly, Ramy, Darwish, Kareem, Glass, James, Nakov, Preslav
Publikováno v:
EMNLP-2019
We introduce Tanbih, a news aggregator with intelligent analysis tools to help readers understanding what's behind a news story. Our system displays news grouped into events and generates media profiles that show the general factuality of reporting,
Externí odkaz:
http://arxiv.org/abs/1910.02028
We address the problem of detecting duplicate questions in forums, which is an important step towards automating the process of answering new questions. As finding and annotating such potential duplicates manually is very tedious and costly, automati
Externí odkaz:
http://arxiv.org/abs/1809.02255