Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Ndapa Nakashole"'
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df748504a71e55288c50fe336f09b306
https://doi.org/10.1109/icassp49357.2023.10097246
https://doi.org/10.1109/icassp49357.2023.10097246
Autor:
Bosung Kim, Ndapa Nakashole
Publikováno v:
Proceedings of the 21st Workshop on Biomedical Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::955f6501824750ad8a405aed984a30fa
https://doi.org/10.18653/v1/2022.bionlp-1.29
https://doi.org/10.18653/v1/2022.bionlp-1.29
Autor:
Xinxin Yan, Ndapa Nakashole
Technologies for enhancing well-being, healthcare vigilance and monitoring are on the rise. However, despite patient interest, such technologies suffer from low adoption. One hypothesis for this limited adoption is loss of human interaction that is c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f4744609cf5a23190868a61ba36c205d
http://arxiv.org/abs/2111.14083
http://arxiv.org/abs/2111.14083
Publikováno v:
Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations.
Understanding the intent of medical questions asked by patients, or Consumer Health Questions, is an essential skill for medical Conversational AI systems. We propose a novel data-augmented and simple joint learning approach combining question summar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::23c7841c7ce206434cec60417d966149
https://doi.org/10.18653/v1/2021.nlpmc-1.8
https://doi.org/10.18653/v1/2021.nlpmc-1.8
Publikováno v:
ACL/IJCNLP (1)
Syntactic structure is an important component of natural language text. Recent top-performing models in Answer Sentence Selection (AS2) use self-attention and transfer learning, but not syntactic structure. Tree structures have shown strong performan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d6da69ea9033d59e7fe3ad3146855046
https://doi.org/10.18653/v1/2021.acl-long.358
https://doi.org/10.18653/v1/2021.acl-long.358
Publikováno v:
NAACL-HLT (Demonstrations)
We present an interactive Plotting Agent, a system that enables users to directly manipulate plots using natural language instructions within an interactive programming environment. The Plotting Agent maps language to plot updates. We formulate this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4007dd94bccba3c188fee51731918474
https://doi.org/10.18653/v1/2021.naacl-demos.11
https://doi.org/10.18653/v1/2021.naacl-demos.11
UCSD-Adobe at MEDIQA 2021: Transfer Learning and Answer Sentence Selection for Medical Summarization
Autor:
Franck Dernoncourt, Emilias Farcas, Ndapa Nakashole, Khalil Mrini, Seung-Hyun Yoon, Trung Bui, Walter Chang
Publikováno v:
BioNLP@NAACL-HLT
In this paper, we describe our approach to question summarization and multi-answer summarization in the context of the 2021 MEDIQA shared task (Ben Abacha et al., 2021). We propose two kinds of transfer learning for the abstractive summarization of m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b7ce3192a64d0651b0b41917c722bb56
https://doi.org/10.18653/v1/2021.bionlp-1.28
https://doi.org/10.18653/v1/2021.bionlp-1.28
Autor:
Trung Bui, Franck Dernoncourt, Ndapa Nakashole, Seung-Hyun Yoon, Emilia Farcas, Khalil Mrini, Walter Chang
Publikováno v:
ACL/IJCNLP (1)
Users of medical question answering systems often submit long and detailed questions, making it hard to achieve high recall in answer retrieval. To alleviate this problem, we propose a novel Multi-Task Learning (MTL) method with data augmentation for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b7ef5d35813f1c840e6b11b5c8f9c1b2
https://doi.org/10.18653/v1/2021.acl-long.119
https://doi.org/10.18653/v1/2021.acl-long.119
Autor:
Yutong Shao, Ndapa Nakashole
Publikováno v:
ACL
This paper presents the problem of conversational plotting agents that carry out plotting actions from natural language instructions. To facilitate the development of such agents, we introduce ChartDialogs, a new multi-turn dialog dataset, covering a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bb972e6e2a7f7fd915c0e07b1689cdfe
https://doi.org/10.18653/v1/2020.acl-main.328
https://doi.org/10.18653/v1/2020.acl-main.328
Publikováno v:
EMNLP (Findings)
Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent work has s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47e71af190eb99f2c00780f37d747247
http://arxiv.org/abs/1911.03875
http://arxiv.org/abs/1911.03875