Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Walter Chang"'
Autor:
Adyasha Maharana, Quan Tran, Franck Dernoncourt, Seunghyun Yoon, Trung Bui, Walter Chang, Mohit Bansal
Publikováno v:
Findings of the Association for Computational Linguistics: NAACL 2022.
Publikováno v:
EACL (System Demonstrations)
Acronyms and abbreviations are the short-form of longer phrases and they are ubiquitously employed in various types of writing. Despite their usefulness to save space in writing and reader's time in reading, they also provide challenges for understan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f68db9b133eb7d0edd6dc5c686c7d6d6
http://arxiv.org/abs/2101.09893
http://arxiv.org/abs/2101.09893
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
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
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
Publikováno v:
NAACL-HLT
Event coreference resolution is an important research problem with many applications. Despite the recent remarkable success of pretrained language models, we argue that it is still highly beneficial to utilize symbolic features for the task. However,
Autor:
Jianguo Zhang, Trung Bui, Seunghyun Yoon, Xiang Chen, Zhiwei Liu, Congying Xia, Quan Hung Tran, Walter Chang, Philip Yu
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be254083628db74faa9cf28d6f9e43f4
Autor:
Franck Dernoncourt, Varun Manjunatha, Lidan Wang, Walter Chang, Thien Huu Nguyen, Quan Hung Tran, Doo Soon Kim, Amir Pouran Ben Veyseh, Rajiv Jain
Publikováno v:
Advances in Knowledge Discovery and Data Mining ISBN: 9783030757649
PAKDD (2)
PAKDD (2)
Event Argument Extraction (EAE) is the task of identifying roles of entity mentions/arguments in events evoked by trigger words. Most existing works have focused on sentence-level EAE, leaving document-level EAE (i.e., event triggers and arguments be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3855c78c4fb23a3c6a3f6c352820e488
https://doi.org/10.1007/978-3-030-75765-6_56
https://doi.org/10.1007/978-3-030-75765-6_56
Publikováno v:
EMNLP (1)
The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts. However, to date, summarizers can fail on fusing sentences. They tend to produce few summary sentences by fusi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f3aba8eb890d8f997d43d3ba55757d7
http://arxiv.org/abs/2010.03726
http://arxiv.org/abs/2010.03726
Autor:
Walter Chang, Xuanli He, Quan Hung Tran, Gholamreza Haffari, Trung Bui, Zhe Lin, Nhan Dam, Franck Dernoncourt
Publikováno v:
EMNLP (Findings)
Structured representations like graphs and parse trees play a crucial role in many Natural Language Processing systems. In recent years, the advancements in multi-turn user interfaces necessitate the need for controlling and updating these structured
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::434ed31dda999123613e4a2176a7c0b5
http://arxiv.org/abs/2010.02591
http://arxiv.org/abs/2010.02591