Zobrazeno 1 - 10
of 169
pro vyhledávání: '"Furu Wei"'
Autor:
Jian Yang, Yuwei Yin, Shuming Ma, Liqun Yang, Hongcheng Guo, Haoyang Huang, Dongdong Zhang, Yutao Zeng, Zhoujun Li, Furu Wei
Publikováno v:
Database Systems for Advanced Applications ISBN: 9783031306747
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::286c0b820531b1966299249740f8e02b
https://doi.org/10.1007/978-3-031-30675-4_34
https://doi.org/10.1007/978-3-031-30675-4_34
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 26:1685-1691
Tweets have become an increasingly popular source of fresh information. We investigate the task of Nominal Semantic Role Labeling (NSRL) for tweets, which aims to identify predicate-argument structures defined by nominals in tweets. Studies of this t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2370e506fc149a8c08669d010f731cce
https://doi.org/10.1609/aaai.v26i1.8349
https://doi.org/10.1609/aaai.v26i1.8349
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 26:1692-1698
Social events are events that occur between people where at least one person is aware of the other and of the event taking place. Extracting social events can play an important role in a wide range of applications, such as the construction of social
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5ff041aaa0caad9a180816629fa2424
https://doi.org/10.1609/aaai.v26i1.8350
https://doi.org/10.1609/aaai.v26i1.8350
Autor:
Jian Yang, Yuwei Yin, Liqun Yang, Shuming Ma, Haoyang Huang, Dongdong Zhang, Furu Wei, Zhoujun Li
Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation. However, vanilla Transformer mainly exploits the top-layer representation, assuming the lower layers p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b3715b6251d4eb5ed0aae9e26bf10f73
http://arxiv.org/abs/2207.14467
http://arxiv.org/abs/2207.14467
Publikováno v:
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence.
Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless, multilingual tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2282de614a51dc5b69bb90c7cebea76
https://doi.org/10.24963/ijcai.2022/619
https://doi.org/10.24963/ijcai.2022/619
Autor:
Jian Yang, Yuwei Yin, Shuming Ma, Dongdong Zhang, Shuangzhi Wu, Hongcheng Guo, Zhoujun Li, Furu Wei
Publikováno v:
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence.
Most translation tasks among languages belong to the zero-resource translation problem where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) enables one-pass translation using shared semantic space for all languages c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2d7f9b108804f966d2f0c3589e87f75
https://doi.org/10.24963/ijcai.2022/618
https://doi.org/10.24963/ijcai.2022/618
Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to interpret. We pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::192c40cae2ab823b0cc9f6b8c73edce5
http://arxiv.org/abs/2206.10125
http://arxiv.org/abs/2206.10125
The Mixture-of-Experts (MoE) technique can scale up the model size of Transformers with an affordable computational overhead. We point out that existing learning-to-route MoE methods suffer from the routing fluctuation issue, i.e., the target expert
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5e940afb43c8d209c15f04d6383ca3bd
http://arxiv.org/abs/2204.08396
http://arxiv.org/abs/2204.08396
Publikováno v:
AAAI
Sentence Split and Rephrase aims to break down a complex sentence into several simple sentences with its meaning preserved. Previous studies tend to address the issue by seq2seq learning from parallel sentence pairs, which takes a complex sentence as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8aabc959ec99cef8afd459f4787f0e89
https://doi.org/10.1609/aaai.v34i05.6291
https://doi.org/10.1609/aaai.v34i05.6291
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28:671-681
Extractive document summarization methods aim to extract important sentences to form a summary. Previous works perform this task by first scoring all sentences in the document then selecting most informative ones; while we propose to jointly learn th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c3cbe3040a26601afe613b23b23dd93
https://doi.org/10.1109/taslp.2020.2964427
https://doi.org/10.1109/taslp.2020.2964427