Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Xusen Yin"'
Publikováno v:
Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021).
Users frequently ask simple factoid questions for question answering (QA) systems, attenuating the impact of myriad recent works that support more complex questions. Prompting users with automatically generated suggested questions (SQs) can improve u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f6f90bdcf45f2ec835e74937fb100ae
https://doi.org/10.18653/v1/2021.dialdoc-1.11
https://doi.org/10.18653/v1/2021.dialdoc-1.11
Publikováno v:
EMNLP (Findings)
We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well when applied
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::970db81d1f2b06f522d38b791b4b9dbf
https://doi.org/10.18653/v1/2020.findings-emnlp.273
https://doi.org/10.18653/v1/2020.findings-emnlp.273
Autor:
Xusen Yin, Jonathan May
Publikováno v:
CoG
In order to train a computer agent to play a text-based computer game, we must represent each hidden state of the game. A Long Short-Term Memory (LSTM) model running over observed texts is a common choice for state construction. However, a normal Dee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c2937a17747e8fbac6d74e914c05fcf
https://doi.org/10.1109/cig.2019.8847954
https://doi.org/10.1109/cig.2019.8847954
Publikováno v:
ICDAR
European libraries and archives are filled with enciphered manuscripts from the early modern period. These include military and diplomatic correspondence, records of secret societies, private letters, and so on. Although they are enciphered with clas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd642fc0e07b9da8506ec157e6e08fa5
http://arxiv.org/abs/1810.04297
http://arxiv.org/abs/1810.04297
Publikováno v:
Journal of Computer Science and Technology. 30:30-41
Big data processing is becoming a standout part of data center computation. However, latest research has indicated that big data workloads cannot make full use of modern memory systems. We find that the dramatic inefficiency of the big data processin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6022160b31f68599f78bb3a5b2492223
https://doi.org/10.1007/s11390-015-1502-9
https://doi.org/10.1007/s11390-015-1502-9
Autor:
Joshua A. Rusow, Xusen Yin, Rens Hoegen, Wei Lan, Anton Leuski, Ron Artstein, Jacqueline Brixey, Karan Singla
Publikováno v:
SIGDIAL Conference
We present the implementation of an autonomous chatbot, SHIHbot, deployed on Facebook, which answers a wide variety of sexual health questions on HIV/AIDS. The chatbot’s response database is com-piled from professional medical and public health res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f84be6f3ad8eaa8695fe2c9a3a135d7
https://doi.org/10.18653/v1/w17-5544
https://doi.org/10.18653/v1/w17-5544
Publikováno v:
IEEE BigData
Matrix computation is the core of many massive data-intensive analytical applications such mining social networks, recommendation systems and nature language processing. Due to the importance of matrix computation, it has been widely studied for many
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e1cdc81b6c4ec2c119316924e5ae692a
https://doi.org/10.1109/bigdata.2015.7364023
https://doi.org/10.1109/bigdata.2015.7364023
Publikováno v:
BigData Conference
Node attributes and their associated links are two crucial components of user profiling in social networks. Recently, several research works show that both attributes and links are partially predictable by various classification methods. However, mos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bad1baff7384eafcf2295fc35926d917
https://doi.org/10.1109/bigdata.2013.6691748
https://doi.org/10.1109/bigdata.2013.6691748
Autor:
Dong Yan, Dong Yang, Xusen Yin, Weihua Jiang, Gan-Sha Wu, Fangqin Dai, Cheng Lian, Xiang Zhong, Zhongliang Zhu
Publikováno v:
BigData Conference
Although Hadoop MapReduce provides good programming abstractions and horizontal scalability, it is often blamed for its poor single node performance. In the meantime, MapReduce has already achieved a large install base, thus any performance improveme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8e31e5d37c45089588d5711b36eb583d
https://doi.org/10.1109/bigdata.2013.6691703
https://doi.org/10.1109/bigdata.2013.6691703