Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Yin, Xusen"'
We investigate the integration of Large Language Models (LLMs) into query encoders to improve dense retrieval without increasing latency and cost, by circumventing the dependency on LLMs at inference time. SoftQE incorporates knowledge from LLMs by m
Externí odkaz:
http://arxiv.org/abs/2402.12663
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:
http://arxiv.org/abs/2010.09692
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:
http://arxiv.org/abs/2010.02229
Autor:
Yin, Xusen, May, Jonathan
Reinforcement learning algorithms such as Q-learning have shown great promise in training models to learn the optimal action to take for a given system state; a goal in applications with an exploratory or adversarial nature such as task-oriented dial
Externí odkaz:
http://arxiv.org/abs/2004.02986
Autor:
Yin, Xusen, May, Jonathan
We consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new instances of
Externí odkaz:
http://arxiv.org/abs/1908.04777
Autor:
Yin, Xusen, May, Jonathan
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:
http://arxiv.org/abs/1905.02265
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:
http://arxiv.org/abs/1810.04297
Publikováno v:
2015 IEEE International Conference on Big Data (Big Data); 2015, p2327-2336, 10p
Publikováno v:
2013 IEEE International Conference on Big Data; 2013, p153-160, 8p
Autor:
Yang, Dong, Zhong, Xiang, Yan, Dong, Dai, Fangqin, Yin, Xusen, Lian, Cheng, Zhu, Zhongliang, Jiang, Weihua, Wu, Gansha
Publikováno v:
2013 IEEE International Conference on Big Data; 2013, p94-101, 8p