Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Cheng, Jianpeng"'
While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also introduces uniqu
Externí odkaz:
http://arxiv.org/abs/2410.09407
Generating user intent from a sequence of user interface (UI) actions is a core challenge in comprehensive UI understanding. Recent advancements in multimodal large language models (MLLMs) have led to substantial progress in this area, but their dema
Externí odkaz:
http://arxiv.org/abs/2409.04081
Autor:
Stacey, Joe, Cheng, Jianpeng, Torr, John, Guigue, Tristan, Driesen, Joris, Coca, Alexandru, Gaynor, Mark, Johannsen, Anders
Spurred by recent advances in Large Language Models (LLMs), virtual assistants are poised to take a leap forward in terms of their dialogue capabilities. Yet a major bottleneck to achieving genuinely transformative task-oriented dialogue capabilities
Externí odkaz:
http://arxiv.org/abs/2403.00462
Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt learning. Previous works use raw dialogue context as search keys and qu
Externí odkaz:
http://arxiv.org/abs/2402.13043
Autor:
Aas, Cecilia, Abdelsalam, Hisham, Belousova, Irina, Bhargava, Shruti, Cheng, Jianpeng, Daland, Robert, Driesen, Joris, Flego, Federico, Guigue, Tristan, Johannsen, Anders, Lal, Partha, Lu, Jiarui, Moniz, Joel Ruben Antony, Perkins, Nathan, Piraviperumal, Dhivya, Pulman, Stephen, Séaghdha, Diarmuid Ó, Sun, David Q., Torr, John, Del Vecchio, Marco, Wacker, Jay, Williams, Jason D., Yu, Hong
It has recently become feasible to run personal digital assistants on phones and other personal devices. In this paper we describe a design for a natural language understanding system that runs on device. In comparison to a server-based assistant, th
Externí odkaz:
http://arxiv.org/abs/2308.03905
Autor:
Cheng, Jianpeng, Xiong, Deping, Jiang, Wenqin, Ye, Wenbin, Song, Peng, Feng, Zuyong, He, Miao
Publikováno v:
In Chemical Physics Letters 16 January 2024 835
Autor:
Cheng, Jianpeng, Agrawal, Devang, Alonso, Hector Martinez, Bhargava, Shruti, Driesen, Joris, Flego, Federico, Ghosh, Shaona, Kaplan, Dain, Kartsaklis, Dimitri, Li, Lin, Piraviperumal, Dhivya, Williams, Jason D, Yu, Hong, Seaghdha, Diarmuid O, Johannsen, Anders
We consider a new perspective on dialog state tracking (DST), the task of estimating a user's goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic compositio
Externí odkaz:
http://arxiv.org/abs/2010.12770
Natural language understanding (NLU) and natural language generation (NLG) are two fundamental and related tasks in building task-oriented dialogue systems with opposite objectives: NLU tackles the transformation from natural language to formal repre
Externí odkaz:
http://arxiv.org/abs/2006.07499
Semantic parsing is the task of converting natural language utterances into machine interpretable meaning representations which can be executed against a real-world environment such as a database. Scaling semantic parsing to arbitrary domains faces t
Externí odkaz:
http://arxiv.org/abs/1812.10037
Dependency grammar induction is the task of learning dependency syntax without annotated training data. Traditional graph-based models with global inference achieve state-of-the-art results on this task but they require $O(n^3)$ run time. Transition-
Externí odkaz:
http://arxiv.org/abs/1811.05889