Zobrazeno 1 - 10
of 267
pro vyhledávání: '"Finch, James A."'
The challenge of defining a slot schema to represent the state of a task-oriented dialogue system is addressed by Slot Schema Induction (SSI), which aims to automatically induce slots from unlabeled dialogue data. Whereas previous approaches induce s
Externí odkaz:
http://arxiv.org/abs/2408.01638
Autor:
Finch, James D., Choi, Jinho D.
We demonstrate substantial performance gains in zero-shot dialogue state tracking (DST) by enhancing training data diversity through synthetic data generation. Existing DST datasets are severely limited in the number of application domains and slot t
Externí odkaz:
http://arxiv.org/abs/2405.12468
Human evaluation has been widely accepted as the standard for evaluating chat-oriented dialogue systems. However, there is a significant variation in previous work regarding who gets recruited as evaluators. Evaluator groups such as domain experts, u
Externí odkaz:
http://arxiv.org/abs/2309.07998
Despite tremendous advancements in dialogue systems, stable evaluation still requires human judgments producing notoriously high-variance metrics due to their inherent subjectivity. Moreover, methods and labels in dialogue evaluation are not fully st
Externí odkaz:
http://arxiv.org/abs/2212.09180
Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to automated
Externí odkaz:
http://arxiv.org/abs/2111.00572
Autor:
Finch, Sarah E., Finch, James D., Huryn, Daniil, Hutsell, William, Huang, Xiaoyuan, He, Han, Choi, Jinho D.
We present a chatbot implementing a novel dialogue management approach based on logical inference. Instead of framing conversation a sequence of response generation tasks, we model conversation as a collaborative inference process in which speakers s
Externí odkaz:
http://arxiv.org/abs/2111.00570
Autor:
Mason, Brandon1 (AUTHOR) brandon.mason@maritimearchaeology.co.uk, Finch, James2 (AUTHOR) james.finch@nikon.com, Paynter, Sarah3 (AUTHOR) sarah.paynter@historicengland.org.uk, Anderson, Heather1 (AUTHOR) lauren.nagler@maritimearchaeology.co.uk, Nagler, Lauren1 (AUTHOR)
Publikováno v:
Heritage (2571-9408). May2024, Vol. 7 Issue 5, p2552-2568. 17p.
Autor:
Finch, Sarah E., Finch, James D., Ahmadvand, Ali, Ingyu, Choi, Dong, Xiangjue, Qi, Ruixiang, Sahijwani, Harshita, Volokhin, Sergey, Wang, Zihan, Wang, Zihao, Choi, Jinho D.
Inspired by studies on the overwhelming presence of experience-sharing in human-human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conversational AI.
Externí odkaz:
http://arxiv.org/abs/2009.04617
Autor:
Finch, James D., Choi, Jinho D.
This demo paper presents Emora STDM (State Transition Dialogue Manager), a dialogue system development framework that provides novel workflows for rapid prototyping of chat-based dialogue managers as well as collaborative development of complex inter
Externí odkaz:
http://arxiv.org/abs/2006.06143