Benchmarking Language-agnostic Intent Classification for Virtual Assistant Platforms

1 code implementation • NAACL (MIA) 2022 • Gengyu Wang, Cheng Qian, Lin Pan, Haode Qi, Ladislav Kunc, Saloni Potdar

Current virtual assistant (VA) platforms are beholden to the limited number of languages they support.

Benchmarking Classification +2

Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants

no code implementations • 16 Jan 2023 • Cheng Qian, Haode Qi, Gengyu Wang, Ladislav Kunc, Saloni Potdar

Out of Scope (OOS) detection in Conversational AI solutions enables a chatbot to handle a conversation gracefully when it is unable to make sense of the end-user query.

Chatbot

Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations

1 code implementation • NAACL 2021 • Haode Qi, Lin Pan, Atin Sood, Abhishek Shah, Ladislav Kunc, Mo Yu, Saloni Potdar

Secondly, even with large training data, the intent detection models can see a different distribution of test data when being deployed in the real world, leading to poor accuracy.

Benchmarking Goal-Oriented Dialog +1

Mostly Passive Information Delivery -- a Prototype

no code implementations • WS 2014 • Jan Vystr{\v{c}}il, Tomas Macek, David Luksch, Martin Labsk{\'y}, Ladislav Kunc, Jan Kleindienst, Tereza Ka{\v{s}}parov{\'a}

Recipes for building voice search UIs for automotive

no code implementations • WS 2014 • Martin Labsky, Ladislav Kunc, Tomas Macek, Jan Kleindienst, Jan Vystrcil

Speech Recognition