Efficient retrieval augmented generation from unstructured knowledge for task-oriented dialog

D Thulke, N Daheim, C Dugast, H Ney - arxiv preprint arxiv:2102.04643, 2021 - arxiv.org
This paper summarizes our work on the first track of the ninth Dialog System Technology
Challenge (DSTC 9)," Beyond Domain APIs: Task-oriented Conversational Modeling with …

[HTML][HTML] Knowledge-grounded task-oriented dialogue modeling on spoken conversations track at DSTC10

S Kim, Y Liu, D **, A Papangelis, B Hedayatnia… - 2022 - amazon.science
A lot of recent work in dialogue modeling has been on written conversations, partly because
of available data sets. However, written dialogues are not sufficient to fully capture the …

Learning to retrieve entity-aware knowledge and generate responses with copy mechanism for task-oriented dialogue systems

CH Tan, X Yang, Z Zheng, T Li, Y Feng, JC Gu… - arxiv preprint arxiv …, 2020 - arxiv.org
Task-oriented conversational modeling with unstructured knowledge access, as track 1 of
the 9th Dialogue System Technology Challenges (DSTC 9), requests to build a system to …

A hybrid task-oriented dialog system with domain and task adaptive pretraining

B Zhang, Y Lyu, N Ding, T Shen, Z Jia, K Han… - arxiv preprint arxiv …, 2021 - arxiv.org
This paper describes our submission for the End-to-end Multi-domain Task Completion
Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9). Participants …

[PDF][PDF] Multi-domain task completion dialog challenge ii at dstc9

J Li, Q Zhu, L Luo, L Liden, K Huang… - Proc. 35th AAAI Conf …, 2021 - microsoft.com
The paper provides an overview of the “Multi-Domain Task-Completion Dialog Challenge II”
track at the 9th Dialog System Technology Challenge (DSTC9). Two tasks are introduced in …

A response retrieval approach for dialogue using a multi-attentive transformer

MA Senese, A Benincasa, B Caputo… - arxiv preprint arxiv …, 2020 - arxiv.org
This paper presents our work for the ninth edition of the Dialogue System Technology
Challenge (DSTC9). Our solution addresses the track number four: Simulated Interactive …

An empirical study of cross-lingual transferability in generative dialogue state tracker

YT Lin, YN Chen - arxiv preprint arxiv:2101.11360, 2021 - arxiv.org
There has been a rapid development in data-driven task-oriented dialogue systems with the
benefit of large-scale datasets. However, the progress of dialogue systems in low-resource …

Evaluating Chatbots to Promote Users' Trust--Practices and Open Problems

B Srivastava, K Lakkaraju, T Koppel… - arxiv preprint arxiv …, 2023 - arxiv.org
Chatbots, the common moniker for collaborative assistants, are Artificial Intelligence (AI)
software that enables people to naturally interact with them to get tasks done. Although …

A unified pre-training framework for conversational AI

S Bao, B Chen, H He, X Tian, H Zhou, F Wang… - arxiv preprint arxiv …, 2021 - arxiv.org
In this work, we explore the application of PLATO-2 on various dialogue systems, including
open-domain conversation, knowledge grounded dialogue, and task-oriented conversation …

Wechat AI & ICT's submission for DSTC9 interactive dialogue evaluation track

Z Li, Z Li, J Zhang, Y Feng, J Zhou - arxiv preprint arxiv:2101.07947, 2021 - arxiv.org
We participate in the DSTC9 Interactive Dialogue Evaluation Track (Gunasekara et al. 2020)
sub-task 1 (Knowledge Grounded Dialogue) and sub-task 2 (Interactive Dialogue). In sub …