Conversational agents: Goals, technologies, vision and challenges

M Allouch, A Azaria, R Azoulay - Sensors, 2021 - mdpi.com
In recent years, conversational agents (CAs) have become ubiquitous and are a presence in
our daily routines. It seems that the technology has finally ripened to advance the use of CAs …

Recent advances and challenges in task-oriented dialog systems

Z Zhang, R Takanobu, Q Zhu, ML Huang… - Science China …, 2020 - Springer
Due to the significance and value in human-computer interaction and natural language
processing, task-oriented dialog systems are attracting more and more attention in both …

Soloist: Building Task Bots at Scale with Transfer Learning and Machine Teaching

B Peng, C Li, J Li, S Shayandeh, L Liden… - Transactions of the …, 2021 - direct.mit.edu
We present a new method, Soloist, that uses transfer learning and machine teaching to build
task bots at scale. We parameterize classical modular task-oriented dialog systems using a …

Archer: Training language model agents via hierarchical multi-turn rl

Y Zhou, A Zanette, J Pan, S Levine, A Kumar - ar** the hallucination of large language model chatbots by few-shot grounding on Wikipedia
SJ Semnani, VZ Yao, HC Zhang, MS Lam - arxiv preprint arxiv …, 2023 - arxiv.org
This paper presents the first few-shot LLM-based chatbot that almost never hallucinates and
has high conversationality and low latency. WikiChat is grounded on the English Wikipedia …

[PDF][PDF] Soloist: Few-shot task-oriented dialog with a single pretrained auto-regressive model

B Peng, C Li, J Li, S Shayandeh… - arxiv preprint arxiv …, 2020 - researchgate.net
This paper presents a new method SOLOIST 1, which uses transfer learning to efficiently
build task-oriented dialog systems at scale. We parameterize a dialog system using a …

Crosswoz: A large-scale chinese cross-domain task-oriented dialogue dataset

Q Zhu, K Huang, Z Zhang, X Zhu… - Transactions of the …, 2020 - direct.mit.edu
To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the
shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale …

User simulation for evaluating information access systems

K Balog, CX Zhai - Proceedings of the Annual International ACM SIGIR …, 2023 - dl.acm.org
With the emergence of various information access systems exhibiting increasing complexity,
there is a critical need for sound and scalable means of automatic evaluation. To address …

[KÖNYV][B] Neural approaches to conversational information retrieval

J Gao, C **ong, P Bennett, N Craswell - 2023 - Springer
A conversational information retrieval (CIR) system is an information retrieval (IR) system
with a conversational interface, which allows users to interact with the system to seek …

GPT-critic: Offline reinforcement learning for end-to-end task-oriented dialogue systems

Y Jang, J Lee, KE Kim - International conference on learning …, 2022 - openreview.net
Training a task-oriented dialogue agent can be naturally formulated as offline reinforcement
learning (RL) problem, where the agent aims to learn a conversational strategy to achieve …