Towards human-centered proactive conversational agents

Y Deng, L Liao, Z Zheng, GH Yang… - Proceedings of the 47th …, 2024 - dl.acm.org
Recent research on proactive conversational agents (PCAs) mainly focuses on improving
the system's capabilities in anticipating and planning action sequences to accomplish tasks …

Exploiting simulated user feedback for conversational search: Ranking, rewriting, and beyond

P Owoicho, I Sekulic, M Aliannejadi, J Dalton… - Proceedings of the 46th …, 2023 - dl.acm.org
This research aims to explore various methods for assessing user feedback in mixed-
initiative conversational search (CS) systems. While CS systems enjoy profuse …

A survey on asking clarification questions datasets in conversational systems

HA Rahmani, X Wang, Y Feng, Q Zhang… - arXiv preprint arXiv …, 2023 - arxiv.org
The ability to understand a user's underlying needs is critical for conversational systems,
especially with limited input from users in a conversation. Thus, in such a domain, Asking …

System initiative prediction for multi-turn conversational information seeking

C Meng, M Aliannejadi, M de Rijke - Proceedings of the 32nd ACM …, 2023 - dl.acm.org
Identifying the right moment for a system to take the initiative is essential to conversational
information seeking (CIS). Existing studies have extensively studied the clarification need …

Knowledge-Enhanced Conversational Recommendation via Transformer-Based Sequential Modeling

J Zou, A Sun, C Long, E Kanoulas - ACM Transactions on Information …, 2024 - dl.acm.org
In conversational recommender systems (CRSs), conversations usually involve a set of
items and item-related entities or attributes, eg, director is a related entity of a movie. These …

Online and offline evaluation in search clarification

L Tavakoli, JR Trippas, H Zamani, F Scholer… - ACM Transactions on …, 2024 - dl.acm.org
The effectiveness of clarification question models in engaging users within search systems
is currently constrained, casting doubt on their overall usefulness. To improve the …

Center-retained fine-tuning for conversational question ranking through unsupervised center identification

Z Liu, Z Chen, Z Ren, S Gao, J Ma, P Ren - Information Processing & …, 2024 - Elsevier
Given a conversation context, conversational question ranking (CQR) aims to select a
proper question from a candidate pool to clarify users' ambiguous information needs. Most …

Clarifying the Path to User Satisfaction: An Investigation into Clarification Usefulness

HA Rahmani, X Wang, M Aliannejadi… - arXiv preprint arXiv …, 2024 - arxiv.org
Clarifying questions are an integral component of modern information retrieval systems,
directly impacting user satisfaction and overall system performance. Poorly formulated …

Ask or Recommend: An Empirical Study on Conversational Product Search

H Ma, J Zou, M Aliannejadi, E Kanoulas, Y Bin… - Proceedings of the 33rd …, 2024 - dl.acm.org
Conversational Product Search (CPS) provides an engaging way for users to find products
through effective natural language conversations. However, understanding the effect of …

A new way of search query like knowledge graph and its interpretability

Y Xie, G Zeng - Knowledge and Information Systems, 2024 - Springer
In online search, it has always been a challenge to provide a way of search query that can
help users accurately express search intentions and encourage them to type easily. This …