The PACINO Project
Personality and Conversational Information Seeking
Welcome to the PACINO Project
Over the past few years, an increasing amount of attention has been directed toward developing methods that enable Conversational Information Retrieval (CIR) and has brought forward the initial development of CIR systems. A CIR system is an IR system that enables the entire information access interaction to be carried out as a conversation with a search agent. Thus, a CIR system should be able to understand the user query, interact with the user to get a better understanding of the user information need, ask clarifying questions, improve the search results in the light of the clarifications provided, and extract and present search results/answers in a simple and clear way.
PACINO aims at advancing the state-of-the-art of CIR systems by incorporating passages of the retrieved information into a knowledge distillation process that will drive a mixed-initiative conversational system and predict when to ask a clarifying question, select/generate the clarifying question, and rank retrieved documents according to users’ responses to the questions. We also plan to enable long-term memory that can span across various conversational sessions by building and attending to user personal knowledge graphs. Finally, we will advance research in the evaluation of CS systems by enriching the training data using synthetic query variations and adding various imperfections.
Furthermore, PACINO will also build a CIR that, while answering the user information need, will be able to understand if the user suffers from some mental health disorder, adapt the conversation to avoid worsening it, and steer it toward topics that could help alleviate the condition.
Lastly, we are going to explore all issues related to bias and fairness in CIR in order to avoid unfair and biased treatment of sensitive topics in the conversation, in particular, but not only, towards users with personality disorders. Thus, this proposal is concerned with advancing the state of the art of CIR systems to enable the development of a Personalized CIR system that will interact with the user in a multi-turn and mixed-initiative conversation manner to enable the user to perform exploratory searches on any topic. The CS system will incorporate an understanding of various aspects of the dialogue with a user, including user's personality recognition, personality disorder identification, adaptation, and dealing with unfair and biased search results. In other words, the system will adapt the modality of interaction and dialogue to the user's behavior and personality enabling a more engaging and effective information-seeking experience.
PACINO is funded by the Swiss National Science Foundation (https://www.snf.ch/en) and is an Internation Co-Investigator Scheme project between Università della Svizzera itailana (USI) and the University of Amsterdam (UvA).
Project PI: Fabio Crestani (USI)
Project Co-PI: Evangelos Kanoulas (UvA), Mohammad Aliannejadi (UvA)
Industry partners: Mahdi Jelodari Mamaghani (Keptika)
Academic partners: Rosalba Morese (USI), Krisztian Balog (UiS)
PACINO offers 4 PhD positions to work on different aspects of personality and conversational assistance. One Phd student will be based in the Netherlands and supervised by Mohammad Aliannejadi and Evangelos Kanoulas. 2 PhD students will work with Fabio Crestani at USI in Lugano, Switzerland. One student will be jointly supervised between USI and UvA by Fabio Crestani and Mohammad Aliannejadi.
PhD1: Conversational AI
The first PhD student will work towards advancing the field of Conversational Information Retrieval (CIR) while ensuring fairness and eliminating bias in these systems. They will work on developing personalized conversational assistants that can cater to the needs of diverse users, including those with mental health concerns. The student will be based in the Netherlands, supervised by Mohammad Aliannejadi and Evangelos Kanoulas. Click here to apply for this position by June 1st.
PhD 2: Interactive AI Agents
The second PhD student will work on the study of the interaction between a user and a CIR system where they would study conversational agents from an IR and HCI perspective. PhD2 will be supervised by Fabio Crestani and will take advantage of the collaboration with Krisztian Balog of UiS in Norway.
PhD3: Psychological Conversational Agents
The third PhD student will work on the development of conversational models that facilitate the detection of personality disorders and other mild psychological disorders in CIR users. PhD3 will be supervised by Fabio Crestani, in collaboration with Dr. Morese of the Faculty of Biomedical Sciences of USI.
PhD4: Fair Conversational Agents
The fourth PhD student will explore all issues related to bias and fairness in CIR in order to avoid unfair and biased treatment of the conversational system towards users with or without personality disorders. PhD4 will be based in Lugano, Switzerland, being jointly supervised by Fabio Crestani at USI and Mohammad Aliannejadi at UvA. The student will spend 1-2 years visiting UvA.