🥁🥁🥁 iglu-contest @ NeurIPS is about to start! The focus is on building an interactive agent that can understand the instructions in natural language to build structures in the #Minecraft environment! In case of uncertainty, ask clarifying questions! Interested? #SIGIR2022 #NAACL2022

fine-tuned REL on AMT annotations of concepts and entities in conversations helpful to answer follow-up questions Hideaki Joko #sigir2022 #convsearch arxiv.org/abs/2105.04903 github.com/informagi/conv… github.com/informagi/conv…

GRILLBot winner of 2022 Alexa Prize Challenge: cooking & DIY assistant TaskGraph representation: branching for interaction & ingredient requirements LLM prompts for contextual QA & question taxonomy Carlos Gemmell #sigir2022 shorturl.at/iOU04 github.com/grill-lab/OAT

main challenges for conversational QA? Aldo Lipani * difficulties in evaluation: * lack of metrics for answer naturalness & facet discovery * need to measure user satisfaction * incorporating personalised context * leveraging non-parametric information sources

📢 3 new research-focused faculty positions Heriot-Watt University computer science. We're looking to strengthen our team in #NLProc and #ConversationalAI. DM me if interested

Chairing the mixed initiative session at SCAI. Sandeep (🙃 Sandeep Avula) from Amazon presenting The Effects of System Initiative during Conversational Collaborative Search arxiv.org/abs/2202.09728… #SIGIR2022 #scai2022

mixed-initiative interaction in collaborative conversational search wizard-of-oz study measuring dialog utility, workload, communication, perceived benefits & challenges 🙃 Sandeep Avula SCAI #sigir2022 #convsearch arxiv.org/abs/2202.09728

user studies of a system prototype that suggests objects or aspects to clarify ambiguous comparative questions alexander bondarenko SCAI #sigir2022 #convsearch webis.de/downloads/publ…

user simulator for answering clarification questions evaluation: automated NLG & document retrieval metrics, human annotations of naturalness & usefulness Ivan Sekulić SCAI #sigir2022 #convsearch arxiv.org/abs/2204.08046

🤵‍♂️I can see myself in the corner :-) Jokes aside it was a wonderful session. Thanks SCAI and SIGIR 2025 for the opportunity, my fellow presenters, session chair, and all the audience for the wonderful discussion at the end of the session. #SCAI #SIGIR2022

Valeriia Bolotova et al. got the best paper award at #SIGIR2022 for their very extensive paper titled "A Non-Factoid Question-Answering Taxonomy", which I really like because it is such a timeless topic and remains relevant dl.acm.org/doi/10.1145/34…

In the perspectives session, I enjoyed the talk by Krisztian Balog on on natural language user profiles for recommendation, especially how they used a few-shot prompt template to turn a large language model (LaMDA) into a recommender. dl.acm.org/doi/10.1145/34…

risk-aware policy trained with RL deep q-learning decides to ask a clarifying question based on a user simulator response & future results session-based evaluation metrics: recall, MRR, decision error rate Zhenduo Wang SCAI #sigir2022 #convsearch arxiv.org/pdf/2101.06327…

Aldo Lipani chairing Conversational QA session at SCAI

limitations of user simulators for conversational search? Jeff Dalton * lack of multi-turn data with natural long-term trajectories * personalisation, cultural & language variations * need for taxonomy & understanding of different system initiative actions SCAI #sigir2022

This was my first debut to the SCAI 😊 Thanks for the invitation and valuable questions and discussion!

Excited to announce that I've been promoted to Associate Professor (Senior Lecturer) at UofG Computing Science. My group, GRILL Lab has open positions for PhD/Postdocs on interactive and multimodal foundation models -- grilllab.ai #conversationalai

The topics for the fourth year of the Conversational Assistance Track (CAsT) have been released: github.com/daltonj/trecca… New this year: (1) Different topic format, (2) Mixed-Initiative system responses (3) Complex discourse structures Jeff Dalton Johanne Mohammad Aliannejadi Leif Azzopardi

Check out the first session of SCAI 2022: "Conversational Search Evaluation", where I present a way to evaluate conversational systems by user simulator that predicts users' satisfaction scores along with actions and utterances 🤖🤖 Joint work with Aldo Lipani