Open-Domain Conversational Search Assistant with Transformers

Guest editorial: special issue on ECIR 2021

“…Rafael Ferreira and colleagues from Universidade NOVA de Lisboa wrote Opendomain Conversational Search Assistants: The Transformer is All You Need, a paper that describes a full end-to-end conversational search system that returns summaries as answers for each turn in the conversation. The paper extends the ECIR 2021 paper (Ferreira et al, 2021) among other things by a new user-study that confirms the need for the conversational search paradigm, and an evaluation of the performance of answer generation. Interestingly, the paper comes with an on-line chat bot called Wiki Wizard.…”

The Wizard of Curiosities: Enriching Dialogues with Fun Facts

“…In system A, the user can accept, deny or ignore the curiosity recommendation. (Ferreira et al, 2021). At the end of a conversation, the user is prompted to give a 1 to 5 rating regarding the quality of the conversation.…”

Zero-shot Query Contextualization for Conversational Search

“…Therefore, most conversational retrieval approaches so far introduce a query rewriting step, which essentially decomposes the conversational search problem into a query resolution problem and an ad-hoc retrieval problem. Regarding query resolution, the majority of methods perform an explicit query re-write attempting to place the user's question in the context of the conversation, by either expanding queries with terms from recent history [27], or rewriting the full question using a sequenceto-sequence model [12,16,18,25,30]. Yu et al [31] learns to better encode the user's question in a latent space so that the learnt embeddings are close to human rewritten questions, while Lin et al [17] uses human rewritten questions to generate large-scale pseudorelevance labels and bring the user's question embeddings closer to the pseudo-relevant passage embeddings.…”