DeepAI AI Chat
Log In Sign Up

Topic Propagation in Conversational Search

by   I. Mele, et al.
Georgetown University
University of Pisa
Consiglio Nazionale delle Ricerche

In a conversational context, a user expresses her multi-faceted information need as a sequence of natural-language questions, i.e., utterances. Starting from a given topic, the conversation evolves through user utterances and system replies. The retrieval of documents relevant to a given utterance in a conversation is challenging due to ambiguity of natural language and to the difficulty of detecting possible topic shifts and semantic relationships among utterances. We adopt the 2019 TREC Conversational Assistant Track (CAsT) framework to experiment with a modular architecture performing: (i) topic-aware utterance rewriting, (ii) retrieval of candidate passages for the rewritten utterances, and (iii) neural-based re-ranking of candidate passages. We present a comprehensive experimental evaluation of the architecture assessed in terms of traditional IR metrics at small cutoffs. Experimental results show the effectiveness of our techniques that achieve an improvement up to 0.28 (+93 for P@1 and 0.19 (+89.9


page 1

page 2

page 3

page 4


Harnessing Evolution of Multi-Turn Conversations for Effective Answer Retrieval

With the improvements in speech recognition and voice generation technol...

BERT Embeddings Can Track Context in Conversational Search

The use of conversational assistants to search for information is becomi...

Topic-based Evaluation for Conversational Bots

Dialog evaluation is a challenging problem, especially for non task-orie...

Automated Utterance Generation

Conversational AI assistants are becoming popular and question-answering...

Snowy: Recommending Utterances for Conversational Visual Analysis

Natural language interfaces (NLIs) have become a prevalent medium for co...

A Hybrid Architecture for Multi-Party Conversational Systems

Multi-party Conversational Systems are systems with natural language int...

Meeting Decision Tracker: Making Meeting Minutes with De-Contextualized Utterances

Meetings are a universal process to make decisions in business and proje...