In a conversational context, a user converses with a system through a sequence of natural-language questions, i.e., utterances. Starting from a given subject, the conversation evolves through sequences of user utterances and system replies. The retrieval of documents relevant to an utterance is difficult due to informal use of natural language in speech and the complexity of understanding the semantic context coming from previous utterances. We adopt the 2019 TREC Conversational Assistant Track (CAST) framework to experiment with a modular architecture performing in order: (i) automatic utterance understanding and rewriting, (ii) first-stage retrieval of candidate passages for the rewritten utterances, and (iii) neural re-ranking of candidate passages. By understanding the conversational context, we propose adaptive utterance rewriting strategies based on the current utterance and the dialogue evolution of the user with the system. A classifier identifies those utterances lacking context information as well as the dependencies on the previous utterances. Experimentally, we evaluate the proposed architecture in terms of traditional information retrieval metrics at small cutoffs. Results demonstrate the effectiveness of our techniques, achieving an improvement up to 0.6512 (+201%) for P@1 and 0.4484 (+214%) for nDCG@3 w.r.t. the CAST baseline.

Adaptive utterance rewriting for conversational search

Nardini F. M.;Perego R.;Tonellotto N.;
2021-01-01

Abstract

In a conversational context, a user converses with a system through a sequence of natural-language questions, i.e., utterances. Starting from a given subject, the conversation evolves through sequences of user utterances and system replies. The retrieval of documents relevant to an utterance is difficult due to informal use of natural language in speech and the complexity of understanding the semantic context coming from previous utterances. We adopt the 2019 TREC Conversational Assistant Track (CAST) framework to experiment with a modular architecture performing in order: (i) automatic utterance understanding and rewriting, (ii) first-stage retrieval of candidate passages for the rewritten utterances, and (iii) neural re-ranking of candidate passages. By understanding the conversational context, we propose adaptive utterance rewriting strategies based on the current utterance and the dialogue evolution of the user with the system. A classifier identifies those utterances lacking context information as well as the dependencies on the previous utterances. Experimentally, we evaluate the proposed architecture in terms of traditional information retrieval metrics at small cutoffs. Results demonstrate the effectiveness of our techniques, achieving an improvement up to 0.6512 (+201%) for P@1 and 0.4484 (+214%) for nDCG@3 w.r.t. the CAST baseline.
2021
Mele, I.; Muntean, C. I.; Nardini, F. M.; Perego, R.; Tonellotto, N.; Frieder, O.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/1114318
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 17
  • ???jsp.display-item.citation.isi??? 11
social impact