Adaptive utterance rewriting for conversational search

نویسندگان

چکیده

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

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Adaptive search area for fast motion estimation

In this paper a new method for determining the search area for motion estimation algorithm based on block matching is suggested. In the proposed method the search area is adaptively found for each block of a frame. This search area is similar to that of the full search (FS) algorithm but smaller for most blocks of a frame. Therefore, the proposed algorithm is analogous to FS in terms of reg...

متن کامل

Neural Utterance Ranking Model for Conversational Dialogue Systems

In this study, we present our neural utterance ranking (NUR) model, an utterance selection model for conversational dialogue agents. The NUR model ranks candidate utterances with respect to their suitability in relation to a given context using neural networks; in addition, a dialogue system based on the model converses with humans using highly ranked utterances. Specifically, the model process...

متن کامل

Lattice-Based Search for Spoken Utterance Retrieval

Recent work on spoken document retrieval has suggested that it is adequate to take the singlebest output of ASR, and perform text retrieval on this output. This is reasonable enough for the task of retrieving broadcast news stories, where word error rates are relatively low, and the stories are long enough to contain much redundancy. But it is patently not reasonable if one’s task is to retriev...

متن کامل

Challenges for Adaptive Conversational Agents

State-of-the-art dialogue technology has reached a level that allows its use in commercial applications, enabling users to have short conversations with the system to search for information. However, the unique requirements that arise from the combination of system knowledge representation, interaction management, and interface design have to be addressed as part of the system development proce...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Information Processing and Management

سال: 2021

ISSN: ['0306-4573', '1873-5371']

DOI: https://doi.org/10.1016/j.ipm.2021.102682