Caching Historical Embeddings in Conversational Search

11/25/2022
by   Ophir Frieder, et al.
0

Rapid response, namely low latency, is fundamental in search applications; it is particularly so in interactive search sessions, such as those encountered in conversational settings. An observation with a potential to reduce latency asserts that conversational queries exhibit a temporal locality in the lists of documents retrieved. Motivated by this observation, we propose and evaluate a client-side document embedding cache, improving the responsiveness of conversational search systems. By leveraging state-of-the-art dense retrieval models to abstract document and query semantics, we cache the embeddings of documents retrieved for a topic introduced in the conversation, as they are likely relevant to successive queries. Our document embedding cache implements an efficient metric index, answering nearest-neighbor similarity queries by estimating the approximate result sets returned. We demonstrate the efficiency achieved using our cache via reproducible experiments based on TREC CAsT datasets, achieving a hit rate of up to 75 Our achieved high cache hit rates significantly improve the responsiveness of conversational systems while likewise reducing the number of queries managed on the search back-end.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/09/2020

Topical Result Caching in Web Search Engines

Caching search results is employed in information retrieval systems to e...
research
05/10/2021

Few-Shot Conversational Dense Retrieval

Dense retrieval (DR) has the potential to resolve the query understandin...
research
05/25/2023

ConvGQR: Generative Query Reformulation for Conversational Search

In conversational search, the user's real search intent for the current ...
research
06/13/2020

Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search

Asking clarifying questions in response to ambiguous or faceted queries ...
research
07/14/2017

Cross-genre Document Retrieval: Matching between Conversational and Formal Writings

This paper challenges a cross-genre document retrieval task, where the q...
research
07/23/2018

A Cache-based Optimizer for Querying Enhanced Knowledge Bases

With recent emerging technologies such as the Internet of Things (IoT), ...
research
10/22/2019

Exploiting Data Skew for Improved Query Performance

Analytic queries enable sophisticated large-scale data analysis within m...

Please sign up or login with your details

Forgot password? Click here to reset