POSSCORE: A Simple Yet Effective Evaluation of Conversational Search with Part of Speech Labelling

TL;DR

POSSCORE is an innovative automatic evaluation metric for conversational search that incorporates part of speech information to better align with human preferences, outperforming existing metrics.

Contribution

This work introduces the first systematic use of POS labels in conversational search evaluation, demonstrating improved correlation with human judgments.

Findings

POSSCORE correlates better with human preferences than baseline metrics.

Incorporating POS information enhances evaluation accuracy.

Experimental results show significant performance improvements.

Abstract

Conversational search systems, such as Google Assistant and Microsoft Cortana, provide a new search paradigm where users are allowed, via natural language dialogues, to communicate with search systems. Evaluating such systems is very challenging since search results are presented in the format of natural language sentences. Given the unlimited number of possible responses, collecting relevance assessments for all the possible responses is infeasible. In this paper, we propose POSSCORE, a simple yet effective automatic evaluation method for conversational search. The proposed embedding-based metric takes the influence of part of speech (POS) of the terms in the response into account. To the best knowledge, our work is the first to systematically demonstrate the importance of incorporating syntactic information, such as POS labels, for conversational search evaluation. Experimental results demonstrate that our metrics can correlate with human preference, achieving significant improvements over state-of-the-art baseline metrics.