← smac.pub home

Expansion via Prediction of Importance with Contextualization

pdf arxiv bibtex code slides doi: 10.1145/3397271.3401262 dblp: conf/sigir/MacAvaneyN0TGF20 short conference paper

Authors: Sean MacAvaney, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto, Nazli Goharian, Ophir Frieder

Appeared in: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020)

Abstract:

The identification of relevance with little textual context is a primary challenge in passage retrieval. We address this problem with a representation-based ranking approach that: (1) explicitly models the importance of each term using a contextualized language model; (2) performs passage expansion by propagating the importance to similar terms; and (3) grounds the representations in the lexicon, making them interpretable. Passage representations can be pre-computed at index time to reduce query-time latency. We call our approach EPIC (Expansion via Prediction of Importance with Contextualization). We show that EPIC significantly outperforms prior importance-modeling and document expansion approaches. We also observe that the performance is additive with the current leading first-stage retrieval methods, further narrowing the gap between inexpensive and cost-prohibitive passage ranking approaches. Specifically, EPIC achieves a [email protected] of 0.304 on the MS-MARCO passage ranking dataset with 78ms average query latency on commodity hardware. We also find that the latency is further reduced to 68ms by pruning document representations, with virtually no difference in effectiveness.

BibTeX @inproceedings{macavaney:sigir2020-epic, author = {MacAvaney, Sean and Nardini, Franco Maria and Perego, Raffaele and Tonellotto, Nicola and Goharian, Nazli and Frieder, Ophir}, title = {Expansion via Prediction of Importance with Contextualization}, booktitle = {Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval}, year = {2020}, url = {https://arxiv.org/abs/2004.14245}, doi = {10.1145/3397271.3401262}, pages = {1573--1576} }