Abstract
Simon Lupart, Thibault Formal, Stéphane Clinchant |
45th European Conference on Information Retrieval (ECIR), Dublin, Ireland, 2–6 April, 2023 |
arXiv |
Abstract
Pre-trained Language Models have recently emerged in Information Retrieval as providing the backbone of a new generation of neural systems that outperform traditional methods on a variety of tasks.
However, it is still unclear to what extent such approaches generalize in zero-shot conditions. The recent BEIR benchmark provides partial answers to this question by comparing models on datasets and tasks that differ from the training conditions. We aim to address the same question by comparing models under more explicit distribution shifts. To this end, we build three query-based distribution shifts within MS MARCO (query-semantic, query-intent, query-length) which are used to evaluate the three main families of neural retrievers based on BERT: sparse, dense and late-interaction – as well as a mono BERT reranker. We further analyse the performance drops between the train and test query distributions. In particular, we identify two generalization indicators: the first one based on train/test query vocabulary overlap, the second based on each model retrieval score. Intuitively, those indicators verify that, the further away the test set is from the train one, the worse the drop in performance. We also show that models respond differently to the shifts – dense approaches being the most impacted. Overall, our study demonstrates that it is possible to design more controllable distribution shifts as a tool to better understand generalization of IR models. Finally, we release the MS MARCO query subsets, which provide an additional resource to benchmark zero-shot transfer in Information Retrieval.
1. Difference in female/male salary: 33/40 points
2. Difference in salary increases female/male: 35/35 points
3. Salary increases upon return from maternity leave: uncalculable
4. Number of employees in under-represented gender in 10 highest salaries: 0/10 points
NAVER France targets (with respect to the 2022 index) are as follows:
En 2022, NAVER France a obtenu les notes suivantes pour chacun des indicateurs :
1. Les écarts de salaire entre les femmes et les hommes: 33 sur 40 points
2. Les écarts des augmentations individuelles entre les femmes et les hommes : 35 sur 35 points
3. Toutes les salariées augmentées revenant de congé maternité : non calculable
4. Le nombre de salarié du sexe sous-représenté parmi les 10 plus hautes rémunérations : 0 sur 10 points
Les objectifs de progression pour l’index 2022 de NAVER France sont :
NAVER LABS Europe 6-8 chemin de Maupertuis 38240 Meylan France Contact
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
FunctionalThis website uses functional cookies which are required for the search function to work and to apply for jobs and internships.
AnalyticalOur website uses analytical cookies to make it possible to analyse our website and optimize its usability.
Social mediaOur website places social media cookies to show YouTube and Vimeo videos. Cookies placed by these sites may track your personal data.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.