TY - JOUR

T1 - Extractive Explanations for Interpretable Text Ranking

AU - Leonhardt, Jurek

AU - Rudra, Koustav

AU - Anand, Avishek

N1 - Funding Information: This work is supported by the European Union – Horizon 2020 Program under the scheme “INFRAIA-01-2018-2019 – Integrating Activities for Advanced Communities”, Grant Agreement n.871042, “SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics” ( http://www.sobigdata.eu ). Furthermore, this work is supported in part by the Science and Engineering Research Board, Department of Science and Technology, Government of India, under Project SRG/2022/001548. Koustav Rudra is a recipient of the DST-INSPIRE Faculty Fellowship [DST/INSPIRE/04/2021/003055] in the year 2021 under Engineering Sciences.

PY - 2023/3/23

Y1 - 2023/3/23

N2 - Neural document ranking models perform impressively well due to superior language understanding gained from pre-Training tasks. However, due to their complexity and large number of parameters these (typically transformer-based) models are often non-interpretable in that ranking decisions can not be clearly attributed to specific parts of the input documents.In this article, we propose ranking models that are inherently interpretable by generating explanations as a by-product of the prediction decision. We introduce the Select-And-Rank paradigm for document ranking, where we first output an explanation as a selected subset of sentences in a document. Thereafter, we solely use the explanation or selection to make the prediction, making explanations first-class citizens in the ranking process. Technically, we treat sentence selection as a latent variable trained jointly with the ranker from the final output. To that end, we propose an end-To-end training technique for Select-And-Rank models utilizing reparameterizable subset sampling using the Gumbel-max trick.We conduct extensive experiments to demonstrate that our approach is competitive to state-of-The-Art methods. Our approach is broadly applicable to numerous ranking tasks and furthers the goal of building models that are interpretable by design. Finally, we present real-world applications that benefit from our sentence selection method.

AB - Neural document ranking models perform impressively well due to superior language understanding gained from pre-Training tasks. However, due to their complexity and large number of parameters these (typically transformer-based) models are often non-interpretable in that ranking decisions can not be clearly attributed to specific parts of the input documents.In this article, we propose ranking models that are inherently interpretable by generating explanations as a by-product of the prediction decision. We introduce the Select-And-Rank paradigm for document ranking, where we first output an explanation as a selected subset of sentences in a document. Thereafter, we solely use the explanation or selection to make the prediction, making explanations first-class citizens in the ranking process. Technically, we treat sentence selection as a latent variable trained jointly with the ranker from the final output. To that end, we propose an end-To-end training technique for Select-And-Rank models utilizing reparameterizable subset sampling using the Gumbel-max trick.We conduct extensive experiments to demonstrate that our approach is competitive to state-of-The-Art methods. Our approach is broadly applicable to numerous ranking tasks and furthers the goal of building models that are interpretable by design. Finally, we present real-world applications that benefit from our sentence selection method.

KW - fact checking

KW - information retrieval

KW - interpretability

KW - Ranking

KW - sentence selection

UR - http://www.scopus.com/inward/record.url?scp=85172691686&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2106.12460

DO - 10.48550/arXiv.2106.12460

M3 - Article

AN - SCOPUS:85172691686

VL - 41

JO - ACM Transactions on Information Systems

JF - ACM Transactions on Information Systems

SN - 1046-8188

IS - 4

M1 - 88

ER -