Pruning the Index Contents for Memory Efficient Open-Domain QA

Autor:	Fajcik, Martin, Docekal, Martin, Ondrej, Karel, Smrz, Pavel
Rok vydání:	2021
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	This work presents a novel pipeline that demonstrates what is achievable with a combined effort of state-of-the-art approaches. Specifically, it proposes the novel R2-D2 (Rank twice, reaD twice) pipeline composed of retriever, passage reranker, extractive reader, generative reader and a simple way to combine them. Furthermore, previous work often comes with a massive index of external documents that scales in the order of tens of GiB. This work presents a simple approach for pruning the contents of a massive index such that the open-domain QA system altogether with index, OS, and library components fits into 6GiB docker image while retaining only 8% of original index contents and losing only 3% EM accuracy. Comment: v2 - added connection between pruner and DPR, results on TriviaQA, new reranker, results with HN-DPR checkpoint and additional analyses
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2102.10697 Zobrazit plný text záznamu View this record from Arxiv