%0 Conference Proceedings %1 nandy2021question %A Nandy, Abhilash %A Sharma, Soumya %A Maddhashiya, Shubham %A Sachdeva, Kapil %A Goyal, Pawan %A Ganguly, NIloy %C Association for Computational Linguistics %D 2021 %K leibnizailab myown %P 4600-4609 %T Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework %U https://aclanthology.org/2021.findings-emnlp.392 %X Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering. This can be primarily attributed to the absence of standard benchmark datasets. In this paper, we meticulously create a large amount of data connected with E-manuals and develop a suitable algorithm to exploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals, and pretrain RoBERTa on this large corpus. We create various benchmark QA datasets which include question answer pairs curated by experts based upon two E-manuals, real user questions from Community Question Answering Forum pertaining to E-manuals etc. We introduce EMQAP (E-Manual Question Answering Pipeline) that answers questions pertaining to electronics devices. Built upon the pretrained RoBERTa, it harbors a supervised multi-task learning framework which efficiently performs the dual tasks of identifying the section in the E-manual where the answer can be found and the exact answer span within that section. For E-Manual annotated question-answer pairs, we show an improvement of about 40% in ROUGE-L F1 scores over most competitive baseline. We perform a detailed ablation study and establish the versatility of EMQAP across different circumstances. The code and datasets are shared at https://github.com/abhi1nandy2/EMNLP-2021-Findings, and the corresponding project website is https://sites.google.com/view/emanualqa/home.

@proceedings{nandy2021question, abstract = {Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering. This can be primarily attributed to the absence of standard benchmark datasets. In this paper, we meticulously create a large amount of data connected with E-manuals and develop a suitable algorithm to exploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals, and pretrain RoBERTa on this large corpus. We create various benchmark QA datasets which include question answer pairs curated by experts based upon two E-manuals, real user questions from Community Question Answering Forum pertaining to E-manuals etc. We introduce EMQAP (E-Manual Question Answering Pipeline) that answers questions pertaining to electronics devices. Built upon the pretrained RoBERTa, it harbors a supervised multi-task learning framework which efficiently performs the dual tasks of identifying the section in the E-manual where the answer can be found and the exact answer span within that section. For E-Manual annotated question-answer pairs, we show an improvement of about 40% in ROUGE-L F1 scores over most competitive baseline. We perform a detailed ablation study and establish the versatility of EMQAP across different circumstances. The code and datasets are shared at https://github.com/abhi1nandy2/EMNLP-2021-Findings, and the corresponding project website is https://sites.google.com/view/emanualqa/home. }, added-at = {2022-02-24T21:35:29.000+0100}, address = {Association for Computational Linguistics}, author = {Nandy, Abhilash and Sharma, Soumya and Maddhashiya, Shubham and Sachdeva, Kapil and Goyal, Pawan and Ganguly, NIloy}, biburl = {https://www.bibsonomy.org/bibtex/23909bcff215b44297b847506f329afd3/niloy}, howpublished = {Punta Cana, Dominican Republic}, interhash = {4b901eea0be294db78d677a3a87125cd}, intrahash = {3909bcff215b44297b847506f329afd3}, keywords = {leibnizailab myown}, pages = {4600-4609}, timestamp = {2022-02-25T09:02:24.000+0100}, title = {Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework}, url = {https://aclanthology.org/2021.findings-emnlp.392}, year = 2021 }