2021/01/01 by Abhilash Nandy, Soumya Sharma, Nandy, Abhilash +9 · 6 citations
Computer Science · Social Sciences · #Artificial intelligence #Baseline (sea) #Benchmark (surveying) #Code (set theory) #Computation and Language (cs.CL) #Computer science #Context (archaeology) #Educational Assessment and Pedagogy #Exploit #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Information retrieval #Machine Learning (cs.LG) #Natural Language Processing Techniques #Natural language processing #Pipeline (software) #Programming language #Question answering #Set (abstract data type) #Task (project management) #Text and Document Classification Technologies #Topic Modeling #World Wide Web #cs.CL #cs.IR #cs.LG
paper · pdf · doi:10.48550/arxiv.2109.05897
published in arXiv (Cornell University), 4600-4609 (Cornell University) · EMNLP Findings 2021, Long
openalex publication_date 2021/09/13 · arxiv created 2021/09/14 · arxiv updated 2021/09/15 · openalex created_date 2022/10/05 · openalex updated_date 2026/08/06
Answering questions asked from instructional corpora such as E-manuals,\nrecipe books, etc., has been far less studied than open-domain factoid\ncontext-based question answering. This can be primarily attributed to the\nabsence of standard benchmark datasets. In this paper we meticulously create a\nlarge amount of data connected with E-manuals and develop suitable algorithm to\nexploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals and\npretrain RoBERTa on this large corpus. We create various benchmark QA datasets\nwhich include question answer pairs curated by experts based upon two\nE-manuals, real user questions from Community Question Answering Forum\npertaining to E-manuals etc. We introduce EMQAP (E-Manual Question Answering\nPipeline) that answers questions pertaining to electronics devices. Built upon\nthe pretrained RoBERTa, it harbors a supervised multi-task learning framework\nwhich efficiently performs the dual tasks of identifying the section in the\nE-manual where the answer can be found and the exact answer span within that\nsection. For E-Manual annotated question-answer pairs, we show an improvement\nof about 40% in ROUGE-L F1 scores over the most competitive baseline. We\nperform a detailed ablation study and establish the versatility of EMQAP across\ndifferent circumstances. The code and datasets are shared at\nhttps://github.com/abhi1nandy2/EMNLP-2021-Findings, and the corresponding\nproject website is https://sites.google.com/view/emanualqa/home.\n