Arısoy, EbruÖzgür, ArzucanÜnlü Menevşe, MerveManav, Yusufcan2024-06-212024-06-2120249782493814104https://hdl.handle.net/20.500.11779/2303Aequa-Tech; Baidu; Bloomberg; Dataforce (Transperfect); et al.; Intesa San Paolo BankThis paper focuses on dealing with data scarcity in spoken question answering (QA) using automatic question-answer generation and a carefully selected fine-tuning strategy that leverages limited annotated data (paragraphs and question-answer pairs). Spoken QA is a challenging task due to using spoken documents, i.e., erroneous automatic speech recognition (ASR) transcriptions, and the scarcity of spoken QA data. We propose a framework for utilizing limited annotated data effectively to improve spoken QA performance. To deal with data scarcity, we train a question-answer generation model with annotated data and then produce large amounts of question-answer pairs from unannotated data (paragraphs). Our experiments demonstrate that incorporating limited annotated data and the automatically generated data through a carefully selected fine-tuning strategy leads to 5.5% relative F1 gain over the model trained only with annotated data. Moreover, the proposed framework is also effective in high ASR errors. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.eninfo:eu-repo/semantics/openAccessSpoken question answeringQuestion generationConference Object2-s2.0-851959471530