Mitigating Noisy Inputs for Question Answering
Natural language processing systems are often downstream of unreliable inputs: machine translation, optical character recognition, or speech recognition. For instance, virtual assistants can only answer your questions after understanding your speech. We investigate and mitigate the effects of noise from Automatic Speech Recognition systems on two factoid Question Answering (QA) tasks. Integrating confidences into the model and forced decoding of unknown words are empirically shown to improve the accuracy of downstream neural QA systems. We create and train models on a synthetic corpus of over 500,000 noisy sentences and evaluate on two human corpora from Quizbowl and Jeopardy! competitions.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine TranslationOptical Character RecognitionOptical Character Recognition (OCR)Question Answeringspeech-recognitionSpeech RecognitionTranslationSimilar Papers 제목 키워드 기반
Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs
The rise of personal assistants has made conversational question answering (ConvQA) a very popular mechanism for user-system interaction. State-of-the-art methods for ConvQA over knowledge graphs (KGs) can only learn fro…
Conversational Question AnsweringKnowledge GraphsQuestion Answeringreinforcement-learning+1Mitigating Knowledge Conflicts in Language Model-Driven Question Answering
In the context of knowledge-driven seq-to-seq generation tasks, such as document-based question answering and document summarization systems, two fundamental knowledge sources play crucial roles: the inherent knowledge e…
Document SummarizationHallucinationLanguage ModelingLanguage Modelling+1Mitigating Easy Option Bias in Multiple-Choice Question Answering
In this early study, we observe an Easy-Options Bias (EOB) issue in some multiple-choice Visual Question Answering (VQA) benchmarks such as MMStar, RealWorldQA, SEED-Bench, Next-QA, STAR benchmark and Video-MME. This bia…
Visual Question AnsweringRoToR: Towards More Reliable Responses for Order-Invariant Inputs
Mitigating positional bias of language models (LMs) for listwise inputs is a well-known and important problem (e.g., lost-in-the-middle). While zero-shot order-invariant LMs have been proposed to solve this issue, their …
Graph Question AnsweringMMLUQuestion AnsweringOn the hidden treasure of dialog in video question answering
High-level understanding of stories in video such as movies and TV shows from raw data is extremely challenging. Modern video question answering (VideoQA) systems often use additional human-made sources like plot synopse…
Question AnsweringVideo Question AnsweringVisual Question Answering (VQA)