Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136258522> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3136258522 abstract "Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously downgrade the performance of the NLP modules. Therefore, it is essential to make them robust to the ASR errors. Previous work has shown it is effective to employ data augmentation methods to solve this problem by injecting ASR noise during the training process. In this paper, we utilize the prevalent pre-trained language model to generate training samples with ASR-plausible noise. Compare to the previous methods, our approach generates ASR noise that better fits the real-world error distribution. Experimental results on spoken language translation(SLT) and spoken language understanding (SLU) show that our approach effectively improves the system robustness against the ASR errors and achieves state-of-the-art results on both tasks." @default.
- W3136258522 created "2021-03-29" @default.
- W3136258522 creator A5010343914 @default.
- W3136258522 creator A5038537171 @default.
- W3136258522 creator A5042898096 @default.
- W3136258522 creator A5066887020 @default.
- W3136258522 creator A5086603207 @default.
- W3136258522 date "2021-03-25" @default.
- W3136258522 modified "2023-09-24" @default.
- W3136258522 title "An Approach to Improve Robustness of NLP Systems against ASR Errors" @default.
- W3136258522 cites W2101105183 @default.
- W3136258522 cites W2153579005 @default.
- W3136258522 cites W2251058040 @default.
- W3136258522 cites W2468328197 @default.
- W3136258522 cites W2762590475 @default.
- W3136258522 cites W2767899794 @default.
- W3136258522 cites W2787560479 @default.
- W3136258522 cites W2794365787 @default.
- W3136258522 cites W2897656024 @default.
- W3136258522 cites W2898989428 @default.
- W3136258522 cites W2911588830 @default.
- W3136258522 cites W2937808806 @default.
- W3136258522 cites W2938704169 @default.
- W3136258522 cites W2945700568 @default.
- W3136258522 cites W2963341956 @default.
- W3136258522 cites W2963403868 @default.
- W3136258522 cites W2963532001 @default.
- W3136258522 cites W2972584841 @default.
- W3136258522 cites W2982399380 @default.
- W3136258522 cites W2997436923 @default.
- W3136258522 cites W2999245659 @default.
- W3136258522 cites W3007759824 @default.
- W3136258522 cites W3015747801 @default.
- W3136258522 cites W3037291366 @default.
- W3136258522 cites W3043665049 @default.
- W3136258522 cites W3054645415 @default.
- W3136258522 cites W3082845185 @default.
- W3136258522 cites W3102273025 @default.
- W3136258522 cites W3113747735 @default.
- W3136258522 cites W399167303 @default.
- W3136258522 cites W2954004546 @default.
- W3136258522 doi "https://doi.org/10.48550/arxiv.2103.13610" @default.
- W3136258522 hasPublicationYear "2021" @default.
- W3136258522 type Work @default.
- W3136258522 sameAs 3136258522 @default.
- W3136258522 citedByCount "1" @default.
- W3136258522 countsByYear W31362585222021 @default.
- W3136258522 crossrefType "posted-content" @default.
- W3136258522 hasAuthorship W3136258522A5010343914 @default.
- W3136258522 hasAuthorship W3136258522A5038537171 @default.
- W3136258522 hasAuthorship W3136258522A5042898096 @default.
- W3136258522 hasAuthorship W3136258522A5066887020 @default.
- W3136258522 hasAuthorship W3136258522A5086603207 @default.
- W3136258522 hasBestOaLocation W31362585221 @default.
- W3136258522 hasConcept C104317684 @default.
- W3136258522 hasConcept C137293760 @default.
- W3136258522 hasConcept C154945302 @default.
- W3136258522 hasConcept C185592680 @default.
- W3136258522 hasConcept C203005215 @default.
- W3136258522 hasConcept C204321447 @default.
- W3136258522 hasConcept C2776230583 @default.
- W3136258522 hasConcept C28490314 @default.
- W3136258522 hasConcept C41008148 @default.
- W3136258522 hasConcept C55493867 @default.
- W3136258522 hasConcept C63479239 @default.
- W3136258522 hasConceptScore W3136258522C104317684 @default.
- W3136258522 hasConceptScore W3136258522C137293760 @default.
- W3136258522 hasConceptScore W3136258522C154945302 @default.
- W3136258522 hasConceptScore W3136258522C185592680 @default.
- W3136258522 hasConceptScore W3136258522C203005215 @default.
- W3136258522 hasConceptScore W3136258522C204321447 @default.
- W3136258522 hasConceptScore W3136258522C2776230583 @default.
- W3136258522 hasConceptScore W3136258522C28490314 @default.
- W3136258522 hasConceptScore W3136258522C41008148 @default.
- W3136258522 hasConceptScore W3136258522C55493867 @default.
- W3136258522 hasConceptScore W3136258522C63479239 @default.
- W3136258522 hasLocation W31362585221 @default.
- W3136258522 hasOpenAccess W3136258522 @default.
- W3136258522 hasPrimaryLocation W31362585221 @default.
- W3136258522 hasRelatedWork W1538473846 @default.
- W3136258522 hasRelatedWork W1569841287 @default.
- W3136258522 hasRelatedWork W1697423248 @default.
- W3136258522 hasRelatedWork W2351428524 @default.
- W3136258522 hasRelatedWork W2747680751 @default.
- W3136258522 hasRelatedWork W2753086417 @default.
- W3136258522 hasRelatedWork W2933022734 @default.
- W3136258522 hasRelatedWork W3107474891 @default.
- W3136258522 hasRelatedWork W61293283 @default.
- W3136258522 hasRelatedWork W970670907 @default.
- W3136258522 isParatext "false" @default.
- W3136258522 isRetracted "false" @default.
- W3136258522 magId "3136258522" @default.
- W3136258522 workType "article" @default.