Matches in SemOpenAlex for { <https://semopenalex.org/work/W3185300501> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3185300501 abstract "Transcripts generated by automatic speech recognition (ASR) systems for spoken documents lack structural annotations such as paragraphs, significantly reducing their readability. Automatically predicting paragraph segmentation for spoken documents may both improve readability and downstream NLP performance such as summarization and machine reading comprehension. We propose a sequence model with self-adaptive sliding window for accurate and efficient paragraph segmentation. We also propose an approach to exploit phonetic information, which significantly improves robustness of spoken document segmentation to ASR errors. Evaluations are conducted on the English Wiki-727K document segmentation benchmark, a Chinese Wikipedia-based document segmentation dataset we created, and an in-house Chinese spoken document dataset. Our proposed model outperforms the state-of-the-art (SOTA) model based on the same BERT-Base, increasing segmentation F1 on the English benchmark by 4.2 points and on Chinese datasets by 4.3-10.1 points, while reducing inference time to less than 1/6 of inference time of the current SOTA." @default.
- W3185300501 created "2021-08-02" @default.
- W3185300501 creator A5018324791 @default.
- W3185300501 creator A5035555253 @default.
- W3185300501 creator A5049242358 @default.
- W3185300501 creator A5068290128 @default.
- W3185300501 creator A5080511731 @default.
- W3185300501 date "2021-07-20" @default.
- W3185300501 modified "2023-09-24" @default.
- W3185300501 title "Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation" @default.
- W3185300501 cites W145178388 @default.
- W3185300501 cites W1626209120 @default.
- W3185300501 cites W1626945812 @default.
- W3185300501 cites W1983814883 @default.
- W3185300501 cites W2080179128 @default.
- W3185300501 cites W2100873065 @default.
- W3185300501 cites W2149367074 @default.
- W3185300501 cites W2512217112 @default.
- W3185300501 cites W2525778437 @default.
- W3185300501 cites W2807938752 @default.
- W3185300501 cites W2952997929 @default.
- W3185300501 cites W2962716111 @default.
- W3185300501 cites W2963341956 @default.
- W3185300501 cites W2964121744 @default.
- W3185300501 cites W2965373594 @default.
- W3185300501 cites W2995923603 @default.
- W3185300501 cites W2996035354 @default.
- W3185300501 cites W2997244287 @default.
- W3185300501 cites W3035027743 @default.
- W3185300501 cites W3102373121 @default.
- W3185300501 doi "https://doi.org/10.48550/arxiv.2107.09278" @default.
- W3185300501 hasPublicationYear "2021" @default.
- W3185300501 type Work @default.
- W3185300501 sameAs 3185300501 @default.
- W3185300501 citedByCount "0" @default.
- W3185300501 crossrefType "posted-content" @default.
- W3185300501 hasAuthorship W3185300501A5018324791 @default.
- W3185300501 hasAuthorship W3185300501A5035555253 @default.
- W3185300501 hasAuthorship W3185300501A5049242358 @default.
- W3185300501 hasAuthorship W3185300501A5068290128 @default.
- W3185300501 hasAuthorship W3185300501A5080511731 @default.
- W3185300501 hasBestOaLocation W31853005011 @default.
- W3185300501 hasConcept C104317684 @default.
- W3185300501 hasConcept C13280743 @default.
- W3185300501 hasConcept C154945302 @default.
- W3185300501 hasConcept C170858558 @default.
- W3185300501 hasConcept C185592680 @default.
- W3185300501 hasConcept C185798385 @default.
- W3185300501 hasConcept C199360897 @default.
- W3185300501 hasConcept C204321447 @default.
- W3185300501 hasConcept C205649164 @default.
- W3185300501 hasConcept C2776214188 @default.
- W3185300501 hasConcept C2778143727 @default.
- W3185300501 hasConcept C28490314 @default.
- W3185300501 hasConcept C41008148 @default.
- W3185300501 hasConcept C55493867 @default.
- W3185300501 hasConcept C63479239 @default.
- W3185300501 hasConcept C89600930 @default.
- W3185300501 hasConceptScore W3185300501C104317684 @default.
- W3185300501 hasConceptScore W3185300501C13280743 @default.
- W3185300501 hasConceptScore W3185300501C154945302 @default.
- W3185300501 hasConceptScore W3185300501C170858558 @default.
- W3185300501 hasConceptScore W3185300501C185592680 @default.
- W3185300501 hasConceptScore W3185300501C185798385 @default.
- W3185300501 hasConceptScore W3185300501C199360897 @default.
- W3185300501 hasConceptScore W3185300501C204321447 @default.
- W3185300501 hasConceptScore W3185300501C205649164 @default.
- W3185300501 hasConceptScore W3185300501C2776214188 @default.
- W3185300501 hasConceptScore W3185300501C2778143727 @default.
- W3185300501 hasConceptScore W3185300501C28490314 @default.
- W3185300501 hasConceptScore W3185300501C41008148 @default.
- W3185300501 hasConceptScore W3185300501C55493867 @default.
- W3185300501 hasConceptScore W3185300501C63479239 @default.
- W3185300501 hasConceptScore W3185300501C89600930 @default.
- W3185300501 hasLocation W31853005011 @default.
- W3185300501 hasOpenAccess W3185300501 @default.
- W3185300501 hasPrimaryLocation W31853005011 @default.
- W3185300501 hasRelatedWork W1704713987 @default.
- W3185300501 hasRelatedWork W2081830265 @default.
- W3185300501 hasRelatedWork W2112132269 @default.
- W3185300501 hasRelatedWork W2250352339 @default.
- W3185300501 hasRelatedWork W2747680751 @default.
- W3185300501 hasRelatedWork W2991150574 @default.
- W3185300501 hasRelatedWork W3014410397 @default.
- W3185300501 hasRelatedWork W3107474891 @default.
- W3185300501 hasRelatedWork W4280575577 @default.
- W3185300501 hasRelatedWork W4323363096 @default.
- W3185300501 isParatext "false" @default.
- W3185300501 isRetracted "false" @default.
- W3185300501 magId "3185300501" @default.
- W3185300501 workType "article" @default.