Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202009528> ?p ?o ?g. }
- W3202009528 endingPage "330" @default.
- W3202009528 startingPage "318" @default.
- W3202009528 abstract "Discovering the logical sequence of events is one of the cornerstones in Natural Language Understanding. One approach to learn the sequence of events is to study the order of sentences in a coherent text. Sentence ordering can be applied in various tasks such as retrieval-based Question Answering, document summarization, storytelling, text generation, and dialogue systems. Furthermore, we can learn to model text coherence by learning how to order a set of shuffled sentences. Previous research has relied on RNN, LSTM, and BiLSTM architecture for learning text language models. However, these networks have performed poorly due to the lack of attention mechanisms. We propose an algorithm for sentence ordering in a corpus of short stories. Our proposed method uses a language model based on Universal Transformers (UT) that captures sentences’ dependencies by employing an attention mechanism. Our method improves the previous state-of-the-art in terms of Perfect Match Ratio (PMR) score in the ROCStories dataset, a corpus of nearly 100K short human-made stories. The proposed model includes three components: Sentence Encoder, Language Model, and Sentence Arrangement with Brute Force Search. The first component generates sentence embeddings using SBERT-WK pre-trained model fine-tuned on the ROCStories data. Then a Universal Transformer network generates a sentence-level language model. For decoding, the network generates a candidate sentence as the following sentence of the current sentence. We use cosine similarity as a scoring function to assign scores to the candidate embedding and the embeddings of other sentences in the shuffled set. Then a Brute Force Search is employed to maximize the sum of similarities between pairs of consecutive sentences." @default.
- W3202009528 created "2021-10-11" @default.
- W3202009528 creator A5004180303 @default.
- W3202009528 creator A5018217143 @default.
- W3202009528 creator A5043519248 @default.
- W3202009528 creator A5070213271 @default.
- W3202009528 creator A5071430429 @default.
- W3202009528 date "2021-01-01" @default.
- W3202009528 modified "2023-09-30" @default.
- W3202009528 title "Using BERT Encoding and Sentence-Level Language Model for Sentence Ordering" @default.
- W3202009528 cites W2003123121 @default.
- W3202009528 cites W2014945137 @default.
- W3202009528 cites W2064675550 @default.
- W3202009528 cites W2106225808 @default.
- W3202009528 cites W2108325777 @default.
- W3202009528 cites W2110568314 @default.
- W3202009528 cites W2125814131 @default.
- W3202009528 cites W2131774270 @default.
- W3202009528 cites W2140676672 @default.
- W3202009528 cites W2158794898 @default.
- W3202009528 cites W2169546346 @default.
- W3202009528 cites W2185726469 @default.
- W3202009528 cites W2413794162 @default.
- W3202009528 cites W2466175319 @default.
- W3202009528 cites W2511178802 @default.
- W3202009528 cites W2692059227 @default.
- W3202009528 cites W2776762669 @default.
- W3202009528 cites W2797585226 @default.
- W3202009528 cites W2891177506 @default.
- W3202009528 cites W2921276740 @default.
- W3202009528 cites W2962784628 @default.
- W3202009528 cites W2963341956 @default.
- W3202009528 cites W2963482033 @default.
- W3202009528 cites W2963498218 @default.
- W3202009528 cites W2964173634 @default.
- W3202009528 cites W2996876695 @default.
- W3202009528 cites W3042631625 @default.
- W3202009528 cites W3132773134 @default.
- W3202009528 doi "https://doi.org/10.1007/978-3-030-83527-9_27" @default.
- W3202009528 hasPublicationYear "2021" @default.
- W3202009528 type Work @default.
- W3202009528 sameAs 3202009528 @default.
- W3202009528 citedByCount "3" @default.
- W3202009528 countsByYear W32020095282022 @default.
- W3202009528 countsByYear W32020095282023 @default.
- W3202009528 crossrefType "book-chapter" @default.
- W3202009528 hasAuthorship W3202009528A5004180303 @default.
- W3202009528 hasAuthorship W3202009528A5018217143 @default.
- W3202009528 hasAuthorship W3202009528A5043519248 @default.
- W3202009528 hasAuthorship W3202009528A5070213271 @default.
- W3202009528 hasAuthorship W3202009528A5071430429 @default.
- W3202009528 hasBestOaLocation W32020095282 @default.
- W3202009528 hasConcept C111919701 @default.
- W3202009528 hasConcept C118505674 @default.
- W3202009528 hasConcept C121332964 @default.
- W3202009528 hasConcept C137293760 @default.
- W3202009528 hasConcept C147168706 @default.
- W3202009528 hasConcept C154945302 @default.
- W3202009528 hasConcept C165801399 @default.
- W3202009528 hasConcept C170858558 @default.
- W3202009528 hasConcept C195324797 @default.
- W3202009528 hasConcept C204321447 @default.
- W3202009528 hasConcept C2777530160 @default.
- W3202009528 hasConcept C2779439875 @default.
- W3202009528 hasConcept C28490314 @default.
- W3202009528 hasConcept C41008148 @default.
- W3202009528 hasConcept C44291984 @default.
- W3202009528 hasConcept C50644808 @default.
- W3202009528 hasConcept C62520636 @default.
- W3202009528 hasConcept C66322947 @default.
- W3202009528 hasConceptScore W3202009528C111919701 @default.
- W3202009528 hasConceptScore W3202009528C118505674 @default.
- W3202009528 hasConceptScore W3202009528C121332964 @default.
- W3202009528 hasConceptScore W3202009528C137293760 @default.
- W3202009528 hasConceptScore W3202009528C147168706 @default.
- W3202009528 hasConceptScore W3202009528C154945302 @default.
- W3202009528 hasConceptScore W3202009528C165801399 @default.
- W3202009528 hasConceptScore W3202009528C170858558 @default.
- W3202009528 hasConceptScore W3202009528C195324797 @default.
- W3202009528 hasConceptScore W3202009528C204321447 @default.
- W3202009528 hasConceptScore W3202009528C2777530160 @default.
- W3202009528 hasConceptScore W3202009528C2779439875 @default.
- W3202009528 hasConceptScore W3202009528C28490314 @default.
- W3202009528 hasConceptScore W3202009528C41008148 @default.
- W3202009528 hasConceptScore W3202009528C44291984 @default.
- W3202009528 hasConceptScore W3202009528C50644808 @default.
- W3202009528 hasConceptScore W3202009528C62520636 @default.
- W3202009528 hasConceptScore W3202009528C66322947 @default.
- W3202009528 hasLocation W32020095281 @default.
- W3202009528 hasLocation W32020095282 @default.
- W3202009528 hasOpenAccess W3202009528 @default.
- W3202009528 hasPrimaryLocation W32020095281 @default.
- W3202009528 hasRelatedWork W20999564 @default.
- W3202009528 hasRelatedWork W2411652523 @default.
- W3202009528 hasRelatedWork W3119558324 @default.
- W3202009528 hasRelatedWork W3120196704 @default.
- W3202009528 hasRelatedWork W3128902667 @default.
- W3202009528 hasRelatedWork W3207693618 @default.