Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211339323> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3211339323 endingPage "334" @default.
- W3211339323 startingPage "323" @default.
- W3211339323 abstract "Question Generation (QG) is an important task in Natural Language Processing (NLP) that involves generating questions automatically when given a context paragraph. While many techniques exist for the task of QG, they employ complex model architectures, extensive features, and additional mechanisms to boost model performance. In this work, we show that transformer-based finetuning techniques can be used to create robust question generation systems using only a single pretrained language model, without the use of additional mechanisms, answer metadata, and extensive features. Our best model outperforms previous more complex RNN-based Seq2Seq models, with an 8.62 and a 14.27 increase in METEOR and ROUGE_L scores, respectively. We show that it also performs on par with Seq2Seq models that employ answer-awareness and other special mechanisms, despite being only a single-model system. We analyze how various factors affect the model’s performance, such as input data formatting, the length of the context paragraphs, and the use of answer-awareness. Lastly, we also look into the model’s failure modes and identify possible reasons why the model fails." @default.
- W3211339323 created "2021-11-22" @default.
- W3211339323 creator A5017208830 @default.
- W3211339323 creator A5048793278 @default.
- W3211339323 creator A5066275070 @default.
- W3211339323 creator A5067640807 @default.
- W3211339323 date "2021-01-01" @default.
- W3211339323 modified "2023-10-18" @default.
- W3211339323 title "Simplifying Paragraph-Level Question Generation via Transformer Language Models" @default.
- W3211339323 cites W2101105183 @default.
- W3211339323 cites W2133459682 @default.
- W3211339323 cites W2606333299 @default.
- W3211339323 cites W2610891036 @default.
- W3211339323 cites W2757978590 @default.
- W3211339323 cites W2890166583 @default.
- W3211339323 cites W2962717047 @default.
- W3211339323 cites W2962977247 @default.
- W3211339323 cites W2963748441 @default.
- W3211339323 doi "https://doi.org/10.1007/978-3-030-89363-7_25" @default.
- W3211339323 hasPublicationYear "2021" @default.
- W3211339323 type Work @default.
- W3211339323 sameAs 3211339323 @default.
- W3211339323 citedByCount "8" @default.
- W3211339323 countsByYear W32113393232022 @default.
- W3211339323 countsByYear W32113393232023 @default.
- W3211339323 crossrefType "book-chapter" @default.
- W3211339323 hasAuthorship W3211339323A5017208830 @default.
- W3211339323 hasAuthorship W3211339323A5048793278 @default.
- W3211339323 hasAuthorship W3211339323A5066275070 @default.
- W3211339323 hasAuthorship W3211339323A5067640807 @default.
- W3211339323 hasBestOaLocation W32113393232 @default.
- W3211339323 hasConcept C111919701 @default.
- W3211339323 hasConcept C121332964 @default.
- W3211339323 hasConcept C136764020 @default.
- W3211339323 hasConcept C137293760 @default.
- W3211339323 hasConcept C154945302 @default.
- W3211339323 hasConcept C162324750 @default.
- W3211339323 hasConcept C165801399 @default.
- W3211339323 hasConcept C187736073 @default.
- W3211339323 hasConcept C204321447 @default.
- W3211339323 hasConcept C2777206241 @default.
- W3211339323 hasConcept C2780451532 @default.
- W3211339323 hasConcept C41008148 @default.
- W3211339323 hasConcept C62520636 @default.
- W3211339323 hasConcept C66322947 @default.
- W3211339323 hasConcept C88006597 @default.
- W3211339323 hasConcept C93518851 @default.
- W3211339323 hasConceptScore W3211339323C111919701 @default.
- W3211339323 hasConceptScore W3211339323C121332964 @default.
- W3211339323 hasConceptScore W3211339323C136764020 @default.
- W3211339323 hasConceptScore W3211339323C137293760 @default.
- W3211339323 hasConceptScore W3211339323C154945302 @default.
- W3211339323 hasConceptScore W3211339323C162324750 @default.
- W3211339323 hasConceptScore W3211339323C165801399 @default.
- W3211339323 hasConceptScore W3211339323C187736073 @default.
- W3211339323 hasConceptScore W3211339323C204321447 @default.
- W3211339323 hasConceptScore W3211339323C2777206241 @default.
- W3211339323 hasConceptScore W3211339323C2780451532 @default.
- W3211339323 hasConceptScore W3211339323C41008148 @default.
- W3211339323 hasConceptScore W3211339323C62520636 @default.
- W3211339323 hasConceptScore W3211339323C66322947 @default.
- W3211339323 hasConceptScore W3211339323C88006597 @default.
- W3211339323 hasConceptScore W3211339323C93518851 @default.
- W3211339323 hasLocation W32113393231 @default.
- W3211339323 hasLocation W32113393232 @default.
- W3211339323 hasOpenAccess W3211339323 @default.
- W3211339323 hasPrimaryLocation W32113393231 @default.
- W3211339323 hasRelatedWork W142374489 @default.
- W3211339323 hasRelatedWork W1505464911 @default.
- W3211339323 hasRelatedWork W2081647779 @default.
- W3211339323 hasRelatedWork W3022039293 @default.
- W3211339323 hasRelatedWork W3097571385 @default.
- W3211339323 hasRelatedWork W3107474891 @default.
- W3211339323 hasRelatedWork W3185852197 @default.
- W3211339323 hasRelatedWork W3196747313 @default.
- W3211339323 hasRelatedWork W4205820553 @default.
- W3211339323 hasRelatedWork W4287890639 @default.
- W3211339323 isParatext "false" @default.
- W3211339323 isRetracted "false" @default.
- W3211339323 magId "3211339323" @default.
- W3211339323 workType "book-chapter" @default.