Matches in SemOpenAlex for { <https://semopenalex.org/work/W3166162885> ?p ?o ?g. }
Showing items 1 to 52 of
52
with 100 items per page.
- W3166162885 abstract "Topic relevance is an important criterion for English writing assessment. It has always been hard work for teachers to evaluate the writing assignments from students. The development of deep learning and natural language processing can help by checking the semantic relevance of article title and content. CNN and RNN have shown good performance in semantic text similarity. However, they usually require large corpora and huge computational power for training. In the case of English writing topic relevance checking, it is hard to collect an exhaustive corpus due to the topic variety. BERT has established an outstanding performance in different natural language processing tasks based on transfer learning. ERNIE set a new level for natural language tasks, since it uses entity information based on BERT. Siamese-ERNIE is a modification of the pretrained ERNIE network that uses siamese network structures to derive semantically meaningful sentence embeddings. We use Siamese-ERNIE to train (fine-tuned) the title and content semantic relevance on our corpus based on a pretrained-model. As the article title and content embedding can be calculated by our Siamese-ERNIE model, we can then measure the topic relevance by computing the semantic cosine distance of its embedding." @default.
- W3166162885 created "2021-06-22" @default.
- W3166162885 creator A5000848460 @default.
- W3166162885 creator A5013418144 @default.
- W3166162885 date "2021-05-25" @default.
- W3166162885 modified "2023-09-24" @default.
- W3166162885 title "Siamese-ERNIE: Topic Relevance Check for English Writing" @default.
- W3166162885 cites W2064675550 @default.
- W3166162885 cites W2117130368 @default.
- W3166162885 cites W2753516388 @default.
- W3166162885 cites W2962739339 @default.
- W3166162885 doi "https://doi.org/10.1145/3456887.3457448" @default.
- W3166162885 hasPublicationYear "2021" @default.
- W3166162885 type Work @default.
- W3166162885 sameAs 3166162885 @default.
- W3166162885 citedByCount "0" @default.
- W3166162885 crossrefType "proceedings-article" @default.
- W3166162885 hasAuthorship W3166162885A5000848460 @default.
- W3166162885 hasAuthorship W3166162885A5013418144 @default.
- W3166162885 hasConcept C121684516 @default.
- W3166162885 hasConcept C127413603 @default.
- W3166162885 hasConcept C158154518 @default.
- W3166162885 hasConcept C17744445 @default.
- W3166162885 hasConcept C199360897 @default.
- W3166162885 hasConcept C199539241 @default.
- W3166162885 hasConcept C199639397 @default.
- W3166162885 hasConcept C41008148 @default.
- W3166162885 hasConceptScore W3166162885C121684516 @default.
- W3166162885 hasConceptScore W3166162885C127413603 @default.
- W3166162885 hasConceptScore W3166162885C158154518 @default.
- W3166162885 hasConceptScore W3166162885C17744445 @default.
- W3166162885 hasConceptScore W3166162885C199360897 @default.
- W3166162885 hasConceptScore W3166162885C199539241 @default.
- W3166162885 hasConceptScore W3166162885C199639397 @default.
- W3166162885 hasConceptScore W3166162885C41008148 @default.
- W3166162885 hasLocation W31661628851 @default.
- W3166162885 hasOpenAccess W3166162885 @default.
- W3166162885 hasPrimaryLocation W31661628851 @default.
- W3166162885 hasRelatedWork W1527862632 @default.
- W3166162885 hasRelatedWork W2109507516 @default.
- W3166162885 hasRelatedWork W2112962394 @default.
- W3166162885 hasRelatedWork W2118300983 @default.
- W3166162885 hasRelatedWork W2135396778 @default.
- W3166162885 hasRelatedWork W2740990710 @default.
- W3166162885 hasRelatedWork W2990623652 @default.
- W3166162885 hasRelatedWork W3137189469 @default.
- W3166162885 hasRelatedWork W4235530921 @default.
- W3166162885 hasRelatedWork W4243252198 @default.
- W3166162885 isParatext "false" @default.
- W3166162885 isRetracted "false" @default.
- W3166162885 magId "3166162885" @default.
- W3166162885 workType "article" @default.