Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290858267> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4290858267 abstract "Online learning systems have multiple data repositories in the form of transcripts, books and questions. To enable ease of access, such systems organize the content according to a well defined taxonomy of hierarchical nature (subject-chapter-topic). The task of categorizing inputs to the hierarchical labels is usually cast as a flat multi-class classification problem. Such approaches ignore the semantic relatedness between the terms in the input and the tokens in the hierarchical labels. Alternate approaches also suffer from class imbalance when they only consider leaf level nodes as labels. To tackle the issues, we formulate the task as a dense retrieval problem to retrieve the appropriate hierarchical labels for each content. In this paper, we deal with categorizing questions. We model the hierarchical labels as a composition of their tokens and use an efficient cross-attention mechanism to fuse the information with the term representations of the content. We also propose an adaptive in-batch hard negative sampling approach which samples better negatives as the training progresses. We demonstrate that the proposed approach textit{TagRec++} outperforms existing state-of-the-art approaches on question datasets as measured by Recall@k. In addition, we demonstrate zero-shot capabilities of textit{TagRec++} and ability to adapt to label changes." @default.
- W4290858267 created "2022-08-12" @default.
- W4290858267 creator A5035621906 @default.
- W4290858267 creator A5047987914 @default.
- W4290858267 creator A5055049872 @default.
- W4290858267 date "2022-08-10" @default.
- W4290858267 modified "2023-09-29" @default.
- W4290858267 title "TagRec++: Hierarchical Label Aware Attention Network for Question Categorization" @default.
- W4290858267 doi "https://doi.org/10.48550/arxiv.2208.05152" @default.
- W4290858267 hasPublicationYear "2022" @default.
- W4290858267 type Work @default.
- W4290858267 citedByCount "0" @default.
- W4290858267 crossrefType "posted-content" @default.
- W4290858267 hasAuthorship W4290858267A5035621906 @default.
- W4290858267 hasAuthorship W4290858267A5047987914 @default.
- W4290858267 hasAuthorship W4290858267A5055049872 @default.
- W4290858267 hasBestOaLocation W42908582671 @default.
- W4290858267 hasConcept C119857082 @default.
- W4290858267 hasConcept C154945302 @default.
- W4290858267 hasConcept C162324750 @default.
- W4290858267 hasConcept C187736073 @default.
- W4290858267 hasConcept C23123220 @default.
- W4290858267 hasConcept C2776482837 @default.
- W4290858267 hasConcept C2777212361 @default.
- W4290858267 hasConcept C2780451532 @default.
- W4290858267 hasConcept C2986744138 @default.
- W4290858267 hasConcept C41008148 @default.
- W4290858267 hasConcept C94124525 @default.
- W4290858267 hasConceptScore W4290858267C119857082 @default.
- W4290858267 hasConceptScore W4290858267C154945302 @default.
- W4290858267 hasConceptScore W4290858267C162324750 @default.
- W4290858267 hasConceptScore W4290858267C187736073 @default.
- W4290858267 hasConceptScore W4290858267C23123220 @default.
- W4290858267 hasConceptScore W4290858267C2776482837 @default.
- W4290858267 hasConceptScore W4290858267C2777212361 @default.
- W4290858267 hasConceptScore W4290858267C2780451532 @default.
- W4290858267 hasConceptScore W4290858267C2986744138 @default.
- W4290858267 hasConceptScore W4290858267C41008148 @default.
- W4290858267 hasConceptScore W4290858267C94124525 @default.
- W4290858267 hasLocation W42908582671 @default.
- W4290858267 hasOpenAccess W4290858267 @default.
- W4290858267 hasPrimaryLocation W42908582671 @default.
- W4290858267 hasRelatedWork W1503883403 @default.
- W4290858267 hasRelatedWork W1536026156 @default.
- W4290858267 hasRelatedWork W1607839343 @default.
- W4290858267 hasRelatedWork W2025376455 @default.
- W4290858267 hasRelatedWork W2123701797 @default.
- W4290858267 hasRelatedWork W2275477659 @default.
- W4290858267 hasRelatedWork W2383115631 @default.
- W4290858267 hasRelatedWork W2887561352 @default.
- W4290858267 hasRelatedWork W3214103303 @default.
- W4290858267 hasRelatedWork W3111945964 @default.
- W4290858267 isParatext "false" @default.
- W4290858267 isRetracted "false" @default.
- W4290858267 workType "article" @default.