Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287554229> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W4287554229 abstract "Text classification, as the task consisting in assigning categories to textual instances, is a very common task in information science. Methods learning distributed representations of words, such as word embeddings, have become popular in recent years as the features to use for text classification tasks. Despite the increasing use of word embeddings for text classification, these are generally used in an unsupervised manner, i.e. information derived from class labels in the training data are not exploited. While word embeddings inherently capture the distributional characteristics of words, and contexts observed around them in a large dataset, they aren't optimised to consider the distributions of words across categories in the classification dataset at hand. To optimise text representations based on word embeddings by incorporating class distributions in the training data, we propose the use of weighting schemes that assign a weight to embeddings of each word based on its saliency in each class. To achieve this, we introduce a novel weighting scheme, Term Frequency-Category Ratio (TF-CR), which can weight high-frequency, category-exclusive words higher when computing word embeddings. Our experiments on 16 classification datasets show the effectiveness of TF-CR, leading to improved performance scores over existing weighting schemes, with a performance gap that increases as the size of the training data grows." @default.
- W4287554229 created "2022-07-25" @default.
- W4287554229 creator A5071220716 @default.
- W4287554229 date "2020-12-11" @default.
- W4287554229 modified "2023-10-16" @default.
- W4287554229 title "TF-CR: Weighting Embeddings for Text Classification" @default.
- W4287554229 hasPublicationYear "2020" @default.
- W4287554229 type Work @default.
- W4287554229 citedByCount "0" @default.
- W4287554229 crossrefType "posted-content" @default.
- W4287554229 hasAuthorship W4287554229A5071220716 @default.
- W4287554229 hasBestOaLocation W42875542291 @default.
- W4287554229 hasConcept C126838900 @default.
- W4287554229 hasConcept C134306372 @default.
- W4287554229 hasConcept C153180895 @default.
- W4287554229 hasConcept C154945302 @default.
- W4287554229 hasConcept C162324750 @default.
- W4287554229 hasConcept C183115368 @default.
- W4287554229 hasConcept C187736073 @default.
- W4287554229 hasConcept C204321447 @default.
- W4287554229 hasConcept C2524010 @default.
- W4287554229 hasConcept C2777212361 @default.
- W4287554229 hasConcept C2780451532 @default.
- W4287554229 hasConcept C33923547 @default.
- W4287554229 hasConcept C41008148 @default.
- W4287554229 hasConcept C71924100 @default.
- W4287554229 hasConcept C77618280 @default.
- W4287554229 hasConcept C90805587 @default.
- W4287554229 hasConceptScore W4287554229C126838900 @default.
- W4287554229 hasConceptScore W4287554229C134306372 @default.
- W4287554229 hasConceptScore W4287554229C153180895 @default.
- W4287554229 hasConceptScore W4287554229C154945302 @default.
- W4287554229 hasConceptScore W4287554229C162324750 @default.
- W4287554229 hasConceptScore W4287554229C183115368 @default.
- W4287554229 hasConceptScore W4287554229C187736073 @default.
- W4287554229 hasConceptScore W4287554229C204321447 @default.
- W4287554229 hasConceptScore W4287554229C2524010 @default.
- W4287554229 hasConceptScore W4287554229C2777212361 @default.
- W4287554229 hasConceptScore W4287554229C2780451532 @default.
- W4287554229 hasConceptScore W4287554229C33923547 @default.
- W4287554229 hasConceptScore W4287554229C41008148 @default.
- W4287554229 hasConceptScore W4287554229C71924100 @default.
- W4287554229 hasConceptScore W4287554229C77618280 @default.
- W4287554229 hasConceptScore W4287554229C90805587 @default.
- W4287554229 hasLocation W42875542291 @default.
- W4287554229 hasOpenAccess W4287554229 @default.
- W4287554229 hasPrimaryLocation W42875542291 @default.
- W4287554229 hasRelatedWork W10596858 @default.
- W4287554229 hasRelatedWork W11209375 @default.
- W4287554229 hasRelatedWork W13608894 @default.
- W4287554229 hasRelatedWork W2218946 @default.
- W4287554229 hasRelatedWork W2651071 @default.
- W4287554229 hasRelatedWork W2864082 @default.
- W4287554229 hasRelatedWork W5192282 @default.
- W4287554229 hasRelatedWork W9761094 @default.
- W4287554229 hasRelatedWork W5829715 @default.
- W4287554229 hasRelatedWork W8458896 @default.
- W4287554229 isParatext "false" @default.
- W4287554229 isRetracted "false" @default.
- W4287554229 workType "article" @default.