Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284680079> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4284680079 abstract "In this paper, we study the semi-supervised text classification (SSTC) by exploring both labeled and extra unlabeled data. One of the most popular SSTC techniques is pseudo-labeling which assigns pseudo labels for unlabeled data via a teacher classifier trained on labeled data. These pseudo labeled data is then applied to train a student classifier. However, when the pseudo labels are inaccurate, the student classifier will learn from inaccurate data and get even worse performance than the teacher. To mitigate this issue, we propose a simple yet efficient pseudo-labeling framework called Dual Pseudo Supervision (DPS), which exploits the feedback signal from the student to guide the teacher to generate better pseudo labels. In particular, we alternately update the student based on the pseudo labeled data annotated by the teacher and optimize the teacher based on the student's performance via meta learning. In addition, we also design a consistency regularization term to further improve the stability of the teacher. With the above two strategies, the learned reliable teacher can provide more accurate pseudo-labels to the student and thus improve the overall performance of text classification. We conduct extensive experiments on three benchmark datasets (i.e., AG News, Yelp and Yahoo) to verify the effectiveness of our DPS method. Experimental results show that our approach achieves substantially better performance than the strong competitors. For reproducibility, we will release our code and data of this paper publicly at https://github.com/GRIT621/DPS." @default.
- W4284680079 created "2022-07-08" @default.
- W4284680079 creator A5018149714 @default.
- W4284680079 creator A5048416659 @default.
- W4284680079 creator A5059967200 @default.
- W4284680079 creator A5062974958 @default.
- W4284680079 date "2022-07-06" @default.
- W4284680079 modified "2023-10-18" @default.
- W4284680079 title "Dual Pseudo Supervision for Semi-Supervised Text Classification with a Reliable Teacher" @default.
- W4284680079 cites W1994484359 @default.
- W4284680079 cites W2102029756 @default.
- W4284680079 cites W2591922431 @default.
- W4284680079 cites W2970189355 @default.
- W4284680079 cites W3091002423 @default.
- W4284680079 cites W3114034564 @default.
- W4284680079 cites W3174231090 @default.
- W4284680079 cites W4233639450 @default.
- W4284680079 doi "https://doi.org/10.1145/3477495.3531887" @default.
- W4284680079 hasPublicationYear "2022" @default.
- W4284680079 type Work @default.
- W4284680079 citedByCount "0" @default.
- W4284680079 crossrefType "proceedings-article" @default.
- W4284680079 hasAuthorship W4284680079A5018149714 @default.
- W4284680079 hasAuthorship W4284680079A5048416659 @default.
- W4284680079 hasAuthorship W4284680079A5059967200 @default.
- W4284680079 hasAuthorship W4284680079A5062974958 @default.
- W4284680079 hasBestOaLocation W42846800791 @default.
- W4284680079 hasConcept C119857082 @default.
- W4284680079 hasConcept C12267149 @default.
- W4284680079 hasConcept C124101348 @default.
- W4284680079 hasConcept C13280743 @default.
- W4284680079 hasConcept C154945302 @default.
- W4284680079 hasConcept C165696696 @default.
- W4284680079 hasConcept C185798385 @default.
- W4284680079 hasConcept C205649164 @default.
- W4284680079 hasConcept C2776135515 @default.
- W4284680079 hasConcept C2776145971 @default.
- W4284680079 hasConcept C38652104 @default.
- W4284680079 hasConcept C41008148 @default.
- W4284680079 hasConcept C66905080 @default.
- W4284680079 hasConcept C95623464 @default.
- W4284680079 hasConceptScore W4284680079C119857082 @default.
- W4284680079 hasConceptScore W4284680079C12267149 @default.
- W4284680079 hasConceptScore W4284680079C124101348 @default.
- W4284680079 hasConceptScore W4284680079C13280743 @default.
- W4284680079 hasConceptScore W4284680079C154945302 @default.
- W4284680079 hasConceptScore W4284680079C165696696 @default.
- W4284680079 hasConceptScore W4284680079C185798385 @default.
- W4284680079 hasConceptScore W4284680079C205649164 @default.
- W4284680079 hasConceptScore W4284680079C2776135515 @default.
- W4284680079 hasConceptScore W4284680079C2776145971 @default.
- W4284680079 hasConceptScore W4284680079C38652104 @default.
- W4284680079 hasConceptScore W4284680079C41008148 @default.
- W4284680079 hasConceptScore W4284680079C66905080 @default.
- W4284680079 hasConceptScore W4284680079C95623464 @default.
- W4284680079 hasFunder F4320321001 @default.
- W4284680079 hasLocation W42846800791 @default.
- W4284680079 hasOpenAccess W4284680079 @default.
- W4284680079 hasPrimaryLocation W42846800791 @default.
- W4284680079 hasRelatedWork W2044507188 @default.
- W4284680079 hasRelatedWork W2116666691 @default.
- W4284680079 hasRelatedWork W2623427976 @default.
- W4284680079 hasRelatedWork W2961085424 @default.
- W4284680079 hasRelatedWork W3004138706 @default.
- W4284680079 hasRelatedWork W3033833039 @default.
- W4284680079 hasRelatedWork W3200179079 @default.
- W4284680079 hasRelatedWork W4249229055 @default.
- W4284680079 hasRelatedWork W4308671172 @default.
- W4284680079 hasRelatedWork W4379255972 @default.
- W4284680079 isParatext "false" @default.
- W4284680079 isRetracted "false" @default.
- W4284680079 workType "article" @default.