Search: id:"swepub:oai:DiVA.org:umu-220260" >
ADCluster: Adaptive...
ADCluster: Adaptive Deep Clustering for unsupervised learning from unlabeled documents
-
- Hatefi, Arezoo, 1990- (author)
- Umeå universitet,Institutionen för datavetenskap
-
- Vu, Xuan-Son, 1988- (author)
- Umeå universitet,Institutionen för datavetenskap
-
- Bhuyan, Monowar H. (author)
- Umeå universitet,Institutionen för datavetenskap
-
show more...
-
- Drewes, Frank (author)
- Umeå universitet,Institutionen för datavetenskap
-
show less...
-
(creator_code:org_t)
- Association for Computational Linguistics, 2023
- 2023
- English.
-
In: Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023). - : Association for Computational Linguistics. ; , s. 68-77
- Related links:
-
https://aclanthology...
-
show more...
-
https://umu.diva-por... (primary) (Raw object)
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- We introduce ADCluster, a deep document clustering approach based on language models that is trained to adapt to the clustering task. This adaptability is achieved through an iterative process where K-Means clustering is applied to the dataset, followed by iteratively training a deep classifier with generated pseudo-labels – an approach referred to as inner adaptation. The model is also able to adapt to changes in the data as new documents are added to the document collection. The latter type of adaptation, outer adaptation, is obtained by resuming the inner adaptation when a new chunk of documents has arrived. We explore two outer adaptation strategies, namely accumulative adaptation (training is resumed on the accumulated set of all documents) and non-accumulative adaptation (training is resumed using only the new chunk of data). We show that ADCluster outperforms established document clustering techniques on medium and long-text documents by a large margin. Additionally, our approach outperforms well-established baseline methods under both the accumulative and non-accumulative outer adaptation scenarios.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Keyword
- deep clustering
- adaptive
- deep learning
- unsupervised
- data stream
- Computer Science
- datalogi
- computational linguistics
- datorlingvistik
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database