About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Alejandro Moreo
- sl:arxiv_num : 1911.11506
- sl:arxiv_published : 2019-11-26T13:11:00Z
- sl:arxiv_summary : Pre-trained word embeddings encode general word semantics and lexical
regularities of natural language, and have proven useful across many NLP tasks,
including word sense disambiguation, machine translation, and sentiment
analysis, to name a few. In supervised tasks such as multiclass text
classification (the focus of this article) it seems appealing to enhance word
representations with ad-hoc embeddings that encode task-specific information.
We propose (supervised) word-class embeddings (WCEs), and show that, when
concatenated to (unsupervised) pre-trained word embeddings, they substantially
facilitate the training of deep-learning models in multiclass classification by
topic. We show empirical evidence that WCEs yield a consistent improvement in
multiclass classification accuracy, using four popular neural architectures and
six widely used and publicly available datasets for multiclass text
classification. Our code that implements WCEs is publicly available at
https://github.com/AlexMoreo/word-class-embeddings@en
- sl:arxiv_title : Word-Class Embeddings for Multiclass Text Classification@en
- sl:arxiv_updated : 2019-11-26T13:11:00Z
- sl:bookmarkOf : https://arxiv.org/abs/1911.11506
- sl:creationDate : 2020-10-11
- sl:creationTime : 2020-10-11T19:29:28Z
- sl:relatedDoc : http://www.semanlink.net/doc/2020/02/joint_embedding_of_words_and_la
Documents with similar tags (experimental)