paper-with-me

홈 › Papers

MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification

2016-03-03 · NAACL 2016 6 · Ye Zhang, Stephen Roller, Byron Wallace

We introduce a novel, simple convolution neural network (CNN) architecture - multi-group norm constraint CNN (MGNC-CNN) that capitalizes on multiple sets of word embeddings for sentence classification. MGNC-CNN extracts features from input embedding sets independently and then joins these at the penultimate layer in the network to form a final feature vector. We then adopt a group regularization strategy that differentially penalizes weights associated with the subcomponents generated from the respective embedding sets. This model is much simpler than comparable alternative architectures and requires substantially less training time. Furthermore, it is flexible in that it does not require input word embeddings to be of the same dimensionality. We show that MGNC-CNN consistently outperforms baseline models.

📄 PDF Abstract BibTeX arXiv:1603.00968

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationSentenceSentence ClassificationWord Embeddings

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Predicting Concreteness and Imageability of Words Within and Across Languages via Word Embeddings

2018-07-09 · Nikola Ljubešić, Darja Fišer, Anita Peti-Stantić

The notions of concreteness and imageability, traditionally important in psycholinguistics, are gaining significance in semantic-oriented natural language processing tasks. In this paper we investigate the predictability…

Cross-Lingual TransferWord Embeddings

Predicting Concreteness and Imageability of Words Within and Across Languages via Word Embeddings

2018-07-01 · WS 2018 7 · Nikola Ljube{\v{s}}i{\'c}, Darja Fi{\v{s}}er, Anita Peti-Stanti{\'c}

The notions of concreteness and imageability, traditionally important in psycholinguistics, are gaining significance in semantic-oriented natural language processing tasks. In this paper we investigate the predictability…

Cross-Lingual TransferRepresentation LearningWord Embeddings

Natural Alpha Embeddings

2019-12-04 · Riccardo Volpi, Luigi Malagò

Learning an embedding for a large collection of items is a popular approach to overcome the computational limitations associated to one-hot encodings. The aim of item embedding is to learn a low dimensional space for the…

Word Embeddings

Exploiting Multiple Embeddings for Chinese Named Entity Recognition

2019-08-28 · Canwen Xu, Feiyang Wang, Jialong Han, Chenliang Li

Identifying the named entities mentioned in text would enrich many semantic applications at the downstream level. However, due to the predominant usage of colloquial language in microblogs, the named entity recognition (…

Chinese Named Entity Recognitionnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1

Context encoders as a simple but powerful extension of word2vec

2017-06-08 · WS 2017 8 · Franziska Horn

With a simple architecture and the ability to learn meaningful word embeddings efficiently from texts containing billions of words, word2vec remains one of the most popular neural language models used today. However, as …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+1