VCWE: Visual Character-Enhanced Word Embeddings
Chinese is a logographic writing system, and the shape of Chinese characters contain rich syntactic and semantic information. In this paper, we propose a model to learn Chinese word embeddings via three-level composition: (1) a convolutional neural network to extract the intra-character compositionality from the visual shape of a character; (2) a recurrent neural network with self-attention to compose character representation into word embeddings; (3) the Skip-Gram framework to capture non-compositionality directly from the contextual information. Evaluations demonstrate the superior performance of our model on four tasks: word similarity, sentiment analysis, named entity recognition and part-of-speech tagging.
Code (1)
Tasks
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Part-Of-Speech TaggingSentiment AnalysisWord EmbeddingsWord SimilaritySimilar Papers 제목 키워드 기반
Implicit Discourse Relation Recognition with Context-aware Character-enhanced Embeddings
For the task of implicit discourse relation recognition, traditional models utilizing manual features can suffer from data sparsity problem. Neural models provide a solution with distributed representations, which could …
Machine TranslationQuestion AnsweringRelationSentiment AnalysisComponent-Enhanced Chinese Character Embeddings
Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English. In this work, we innovatively develop two component…
General Classificationtext-classificationText ClassificationWord Embeddings+1Visualizing Linguistic Shift
Neural network based models are a very powerful tool for creating word embeddings, the objective of these models is to group similar words together. These embeddings have been used as features to improve results in vario…
Document ClassificationLanguage ModelingLanguage Modellingnamed-entity-recognition+4Learning Chinese Word Representations From Glyphs Of Characters
In this paper, we propose new methods to learn Chinese word representations. Chinese characters are composed of graphical components, which carry rich semantics. It is common for a Chinese learner to comprehend the meani…
Learning Character-level Compositionality with Visual Features
Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on…
text-classificationText Classification