Joint Learning of Character and Word Embeddings

By Xinxiong Chen, Lei Xu, Zhiyuan Liu, Maosong Sun, Huanbo Luan. 2015

295 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Sequence-Level Knowledge Distillation (2016, background): “…of weight matrices (Denton et al., 2014; Jaderberg et al., 2014; Lu et al., 2016; Prabhavalkar et al., 2016), sparsity-inducing regularizers (Murray and Chiang, 2015), binarization of weights (Courbariaux et al., 2016; Lin et al., 2016), and weight sharing (Chen et al., 2015; Han et al., 2016).”
Learning Word Vectors for 157 Languages (2018, methodology): “r Spanish, that of Venekoski and Vankka (2017) for Finnish, that of Berardi et al. (2015) for Italian, the European variant of the dataset proposed by Hartmann et al. (2017) for Portugueseand that of Chen et al. (2015) for Chinese. One of the contributions of this work is the introductionof word ana”
Enriching Word Vectors with Subword Information (2016, methodology): “Similarly, Chen et al. (2015) introduced a method to jointly learn embeddings for Chinese words and characters.”
Recent Trends in Deep Learning Based Natural Language Processing (2017, methodology): “To overcome this loss of information for multiple-event modeling, (Chen et al., 2015b) proposed a modified pooling strategy: dynamic multi-pooling CNN (DMCNN).”
Character-based Neural Machine Translation (2016, background): “…been explored in Natural Language Processing (NLP), e.g. for POS tagging (Santos and Zadrozny, 2014), name entity recognition (Santos and aes, 2015), parsing (Ballesteros et al., 2015), normalization (Chrupala, 2014) or learning word representations (Botha and Blunsom, 2014; Chen et al., 2015).”
Charagram: Embedding Words and Sentences via Character n-grams (2016, background): “Others learned embeddings jointly for subword units and words, deﬁning simple compositional architectures (often based on addition) to create word embeddings from subword embeddings (Lazaridou et al., 2013; Botha and Blunsom, 2014; Qiu et al., 2014; Chen et al., 2015).”
Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs (2015, background): “Similarly, Chen et al. (2015) proposed joint learning of character and word embeddings for Chinese, claiming that characters contain rich information.”
Analogical Reasoning on Chinese Morphological and Semantic Relations (2018, background): “The only Chinese analogy dataset is translated from part of an English dataset (Chen et al., 2015) (denote as CA_translated).”
A Review of Sentiment Analysis Research in Chinese Language (2017, unknown): “[59] started to decompose Chinese words into characters and proposed a character-enhanced word embedding”
Recent Trends in Deep Learning Based Natural Language Processing [Review Article] (2018, background): “In languages where text is not composed of separated words but individual characters and the semantic meaning of words map to its compositional characters (such as Chinese), building systems at the character level is a natural choice to avoid word segmentation [33].”
Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings (2015, background): “While work has explored different embeddings for Chinese (Liu et al., 2014; Sun et al., 2014; Qiu et al., 2014; Chen et al., 2015), their inclusion in downstream tasks, such as NER, remains untested.”
Radical-Based Hierarchical Embeddings for Chinese Sentiment Analysis at Sentence Level (2017, background): “Chinese Radical Embedding (Chen et al. 2015) started to decompose Chinese words into characters and proposed a character-enhanced word embedding model (CWE).”
A clinical text classification paradigm using weak supervision and deep representation (2019, background): “In addition, other deep representation methods, such as character embeddings [72], are also subject to a future study.”