Topical word embeddings
Citations
703 citations
Cites result from "Topical word embeddings"
...Similar results to ours are also reported in [14]....
[...]
276 citations
265 citations
Cites background from "Topical word embeddings"
...The problem can be addressed by training a global model with multiple vector embeddings per word (Reisinger and Mooney, 2010a; Huang et al., 2012) or topicspecific embeddings (Liu et al., 2015)....
[...]
..., 2012) or topicspecific embeddings (Liu et al., 2015)....
[...]
251 citations
Cites background from "Topical word embeddings"
...Recent approaches based on deep neural networks learn vectors by predicting words given their window-based context (Collobert and Weston, 2008; Mikolov et al., 2013; Pennington et al., 2014; Liu et al., 2015)....
[...]
... counts. Recent approaches based on deep neural networks learn vectors by predicting words given their window-based context (Collobert and Weston, 2008; Mikolov et al., 2013; Pennington et al., 2014; Liu et al., 2015). Mikolov et al. (2013)’s method maximizes the log likelihood of each word given its context. Pennington et al. (2014) used back-propagation to minimize the squared error of a prediction of the logfre...
[...]
222 citations
References
30,570 citations
"Topical word embeddings" refers methods in this paper
...We employ the widely used latent Dirichlet allocation (LDA) (Blei, Ng, and Jordan 2003) to obtain word topics, and perform collapsed Gibbs sampling (Griffiths and Steyvers 2004) to iteratively assign latent topics for each word token....
[...]
25,546 citations
24,012 citations
"Topical word embeddings" refers methods in this paper
...The training objective of CBOW is to combine the embeddings of context words to predict the target word; while Skip-Gram is to use the embedding of each target word to predict its context words (Mikolov et al. 2013)....
[...]
...We extend Skip-Gram (Mikolov et al. 2013), the stateof-the-art word embedding model, to implement our TWE models....
[...]
...In previous work, the task of word similarity is always used to evaluate the performance of word embedding methods (Mikolov et al. 2013; Baroni, Dinu, and Kruszewski 2014)....
[...]
...In order to make the model efficient for learning, the techniques of hierarchical softmax and negative sampling are used when learning Skip-Gram (Mikolov et al. 2013)....
[...]
...Skip-Gram is a well-known framework for learning word vectors (Mikolov et al. 2013), as shown in Fig....
[...]
23,814 citations
"Topical word embeddings" refers methods in this paper
...Word embeddings, first proposed in (Rumelhart, Hintont, and Williams 1986), have been successfully used in language models (Bengio et al. 2006; Mnih and Hinton 2008) and many NLP tasks, such as named entity recognition (Turian, Ratinov, and Bengio 2010), disambiguation (Collobert et al. 2011) and…...
[...]
15,068 citations
"Topical word embeddings" refers background in this paper
...• There are many knowledge bases available, such as WordNet (Miller 1995), containing rich linguistic knowledge of homonymy and polysemy....
[...]