RC-NET: A General Framework for Incorporating Knowledge into Word Representations

By Chang Xu, Yalong Bai, Jiang Bian, Bin Gao, G. Wang, Xiaoguang Liu, Tie-Yan Liu. 2014

205 citations recorded by the source corpus.

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, background): “ial KGs, such as Google Knowledge Graph3 and Microsoft Satori4. These knowledge graphs are successfully applied in many applications such as KG completion [14], question answering [7], word embedding [40], and text classification [34]. Inspired by the success of applying KG in a wide variety of task”
DKN: Deep Knowledge-Aware Network for News Recommendation (2018, background): “wledge.html arXiv:1801.08284v2 [stat.ML] 30 Jan 2018 Microsoft Satori6. These knowledge graphs are successfully applied in scenarios of machine reading[51], text classification[46], and word embedding[49]. Considering the above challenges in news recommendation and inspired by the wide success of le”
Sparse Overcomplete Word Vector Representations (2015, methodology): “Unlike recent approaches of incorporating semantics in distributional word vectors (Yu and Dredze, 2014; Xu et al., 2014; Faruqui et al., 2015), the method does not rely on any external information source.”
Neural information retrieval: at the end of the early years (2017, methodology): “The authors’ first model exploits KBs to enhance the representation of a document-query pair and its similarity score by exploiting concept embeddings learned from the KB distributed representation (Faruqui et al. 2014; Xu et al. 2014) as input to deep NNss like DSSM.”
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning (2018, methodology): “…embeddings using lexical resources modiﬁed the objective function of a neural language model for learning word embeddings (e.g., Skip-gram of Word2vec) in order to integrate relations from lexical resources into the learning process (Xu, Bai, Bian, Gao, Wang, Liu, & Liu, 2014; Yu & Dredze, 2014).”
Learning Continuous Word Embedding with Metadata for Question Retrieval in Community Question Answering (2015, methodology): “Xu et al. (2014) used the knowledge graph to advance the learning of word embeddings.”
Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge (2016, background): “In the natural language processing community, there are some works that have been proposed to employ semantic knowledge to improve the learning of word embeddings [17, 18, 19, 20, 21].”
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints (2017, methodology): “Learning from Scratch: some methods modify the prior or the regularization of the original training procedure using the set of linguistic constraints (Yu and Dredze, 2014; Xu et al., 2014; Bian et al., 2014; Kiela et al., 2015; Aletras and Stevenson, 2015).”
Mut2Vec: distributed representation of cancerous mutations (2018, methodology): “RC-NET [13] adds two regularization functions to the Skip-Gram objective function, which capture the relational distance between the words based on their categorical information.”
Exploiting Domain Knowledge via Grouped Weight Sharing with Application to Text Categorization (2017, background): “There have been efforts to exploit such resources specifically to induce better word vectors (Yu and Dredze, 2014; Faruqui et al., 2014; Yu et al., 2016; Xu et al., 2014).”
Learning to Compute Word Embeddings On the Fly (2017, background): “Enhancing word embeddings with auxiliary data from knowledge bases (including wordnet) has a long tradition (Xu et al., 2014; Faruqui et al., 2015).”
Assessing State-of-the-Art Sentiment Models on State-of-the-Art Sentiment Datasets (2017, background): “All above approaches show improvements over previous word embedding approaches (Mnih and Teh, 2012; Yu and Dredze, 2014; Xu et al., 2014) on this data set.”
Knowledge-Driven Event Embedding for Stock Prediction (2016, result): “Our work is also related to prior research on joint embedding of words and knowledge graphs (Xu et al., 2014; Wang et al., 2014; Tian et al., 2016; Yang et al., 2014).”
Memory, Show the Way: Memory Based Few Shot Word Representation Learning (2018, background): “Note that several rare word learning methods (Long et al., 2017; Xu et al., 2014; Lazaridou et al., 2013) that rely on auxiliary information don’t apply with most of our task settings.”
Learning Domain-Specific Word Embeddings from Sparse Cybersecurity Texts (2017, background): “Since then, many extensions to Word2Vec have been proposed (Levy and Goldberg 2014), (Luong, Socher, and Manning 2013), (Yu and Dredze 2014), (Bian, Gao, and Liu 2014), (Xu et al. 2014), (Faruqui et al. 2014), (Bol-legala et al. 2016), (Le and Mikolov 2014).”
Learning Semantic Word Embeddings based on Ordinal Knowledge Constraints (2015, methodology): “Besides, a novel framework has been proposed in (Xu et al., 2014) to take advantage of both relational and categorical knowledge to learn high-quality word representations, where two regularization functions are used to model the relational and categorical knowledge respectively.”