Knowledge-Powered Deep Learning for Word Embedding

By Jiang Bian, Bin Gao, Tie-Yan Liu. 2014

188 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

Knowledge Infused Learning (K-IL): Towards Deep Incorporation of Knowledge in Deep Learning (2019, background): “(Bian, Gao, and Liu 2014) has empirically demonstrated the effectiveness of combining richer semantics from domain knowledge with morphological and syntactic knowledge in the text, by modeling knowledge as an auxiliary task that reg-ularizes the learning of the main objective in a deep neural…”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “Known relations among words can be utilized as augmented contexts [88] in word2vec training”
AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes (2015, methodology): “Bian et al. (2014) used not only semantic, but also morphological and syntactic knowledge to compute more effective word embeddings.”
RC-NET: A General Framework for Incorporating Knowledge into Word Representations (2014, methodology): “Then, we describe how we model relational knowledge and categorical knowledge as regularization functions.”
Dependency Recurrent Neural Language Models for Sentence Completion (2015, methodology): “Similarly, Bian et al. (2014) enriched the Continuous Bag-of-Words (CBOW) model of Mikolov et al. (2013) by incorporating morphology, PoS tags and entity categories into 600-dimensional word embed-dings trained on the Gutenberg dataset, increasing sentence completion accuracy from 41% to 44%.”
Large Language Models as Analogical Reasoners (2023, methodology): “Analogical reasoning has also influenced the development of artificial intelligence and machine learning algorithms (Carbonell, 1983; Mitchell et al., 1986) and has been employed as a reasoning benchmark for assessing machine learning models (Bian et al., 2014; Huang et al., 2021).”
Counter-fitting Word Vectors to Linguistic Constraints (2016, methodology): “Some methods modify the prior or the regularization of the original training procedure (Yu and Dredze, 2014; Bian et al., 2014; Kiela et al., 2015).”
Neural Network Matrix Factorization (2015, methodology): “Other approaches to KGs use neural networks to produce representations, rather than map representations to predictions, like NTN and NNMF. (See, e.g., (Huang et al., 2015) and (Bian et al., 2014).)”
Shades of Knowledge-Infused Learning for Enhancing Deep Learning (2019, background): “In an empirical study, Bian et al.(3) showed the effectiveness of combining richer semantics from domain knowledge with morphological and syntactic knowledge in the text, by modeling knowledge assistance as an auxiliary task that regularizes learning of the main objective in a deep neural network.”
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).”
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).”