Re-embedding words

By Igor Labutov, Hod Lipson. 2013

114 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.

Citations in the corpus

Recent Trends in Deep Learning Based Natural Language Processing (2017, background): “(Labutov and Lipson, 2013) proposed task specific embeddings which retrain the word embeddings to align them in the current task space.”
Document Modeling with Gated Recurrent Neural Network for Sentiment Classification (2015, background): ““good” and “bad”) to neighboring vectors, several studies (Maas et al., 2011; Labutov and Lipson, 2013; Tang et al., 2014) learn sentiment-specific word embeddings by taking sentiment of texts into account.”
Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification (2014, methodology): “The representation of words heavily relies on the applications or tasks in which it is used (Labutov and Lipson, 2013).”
Building Large-Scale Twitter-Specific Sentiment Lexicon : A Representation Learning Approach (2014, background): “Labutov and Lipson (2013) learn task-speciﬁc embedding from an existing embedding and sentences with gold sentiment polarity.”
Sentiment Embeddings with Applications to Sentiment Analysis (2016, background): “ReEmbed: Labutov and Lipson [47] learn taskspecific embeddings based on an existing background embedding and sentiment-specific corpus.”
Refining Word Embeddings for Sentiment Analysis (2017, background): “…of distinguishing words with similar vector representations but opposite sentiment polarities, recent studies have suggested learning sentiment embeddings from labeled data in a supervised manner (Maas et al., 2011; Labutov and Lipson, 2013; Lan et al., 2016; Ren et al., 2016; Tang et al., 2016).”
Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory (2015, unknown): “(Maas et al., 2011; Labutov and Lipson, 2013).”
AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes (2015, background): “Labutov and Lipson (2013) tuned existing word embeddings in supervised training, not to create new embeddings for senses or entities, but to get better predictive performance on a task while not changing the space of embeddings.”
Uncovering Divergent Linguistic Information in Word Embeddings with Lessons for Intrinsic and Extrinsic Evaluation (2018, background): “Finally, Labutov and Lipson (2013) perform unconstrained optimization with proper regularization to specialize embeddings in a supervised task.”
Word Embeddings through Hellinger PCA (2013, background): “For supervised tasks relying more on the semantic aspect as sentiment classification, it is usually helpful to adapt the existing embeddings to improve performance (Labutov and Lipson, 2013).”
Learning Semantic Representations of Users and Products for Document Level Sentiment Classification (2015, background): “, 2014) use local and global contexts, (Maas et al., 2011; Labutov and Lipson, 2013; Tang et al., 2014b; Tang et al., 2014a; Zhou et al., 2015) further incorporate sentiment of texts.”
A Comparative Study on Regularization Strategies for Embedding-based Neural Networks (2015, methodology): “• Re-embedding words (Labutov and Lipson, 2013).”
Recent Trends in Deep Learning Based Natural Language Processing [Review Article] (2018, background): “Labutov and Lipson [26] proposed task specific embeddings which retrain the word embeddings to align them in the current task space.”
Sentiment Analysis: Detecting Valence, Emotions, and Other Affectual States from Text (2016, unknown): “…farther away from each other (Maas, Daly, Pham, Huang, Ng, & Potts, 2011; Tang, Wei, Qin, Zhou, & Liu, 2014b; Ren, Zhang, Zhang, & Ji, 2016); and (2) those that modify (refine/retrofit) word embeddings post-hoc (Labutov & Lipson, 2013; Faruqui et al., 2015; Hamilton et al., 2016; Yu et al., 2017).”