R
Richard Socher
Researcher at Salesforce.com
Publications - 280
Citations - 133837
Richard Socher is an academic researcher from Salesforce.com. The author has contributed to research in topics: Question answering & Language model. The author has an hindex of 77, co-authored 274 publications receiving 97703 citations. Previous affiliations of Richard Socher include Princeton University & University of Colorado Boulder.
Papers
More filters
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Proceedings ArticleDOI
Glove: Global Vectors for Word Representation
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Proceedings Article
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Richard Socher,Alex Perelygin,Jean Y. Wu,Jason Chuang,Christopher D. Manning,Andrew Y. Ng,Christopher Potts +6 more
TL;DR: A Sentiment Treebank that includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality, and introduces the Recursive Neural Tensor Network.
Proceedings ArticleDOI
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
TL;DR: The authors introduced the Tree-LSTM, a generalization of LSTMs to tree-structured network topologies, which outperformed all existing systems and strong LSTM baselines on two tasks: predicting the semantic relatedness of two sentences (SemEval 2014, Task 1) and sentiment classification (Stanford Sentiment Treebank).
Proceedings Article
Reasoning With Neural Tensor Networks for Knowledge Base Completion
TL;DR: An expressive neural tensor network suitable for reasoning over relationships between two entities given a subset of the knowledge base is introduced and performance can be improved when entities are represented as an average of their constituting word vectors.