J
Jacob Eisenstein
Researcher at Google
Publications - 201
Citations - 11502
Jacob Eisenstein is an academic researcher from Google. The author has contributed to research in topics: Gesture & Language model. The author has an hindex of 50, co-authored 196 publications receiving 9772 citations. Previous affiliations of Jacob Eisenstein include Georgia Institute of Technology & University of Illinois at Urbana–Champaign.
Papers
More filters
Journal ArticleDOI
One Vector is Not Enough: Entity-Augmented Distributed Semantics for Discourse Relations
Yangfeng Ji,Jacob Eisenstein +1 more
TL;DR: This work computes distributed meaning representations for each discourse argument by composition up the syntactic parse tree and performs a downward compositional pass to capture the meaning of coreferent entity mentions.
Posted Content
Mimicking Word Embeddings using Subword RNNs
TL;DR: MIMICK is presented, an approach to generating OOV word embeddings compositionally, by learning a function from spellings to distributionalembeddings by performing learning at the type level of the original word embedding corpus.
Proceedings ArticleDOI
Mimicking Word Embeddings using Subword RNNs
TL;DR: This article proposed MIMICK, an approach to generate OOV word embeddings compositionally by learning a function from spellings to distributional embedding, which does not require re-training on the original word embedding corpus.
Proceedings Article
Learning Document-Level Semantic Properties from Free-Text Annotations
TL;DR: In this paper, a hierarchical Bayesian model with joint inference is proposed for summarizing single and multiple documents into a set of semantically salient keyphrases, which can be used to predict the properties of unannotated documents and to aggregate the semantic properties of multiple reviews.
Proceedings Article
A Log-Linear Model for Unsupervised Text Normalization
Yi Yang,Jacob Eisenstein +1 more
TL;DR: This work uses the output of UNLOL to automatically normalize a large corpus of social media text, revealing a set of coherent orthographic styles that underlie online language variation.