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
Proceedings ArticleDOI
On Writing a Textbook on Natural Language Processing
TL;DR: The motivation and process for writing a college textbook on natural language processing are described, and advice and encouragement for readers who may be interested in writing a textbook of their own are offered.
Posted Content
Learning to Recognize Dialect Features
TL;DR: This paper introduced the task of dialect feature detection, and presented two multitask learning approaches, both based on pretrained transformers, to detect dialect differences in Indian English text and speech.
Proceedings Article
Counterfactual Invariance to Spurious Correlations in Text Classification
Posted Content
Learning to Look Inside: Augmenting Token-Based Encoders with Character-Level Information.
TL;DR: XRayEmb as discussed by the authors is a character-level encoder that computes vector representations of character sequences, and a generative component that decodes from the internal representation to a character sequence.
Proceedings Article
Unsupervised Domain Adaptation with Feature Embeddings.
Yi Yang,Jacob Eisenstein +1 more
TL;DR: In this paper, a simple feature embedding approach is proposed to exploit the feature template structure common in NLP problems, which provides better performance than the traditional pivot features that generalize across domains.