Jacob Eisenstein

TL;DR: This tutorial will provide an overview of techniques and datasets from the quantitative social sciences and the digital humanities, which are not well-known in the computational linguistics community, which include vector autoregressive models, multiple comparisons corrections for hypothesis testing, and causal inference.

TL;DR: In this paper, the authors, mentions, and entities are encoded in a continuous vector space, which is constructed so that socially-connected authors have similar vector representations, and incorporated into a neural structured prediction model, which captures structural constraints that are inherent in the entity linking task.

TL;DR: Two novel techniques for nominating attributes and a method for assessing the suitability of candidate attributes for object recognition are introduced and both taxonomy and distributional similarity serve as useful sources of information for attribute nomination and the methods can effectively exploit them.

TL;DR: This paper assess the capability of domain adaptation techniques to cope with historical texts, focusing on the classic benchmark task of part-of-speech tagging, and demonstrate that feature embedding method for unsupervised domain adaptation outperforms word embeddings and Brown clusters, showing the importance of embedding the entire feature space, rather than just individual words.

TL;DR: The authors compare English with other transfer languages for fine-tuning, on two pre-trained multilingual models (mBERT and mT5) and multiple classification and question answering tasks.