Edward Newell


2020

pdf bib
Deconstructing word embedding algorithms
Kian Kenyon-Dean | Edward Newell | Jackie Chi Kit Cheung
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Word embeddings are reliable feature representations of words used to obtain high quality results for various NLP applications. Uncontextualized word embeddings are used in many NLP tasks today, especially in resource-limited settings where high memory capacity and GPUs are not available. Given the historical success of word embeddings in NLP, we propose a retrospective on some of the most well-known word embedding algorithms. In this work, we deconstruct Word2vec, GloVe, and others, into a common form, unveiling some of the common conditions that seem to be required for making performant word embeddings. We believe that the theoretical findings in this paper can provide a basis for more informed development of future models.

2018

pdf bib
An Attribution Relations Corpus for Political News
Edward Newell | Drew Margolin | Derek Ruths
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Constructing a Lexicon of Relational Nouns
Edward Newell | Jackie C.K. Cheung
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2017

pdf bib
Assessing the Verifiability of Attributions in News Text
Edward Newell | Ariane Schang | Drew Margolin | Derek Ruths
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

When reporting the news, journalists rely on the statements of stakeholders, experts, and officials. The attribution of such a statement is verifiable if its fidelity to the source can be confirmed or denied. In this paper, we develop a new NLP task: determining the verifiability of an attribution based on linguistic cues. We operationalize the notion of verifiability as a score between 0 and 1 using human judgments in a comparison-based approach. Using crowdsourcing, we create a dataset of verifiability-scored attributions, and demonstrate a model that achieves an RMSE of 0.057 and Spearman’s rank correlation of 0.95 to human-generated scores. We discuss the application of this technique to the analysis of mass media.