J
Jason Bolton
Researcher at Stanford University
Publications - 8
Citations - 1961
Jason Bolton is an academic researcher from Stanford University. The author has contributed to research in topics: Stanza & Tokenization (data security). The author has an hindex of 7, co-authored 8 publications receiving 1259 citations.
Papers
More filters
Proceedings ArticleDOI
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
TL;DR: This work introduces Stanza, an open-source Python natural language processing toolkit supporting 66 human languages that features a language-agnostic fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech and morphological feature tagging, dependency parsing, and named entity recognition.
Posted Content
A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
TL;DR: This paper conducted a thorough examination of this new reading comprehension task and showed that simple, carefully designed systems can obtain accuracies of 73.6% and 76.6 % on these two datasets, exceeding current state-of-the-art results by 7-10% and approaching what they believe is the ceiling for performance on this task.
Proceedings ArticleDOI
A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
TL;DR: A thorough examination of this new reading comprehension task by creating over a million training examples by pairing CNN and Daily Mail news articles with their summarized bullet points, and showing that a neural network can be trained to give good performance on this task.
Journal Article
Bootstrapped Self Training for Knowledge Base Population.
Gabor Angeli,Victor Zhong,Danqi Chen,Arun Tejasvi Chaganty,Jason Bolton,Melvin Jose Johnson Premkumar,Panupong Pasupat,Sonal Gupta,Christopher D. Manning +8 more
TL;DR: This work proposes bootstrapped selftraining to capture the benefits of both systems: the precision of patterns and the generalizability of trained models and shows that training on the output of patterns drastically improves performance over the patterns.
Posted Content
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
TL;DR: Stanza as mentioned in this paper is an open-source Python NLP toolkit supporting 66 human languages, including English, French, German, Dutch, Russian, Japanese, and Chinese. But it does not have a language-agnostic fully neural pipeline.