W
Waleed Ammar
Researcher at Allen Institute for Artificial Intelligence
Publications - 57
Citations - 4323
Waleed Ammar is an academic researcher from Allen Institute for Artificial Intelligence. The author has contributed to research in topics: Context (language use) & Scientific literature. The author has an hindex of 27, co-authored 53 publications receiving 3424 citations. Previous affiliations of Waleed Ammar include University of Pittsburgh & Google.
Papers
More filters
Proceedings ArticleDOI
Semi-supervised sequence tagging with bidirectional language models
TL;DR: A general semi-supervised approach for adding pre- trained context embeddings from bidirectional language models to NLP systems and apply it to sequence labeling tasks, surpassing previous systems that use other forms of transfer or joint learning with additional labeled data and task specific gazetteers.
Posted Content
DyNet: The Dynamic Neural Network Toolkit
Graham Neubig,Chris Dyer,Yoav Goldberg,Austin Matthews,Waleed Ammar,Antonios Anastasopoulos,Miguel Ballesteros,David Chiang,Daniel Clothiaux,Trevor Cohn,Kevin Duh,Manaal Faruqui,Cynthia Gan,Dan Garrette,Yangfeng Ji,Lingpeng Kong,Adhiguna Kuncoro,Gaurav Kumar,Chaitanya Malaviya,Paul Michel,Yusuke Oda,Matthew Richardson,Naomi Saphra,Swabha Swayamdipta,Pengcheng Yin +24 more
TL;DR: DyNet is a toolkit for implementing neural network models based on dynamic declaration of network structure that has an optimized C++ backend and lightweight graph representation and is designed to allow users to implement their models in a way that is idiomatic in their preferred programming language.
Proceedings ArticleDOI
ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing
TL;DR: ScispaCy as mentioned in this paper is a new tool for practical biomedical/scientific text processing, which heavily leverages the spaCy library and demonstrates robustness on several tasks and datasets.
Posted Content
Massively Multilingual Word Embeddings
TL;DR: New methods for estimating and evaluating embeddings of words in more than fifty languages in a single shared embedding space are introduced and a new evaluation method is shown to correlate better than previous ones with two downstream tasks.
Proceedings ArticleDOI
ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing
TL;DR: ScispaCy as discussed by the authors is a new Python library and models for practical biomedical/scientific text processing, which heavily leverages the spaCy library and demonstrates their robustness on several tasks and datasets.