1 code implementation • 6 Apr 2018 • Noah Siegel, Nicholas Lourie, Russell Power, Waleed Ammar
Non-textual components such as charts, diagrams and tables provide key information in many scientific documents, but the lack of large labeled datasets has impeded the development of data-driven methods for scientific figure extraction.
1 code implementation • NAACL 2018 • Chandra Bhagavatula, Sergey Feldman, Russell Power, Waleed Ammar
We present a content-based method for recommending citations in an academic paper draft.
no code implementations • SEMEVAL 2017 • Waleed Ammar, Matthew Peters, Ch Bhagavatula, ra, Russell Power
This paper describes our submission for the ScienceIE shared task (SemEval- 2017 Task 10) on entity and relation extraction from scientific papers.
1 code implementation • 20 Jun 2017 • Chenyan Xiong, Zhuyun Dai, Jamie Callan, Zhiyuan Liu, Russell Power
Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to extract multi-level soft match features, and a learning-to-rank layer that combines those features into the final ranking score.
2 code implementations • ACL 2017 • Matthew E. Peters, Waleed Ammar, Chandra Bhagavatula, Russell Power
Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks.
Ranked #50 on Named Entity Recognition (NER) on CoNLL 2003 (English)