Search Results for author:
Found 5 papers, 2 papers with code
Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations
Most weakly supervised named entity recognition (NER) models rely on domain-specific dictionaries provided by experts.
Lack of Fluency is Hurting Your Translation Model
While the most train sentences are created via automatic techniques such as crawling and sentence-alignment methods, the test sentences are annotated with the consideration of fluency by human.
Simple Questions Generate Named Entity Recognition Datasets
Recent named entity recognition (NER) models often rely on human-annotated datasets, requiring the significant engagement of professional knowledge on the target domain and entities.
Transferability of Natural Language Inference to Biomedical Question Answering
We observe that BioBERT trained on the NLI dataset obtains better performance on Yes/No (+5. 59%), Factoid (+0. 53%), List type (+13. 58%) questions compared to performance obtained in a previous challenge (BioASQ 7B Phase B).
SANVis: Visual Analytics for Understanding Self-Attention Networks
Attention networks, a deep neural network architecture inspired by humans' attention mechanism, have seen significant success in image captioning, machine translation, and many other applications.
