AI Strategy and Concepts Bibliography

WIKINDX Resources

Alt, C., H"ubner, M., & Hennig, L. (2019). Fine-tuning pre-trained transformer language models to distantly supervised relation extraction. arXiv preprint arXiv:1906.08646, 
Added by: SijanLibrarian (2020-10-06 13:14:19)   Last edited by: SijanLibrarian (2020-10-06 13:17:14)
Resource type: Journal Article
BibTeX citation key: Alt2019
Email resource to friend
View all bibliographic details
Categories: Artificial Intelligence, Cognitive Science, Computer Science, Data Sciences, Decision Theory, General
Subcategories: Autonomous systems, Big data, Decision making, Deep learning, Machine intelligence, Machine learning, Machine recognition, Neural nets, Synthetic intelligence
Creators: Alt, H"ubner, Hennig
Collection: arXiv preprint arXiv:1906.08646
Views: 48/61
Views index: 16%
Popularity index: 4%
Abstract
Distantly supervised relation extraction is widely used to extract relational facts from text, but suffers from noisy labels. Current relation extraction methods try to alleviate the noise by multi-instance learning and by providing supporting linguistic and contextual information to more efficiently guide the relation classification. While achieving state-of-the-art results, we observed these models to be biased towards recognizing a limited set of relations with high precision, while ignoring those in the long tail. To address this gap, we utilize a pre-trained language model, the OpenAI Generative Pre-trained Transformer (GPT) [Radford et al., 2018]. The GPT and similar models have been shown to capture semantic and syntactic features, and also a notable amount of "common-sense" knowledge, which we hypothesize are important features for recognizing a more diverse set of relations. By extending the GPT to the distantly supervised setting, and fine-tuning it on the NYT10 dataset, we show that it predicts a larger set of distinct relation types with high confidence. Manual and automated evaluation of our model shows that it achieves a state-of-the-art AUC score of 0.422 on the NYT10 dataset, and performs especially well at higher recall levels.
  
wikindx 6.2.2 ©2003-2020 | Total resources: 1447 | Username: -- | Bibliography: WIKINDX Master Bibliography | Style: American Psychological Association (APA) | Database queries: 61 | DB execution: 0.12362 secs | Script execution: 0.13704 secs