Natural Language Processing
Much of the information that can help transform enterprises is locked away in text, like documents, tables, and charts. We’re building advanced AI systems that can parse vast bodies of text to help unlock that data, but also ones flexible enough to be applied to any language problem.
Our work
Debugging foundation models for bias
ResearchImproving Watson NLP performance in IBM products through Intel optimizations
Technical noteTraining a customer service bot to sound more human
ResearchConverting several audio streams into one voice makes it easier for AI to learn
ResearchFrom unlabeled text to a working classifier in a few hours
NewsPutting more knowledge at the fingertips of non-English speakers
Release- See more of our work on Natural Language Processing
Tools + code
Transition-based AMR Parser
Transition-based parser for Abstract Meaning Representation (AMR) in Pytorch.
View project →sIB: sequential Information Bottleneck
Implementation of sequential Information Bottleneck (sIB) in Python and in C++
View project →Low-Resource Text Classification Framework
Research framework for low resource text classification that allows the user to experiment with classification models and active learning strategies on a large number of sentence classification datasets, and to simulate real-world scenarios. The framework is easily expandable to new classification models, active learning strategies and datasets.
View project →Project Debater for Academic Use
The technologies underlying Project Debater available as cloud services. Includes core natural language understanding capabilities, argument mining, and narrative generation.
View project →
Publications
- 2023
- AAAI 2023
- 2023
- AAAI 2023
- 2023
- AAAI 2023
- 2023
- AAAI 2023
- 2023
- AAAI 2023
- 2023
- GWC 2023