Enabling Dynamic Interactions between Natural Language and Structured Knowledge Bases
- Speaker
- Hady Elsahar (Naver Labs Europe)
- Date
- Room
- Salle 306, bâtiment IMAG
The complementary nature between Natural Language and Structured Knowledge Bases has inspired a lot of applications that involve interactions in between, such as Information Extraction, Question Answering and Natural Language Generation.
Natural language processing models responsible for those interactions are usually designed in a static way, with the abundance of continuously published new information on the web they require a tedious process of maintenance and adaptation.
In this direction, I’ll present several contributions from My PhD. thesis to tackle this issue. Firstly, T-REx an architecture for automatically generating alignment datasets between natural language text and structured knowledge bases, alongside with the largest available dataset of the same kind.
Secondly, I’ll present an encoder-decoder neural network architecture for question generation from knowledge base triples in a zero-shot setup; this model occupied with part-of-speech tag copy actions has proven its capacity of generating questions for unseen relation and entity types during test time, and hence has a large potential of being used in data-augmentation techniques for training Question Answering systems in an evolving way. Finally, I’ll present several delexicalization techniques to generate entity descriptions from structured triples, this method has proven efficiency to generate entity summaries in an under-served multilingual setup with limited training datasets.
