He is s defending the thesis Low-Resource Adaptation of Neural NLP Models.

Real-world applications of natural language processing (NLP) are challenging. NLP models rely heavily on supervised machine learning and require copious amounts of annotated data. These resources are often based on language data available in massive quantities, such as English newswires. However, in real-world applications of NLP, the textual resources vary across several dimensions, such as language, dialect, topic, and genre. It is challenging to find annotated data of sufficient amount and quality. The objective of this thesis is to investigate methods for dealing with such low-resource scenarios in information extraction and natural language understanding. To this end, we study distant supervision and sequential transfer learning in various low-resource settings. We develop and adapt neural NLP models to explore several research questions concerning NLP tasks with minimal or no training data.

During his time at SIRIUS, Farhad has collaborated with Schlumberger and IBM. He was also an UTFORSK exchange fellow at the Federal University of Rio Grande do Sul.

Trial Lecture

His trial lecture will be on “Natural Language Inference: Datasets, Methods, Current Challenges and What’s Next”

The post PhD Defence for Farhad Nooralahzadeh 30th October 2020 appeared first on Sirius.

Rustam Mehmandarov moderated the questions at the seminar.

Basil’s talk is in English, while the rest of the seminar is in Norwegian.

The post Public Lecture on Language Processing appeared first on Sirius.