Deep semi-supervised learning is a fast-growing field with a range of practical applications.
This paper provides a comprehensive survey on both fundamentals and recent advances in …

Neural networks are a family of powerful machine learning models and this book focuses on
their application to natural language data. The first half of the book (Parts I and II) covers the …

Cross-linguistically consistent annotation is necessary for sound comparative evaluation
and cross-lingual learning experiments. It is also useful for multilingual system development …

Abstract Concept erasure aims to remove specified features from a representation. It can
improve fairness (eg preventing a classifier from using gender or race) and interpretability …

Although the Indonesian language is spoken by almost 200 million people and the 10th
most spoken language in the world, it is under-represented in NLP research. Previous work …

Dependency grammar is a descriptive and theoretical tradition in linguistics that can be
traced back to antiquity. It has long been influential in the European linguistics tradition and …

Revisiting the now de facto standard Stanford dependency representation, we propose an
improved taxonomy to capture grammatical relations across languages, including …

Please note that this manual describes the original Stanford Dependencies representation.
As of version 3.5. 2, the default representation output by the Stanford Parser and Stanford …