The group is concerned with interdisciplinary research combining linguistic modelling with machine learning techniques. The scope of research includes fundamental issues in the statistical nature of language, fundamental issues in machine learning for structure prediction problems, and empirical evaluations that cross these two themes.
- Semantic role parsing
- Latent variable models
- Multi-lingual processing
- Syntactic dependency parsing
- Cross-lingual annotation transfer
- Statistical spoken dialogue systems
- Syntactic function parsing
- Spoken language understanding.
- A Vector Space for Distributional Semantics for Entailment.
- Multi-lingual Dependency Parsing Evaluation: a Large-scale Analysis of Word Order Properties using Artificial Data. TACL
- Diachronic Trends in Word Order Freedom and Dependency Length in Dependency-Annotated Corpora of Latin and Ancient Greek.
- Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training.