ACS Project Suggestions

English Resource Semantic parsing for question answering

Proposer: Weiwei Sun

Supervisor: Weiwei Sun and Guy Emerson

Description: English Resource Semantics (ERS) is a linguistically-precise resource for semantically-informed natural language processing. The recent years have seen a rapid progress in semantic parsing for ERS  —  modern neural parsers are of high-quality in terms of accuracy, efficiency and robustness. However, it is still understudied how to consume ERS analyses in advanced natural language understanding applications. In this project the student will work on models to transduce from ERS representations to (complex) database queries and build practical systems for knowledge base question answering.


Surface realisation from incomplete meaning representations (ticketed)

Mark Steedman @ACL Lifetime Achievement Award Lecture

... you can get away with incomplete semantics when you are doing parsing, but when you're doing generation, you have to specify everything in semantics. And we don't know how to do that. At least we don't know how to do that completely or properly.

Proposer/Supervisor: Weiwei Sun

Description: In this project, the student will empirically study the computational problems in mapping incomplete meaning representations to surface forms.


Supporting language learners understanding complex syntactic structures in English texts

Proposer: Weiwei Sun

Supervisor: Weiwei Sun, Andrew Caines and Paula Buttery

Description: Long multi-agent, multi-clause sentences can prove challenging for learners of English to understand. Many such sentences occur in professional literature, teaching textbooks and language exams, e.g. IELTS, SAT and GRE. Modern parsers trained on large-scale data can produce high-quality syntactic and semantic analysis for English sentences, even those with very complicated structures. However, how to automatically interpret linguistic representations for pedagogical purpose is still understudied. In this project the student will work on models to transduce from syntactic constituency parses of long sentences to pedagogical analyses of long sentences which may be presented to learners as a way to support sentence interpretation.

Resources: corpus of 1000 English textbook sentences annotated with templates for pedagogical explanation of syntactic structures (already built).