Zulipiye Yusupujiang


Status : PhD student

Address :

LLF, CNRS – UMR 7110
Université Paris Diderot-Paris 7
Case 7031 – 5, rue Thomas Mann,
75205 Paris cedex 13

E-mail : mhyvcvlr.lhfhchwvnat@yvathvfg.havi-cnevf-qvqrebg.se


Title : Characterising the Response Space of Questions Across Languages

Supervision :
  Jonathan Ginzburg

Inscription : 2019 à Paris 7

Abstract :

The main objective of this project is to characterize the response space of questions within and across languages through detailed corpus studies, formal modelling, and by using advanced machine learning technique to learn the classification of di↵erent response spaces. This involves the following aims:

  1. Dialogue Corpus Construction: constructing a dialogue corpus for a low resource language, using a controlled but non-intrusive experimental technique.

  2. Semantics and pragmatics: building a corpus-based taxonomy of response spaces for English and Uyghur; Using machine learning techniques for classification.

  3. Syntax/semantics interface: enhancing the machine learning system by developing formal grammatical analysis using syntactic and semantic dependency parsing.