Computational Linguistics Colloquium

Thursday, 28 May, 16:15
Conference Room, Building C7 4

Constraint satisfaction inference for dependency parsing and MT

Antal van den Bosch
Tilburg centre for Creative Computing, Tilburg University

Many tasks in NLP are mappings to output spaces representing complex structures. Yet, machine learning methods cannot learn mappings to structures with the level of complexity found in NLP (e.g. complete dependency graphs, or full translations). The consequence is that the larger tasks are partially solved at more local levels by machine learning classifiers, and in a second stage at the global level by a search or inference method that finds the most likely output structure. In this presentation I present constraint satisfaction inference, a theory-neutral inference method that accepts heterogeneous partial solutions to a structured prediction problem, using weighted constraint satisfaction as a means to quantify the success of global solutions. The approach is exemplified on two NLP tasks: dependency parsing and machine translation, using memory-based learning for the local classifiers. This presentation is based on collaborative work with Sander Canisius.

If you would like to meet with the speaker, please contact Caroline Sporleder.