LKE/KDSL Research Seminar


On Tuesday August 26th, there will be two talks at the LKE/KDSL Research Seminar.

Ilia Kuznetsov

Annotation projection for Semantic Role Labeling (Implementation)

I will present a DKPro-based implementation of the annotation projection method described in [1]. A graph alignment technique based on Integer Linear Programming is used to project SRL annotations from a small labeled seed corpus to a larger expansion corpus. The resulting extended dataset is then used to train an SRL system. In my talk, I will explain the method and present the preliminary results of our implementation work. In addition, I will give a short overview of the additional DKPro-based modules that we have developed. These modules can be re-used in other research projects.

[1] Semi-supervised Semantic Role Labeling via Structural Alignment. Hagen Fürstenau and Mirella Lapata. 2012. Computational Linguistics, 38(1):135-171.

Ahcène Boubekki

Mining Implications from Data

Item Tree Analysis (ITA) can be used to mine deterministic relationships from noisy data. In the educational domain, it has been used to infer descriptions of student knowledge from test responses in order to discover the implications between test items, allowing researchers to gain insight into the structure of the respective knowledge space. Existing approaches to ITA are computationally intense and yield results of limited accuracy, constraining the use of ITA to small datasets. We present work in progress towards an improved method that allows for efficient approximate ITA, enabling the use of ITA on larger data sets. Experimental results show that our method performs comparably to or better than existing approaches.