UTD: Ensemble-Based Spatial Relation Extraction

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 862–869, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics UTD: Ensemble-Based Spatial Relation Extraction Jennifer D’Souza and Vincent Ng Human Language Technology Research Institute University of Texas at Dallas Richardson, TX 75083-0688 {jld082000,vince}@hlt.utdallas.edu Abstract SpaceEval (SemEval 2015 Task 8), which concerns spatial information extraction, builds on the spatial role identification tasks intro- duced in SemEval 2012 and used in SemEval 2013. Among the host of subtasks presented in SpaceEval, we participated in subtask 3a, which focuses solely on spatial relation ex- traction. To address the complexity of a MOVELINK, we decompose it into smaller re- lations so that the roles involved in each rela- tion can be extracted in a joint fashion with- out losing computational tractability. Our sys- tem was ranked first in the official evaluation, achieving an overall spatial relation extraction F-score of 84.5%. 1 Introduction SpaceEval1 was organized as a shared task for the semantic evaluation of spatial information extraction (IE) systems. The goals of the shared task include identifying and classifying particular constructions in natural language for expressing spatial informa- tion that are conveyed through the spatial concepts of locations, entities participating in spatial rela- tions, paths, topological relations, direction and ori- entation, motion, etc. It presents a wide spectrum of spatial IE related subtasks for interested participants to choose from, building on the two previous years shared tasks on the same topic (Kordjamshidi et al., 2012; Kolomiyets et al., 2013). Our goal in this paper is to describe the version of our spatial relation extraction system that partic- 1http://alt.qcri.org/semeval2015/task8/ ipated in subtask 3a of SpaceEval. Systems par- ticipating in this subtask assume as input the spa- tial elements in a text document. For example, in the sentence The flower is in the vase1 and the vase2 is on the table, the set of spatial elements {flower, in, vase1, vase2, on, table} are given and subsequently used as candidates for predicting spa- tial relations. Leveraging the successes of a joint role-labeling approach to spatial relation extraction involving stationary objects, we employ it to ex- tract so-called MOVELINKs, which are spatial re- lations defined over objects in motion. In partic- ular, we discuss the adaptations needed to handle the complexity of MOVELINKs. Experiments on the SpaceEval corpus demonstrate the effectiveness of our ensemble-based approach to spatial relation ex- traction. Among the three teams participating in subtask 3a, our team was ranked first in the official evaluation, achieving an overall F-score of 84.5%. The rest of the paper is organized as follows. We first give a brief overview of the subtask 3a of SpaceEval and the corpus (Section 2). After that, we describes related work (Section 3). Finally, we present our approach (Section 4), evaluation results (Section 5), and conclusions (Section 6). 2 The SpaceEval Task 2.1 Subtask 3a: Task Description Subtask 3a focuses solely on spatial relation extrac- tion using a specified set of spatial elements for a given sentence. Specifically, given an …

Content truncated to 500 words