*SEM 2012: The First Joint Conference on Lexical and Computational Semantics

*SEM 2012 Shared Task: Resolving the Scope and Focus of Negation

The Joint Conference on Lexical and Computational Semantics (*SEM) each year hosts a shared task on semantic related topics. In its first edition held in 2012, the shared task was dedicated to resolving the scope and focus of negation. This paper presents the specifications, datasets and evaluation criteria of the task. An overview of participating systems is provided and their results are summ...

Proceedings of the Third Joint Conference on Lexical and Computational Semantics, *SEM@COLING 2014, August 23-24, 2014, Dublin, Ireland

*SEM 2013: The Second Joint Conference on Lexical and Computational Semantics

Within the SemEval-2013 evaluation exercise, theTempEval-3 shared task aims to advance researchon temporal information processing. It follows onfrom TempEval-1 and -2, with: a three-part struc-ture covering temporal expression, event, and tem-poral relation extraction; a larger dataset; and newsingle measures to rank systems – in each task and ingeneral. In this pape...

Burford, Clint, Steven Bird and Timothy Baldwin (to appear) Collective Document Classification with Implicit Inter-document Semantic Relationships, In Proceedings of *SEM 2015: The Fourth Joint Conference on Lexical and Computational Semantics, Denver, USA

This paper addresses the question of how document classifiers can exploit implicit information about document similarity to improve document classifier accuracy. We infer document similarity using simple n-gram overlap, and demonstrate that this improves overall document classification performance over two datasets. As part of this, we find that collective classification based on simple iterati...

DLS$@$CU-CORE: A Simple Machine Learning Model of Semantic Textual Similarity

We present a system submitted in the Semantic Textual Similarity (STS) task at the Second Joint Conference on Lexical and Computational Semantics (*SEM 2013). Given two short text fragments, the goal of the system is to determine their semantic similarity. Our system makes use of three different measures of text similarity: word n-gram overlap, character n-gram overlap and semantic overlap. Usi...