LIMSI-COT at SemEval-2016 Task 12: Temporal relation identification using a pipeline of classifiers

Abstract

SemEval 2016 Task 12 addresses temporal reasoning in the clinical domain. In this paper, we present our participation for relation extraction based on gold standard entities (subtasks DR and CR). We used a supervised approach comparing plain lexical features to word embeddings for temporal relation identification, and obtained above-median scores.

LIMSI-COT at SemEval-2017 Task 12: Neural Architecture for Temporal Information Extraction from Clinical Narratives

“…which) which are not available at the inter-sentence level. Furthermore, past work on the topic seems to indicate that this differentiation improves overall performance (Tourille et al, 2016). We have adopted this approach by building two separate classifiers, one for intra-sentence relations and one for inter-sentence relations.…”

“…Similarly, CRF and neural networks models have been used for the second group of subtasks (AAl Abdulsalam et al, 2016;Cohan et al, 2016;Lee et al, 2016). Other approaches include Support Vector Machines (SVM) (AAl Abdulsalam et al, 2016;Tourille et al, 2016).…”

SemEval-2016 Task 12: Clinical TempEval

“…LIMSI (Grouin and Moriceau, 2016) submitted 2 runs for each phase, based on conditional random fields with lexical, morphological, and word cluster features, and the rule-based Heidel-Time (Strötgen and Gertz, 2013). LIMSI-COT (Tourille et al, 2016) submitted 2 runs for phase 2, the first based on support vector ma-chines with lexical, syntactic, structural, and UMLS features, and the second based on replacing the lexical features with word embeddings. ULISBOA (Barros et al, 2016) 2 runs for each phase, based on conditional random fields with morpho-syntactic, lexical, UMLS, and DBpedia features.…”

Neural Architecture for Temporal Relation Extraction: A Bi-LSTM Approach for Detecting Narrative Containers

“…Herein, we focus on the second part of the challenge, temporal relation extraction and more specifically the narrative container relations. Different approaches have been implemented by the participants, including Support Vector Machine (SVM) classifiers (AAl Abdulsalam et al, 2016;Cohan et al, 2016;Lee et al, 2016;Tourille et al, 2016), Conditional Random Fields (CRF) and convolutional neural networks (CNNs) (Chikka, 2016). Beyond the challenges, Leeuwenberg and Moens (2017) propose a model based on a structured perceptron to jointly predict both types of temporal relations.…”