CitiusNLP at SemEval-2018 Task 10: The Use of Transparent Distributional Models and Salient Contexts to Discriminate Word Attributes

TítuloCitiusNLP at SemEval-2018 Task 10: The Use of Transparent Distributional Models and Salient Contexts to Discriminate Word Attributes
AutoresPablo Gamallo
TipoComunicación para congreso
Fonte 12th International Workshop on Semantic Evaluation (colocated at NAACL-HLT 2018), New Orleans, Louisiana, Estados Unidos, 2018.
DOI10.18653/v1/S18-1156
AbstractThis article describes the unsupervised strategy submitted by the CitiusNLP team to SemEval 2018 Task 10, a task which consists of predicting whether a word is a discriminative attribute between two other words. The proposed strategy relies on the correspondence between discriminative attributes and relevant contexts of a word. More precisely, the method uses transparent distributional models to extract salient contexts of words which are identified as discriminative attributes. The system performance reaches about 70% accuracy when it is applied on the development dataset, but its accuracy goes down (63%) on the official test dataset.
Palabras chavedistributional semantics, dependency analysis, discriminative attributes, similarity