Please use this identifier to cite or link to this item:
Title: LCT-MALTAs submission to RepEval 2017 shared task
Authors: Trong Vu, Hoa
Pham, Thuong-Hai
Bai, Xiaoyu
Tanti, Marc
van der Plas, Lonneke
Gatt, Albert
Keywords: Reference (Linguistics)
Natural language processing (Computer science)
Corpora (Linguistics)
Linguistic analysis (Linguistics)
Issue Date: 2017
Publisher: Association for Computational Linguistics
Citation: Trong Vu, H., Pham, T-H., Bai, X., Tanti, M., Van der Plas, L., & Gatt, A. (2017). LCT-MALTA's submission to RepEval 2017 shared Task. 2nd Workshop on Evaluating Vector Space Representations for NLP, Copenhagen. 56-60.
Abstract: We present in this paper our team LCTMALTA’s submission to the RepEval 2017 Shared Task on natural language inference. Our system is a simple system based on a standard BiLSTM architecture, using as input GloVe word embeddings augmented with further linguistic information. We use max pooling on the BiLSTM outputs to obtain embeddings for sentences. On both the matched and the mismatched test sets, our system clearly beats the shared task’s BiLSTM baseline model.
Appears in Collections:Scholarly Works - InsLin

Files in This Item:
File Description SizeFormat 
document(1).pdf100.69 kBAdobe PDFView/Open

Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.