NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs
| Autor: | Alexandros Potamianos, Georgios Paraskevopoulos, Christos Baziotis, Athanasia Kolovou, Nikolaos Ellinas, Pinelopi Papalampidi, Athanasiou Nikolaos |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Computer science business.industry 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Syntax Backpropagation SemEval Task (project management) Recurrent neural network Character (mathematics) Ranking 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Word2vec Artificial intelligence business computer Computation and Language (cs.CL) Natural language processing Word (computer architecture) 0105 earth and related environmental sciences |
| Zdroj: | SemEval@NAACL-HLT |
| Popis: | In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3 "Irony detection in English tweets". We design and ensemble two independent models, based on recurrent neural networks (Bi-LSTM), which operate at the word and character level, in order to capture both the semantic and syntactic information in tweets. Our models are augmented with a self-attention mechanism, in order to identify the most informative words. The embedding layer of our word-level model is initialized with word2vec word embeddings, pretrained on a collection of 550 million English tweets. We did not utilize any handcrafted features, lexicons or external datasets as prior information and our models are trained end-to-end using back propagation on constrained data. Furthermore, we provide visualizations of tweets with annotations for the salient tokens of the attention layer that can help to interpret the inner workings of the proposed models. We ranked 2nd out of 42 teams in Subtask A and 2nd out of 31 teams in Subtask B. However, post-task-completion enhancements of our models achieve state-of-the-art results ranking 1st for both subtasks. SemEval-2018, Task 3 "Irony detection in English tweets" |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|