论文信息 - UMDSub at SemEval-2018 Task 2: Multilingual Emoji Prediction Multi-channel Convolutional Neural Network on Subword Embedding

UMDSub at SemEval-2018 Task 2: Multilingual Emoji Prediction Multi-channel Convolutional Neural Network on Subword Embedding

This paper describes the UMDSub system that participated in Task 2 of SemEval-2018. We developed a system that predicts an emoji given the raw text in a English tweet. The system is a Multi-channel Convolutional Neural Network based on subword embeddings for the representation of tweets. This model improves on character or word based methods by about 2\%. Our system placed 21st of 48 participating systems in the official evaluation.

Ted Pedersen | Zhenduo Wang

[1] Jeffrey Dean,et al. Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[2] Xiang Zhang,et al. Character-level Convolutional Networks for Text Classification , 2015, NIPS.

[3] Kyunghyun Cho,et al. Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers , 2016, ArXiv.

[4] Alexander M. Rush,et al. Character-Aware Neural Language Models , 2015, AAAI.

[5] John G. Breslin,et al. Character-level and Multi-channel Convolutional Neural Networks for Large-scale Authorship Attribution , 2016, ArXiv.

[6] Rico Sennrich,et al. Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[7] Paolo Rosso,et al. Convolutional Neural Networks for Authorship Attribution of Short Texts , 2017, EACL.

[8] Adam Kilgarriff,et al. Language is never, ever, ever, random , 2005 .

[9] Horacio Saggion,et al. SemEval 2018 Task 2: Multilingual Emoji Prediction , 2018, *SEMEVAL.

[10] Jeffrey Pennington,et al. GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[11] Tomas Mikolov,et al. Enriching Word Vectors with Subword Information , 2016, TACL.

[12] S. Arikawa,et al. Byte Pair Encoding: a Text Compression Scheme That Accelerates Pattern Matching , 1999 .