Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder

Abstract

We present Tweet2Vec, a novel method for generating general-purpose vector representation of tweets. The model learns tweet embeddings using character-level CNN-LSTM encoder-decoder. We trained our model on 3 million, randomly selected English-language tweets. The model was evaluated using two methods: tweet semantic similarity and tweet sentiment categorization, outperforming the previous state-of-the-art in both tasks. The evaluations demonstrate the power of the tweet embeddings generated by our model for various tweet categorization tasks. The vector representations generated by our model are generic, and hence can be applied to a variety of tasks. Though the model presented in this paper is trained on English-language tweets, the method presented can be used to learn tweet embeddings for different languages.

SIGIR 2016, July 17-21, 2016, Pisa. Proceedings of SIGIR 2016. Pisa, Italy (2016)

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Distributed Representations of Words and Phrases and their Compositionality
• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Natural Language Processing (almost) from Scratch
• Distributed Representations of Sentences and Documents
• Text Understanding from Scratch
• A Hierarchical Neural Autoencoder for Paragraphs and Documents

Cited by in corpus (12)

• EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition
• Online Training of LSTM Networks in Distributed Systems for Variable Length Data Sequences
• Large-scale, Language-agnostic Discourse Classification of Tweets During COVID-19
• MaskDGA: A Black-box Evasion Technique Against DGA Classifiers and Adversarial Defenses
• Word Shape Matters: Robust Machine Translation with Visual Embedding
• On Early-stage Debunking Rumors on Twitter: Leveraging the Wisdom of Weak Learners
• Learning Invariant Representations of Social Media Users
• Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages
• Learning Representations of Social Media Users
• DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection
• How to Evaluate Word Representations of Informal Domain?
• CRNN: A Joint Neural Network for Redundancy Detection