Character-based Neural Embeddings for Tweet Clustering

03/15/2017

∙

by Svitlana Vakulenko, et al.

∙

WU (Vienna University of Economics and Business)

∙

MODUL Technology GmbH

∙

TU Wien

∙

In this paper we show how the performance of tweet clustering can be improved by leveraging character-based neural networks. The proposed approach overcomes the limitations related to the vocabulary explosion in the word-based models and allows for the seamless processing of the multilingual content. Our evaluation results and code are available on-line at https://github.com/vendi12/tweet2vec_clustering

READ FULL TEXT

Character-based Neural Embeddings for Tweet Clustering

Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English

Character Transformations for Non-Autoregressive GEC Tagging

RetVec: Resilient and Efficient Text Vectorizer

Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?

Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models

Explaining Away Attacks Against Neural Networks

A Comparison of Feature-Based and Neural Scansion of Poetry

Code Repositories

tweet2vec_clustering

Character-based Neural Embeddings for Tweet Clustering

Related Research

Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English

Character Transformations for Non-Autoregressive GEC Tagging

RetVec: Resilient and Efficient Text Vectorizer

Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?

Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models

Explaining Away Attacks Against Neural Networks

A Comparison of Feature-Based and Neural Scansion of Poetry

Code Repositories

tweet2vec_clustering