1 |
Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification ...
|
|
|
|
Abstract:
This paper presents a novel approach for multi-lingual sentiment classification in short texts. This is a challenging task as the amount of training data in languages other than English is very limited. Previously proposed multi-lingual approaches typically require to establish a correspondence to English for which powerful classifiers are already available. In contrast, our method does not require such supervision. We leverage large amounts of weakly-supervised data in various languages to train a multi-layer convolutional network and demonstrate the importance of using pre-training of such networks. We thoroughly evaluate our approach on various multi-lingual datasets, including the recent SemEval-2016 sentiment prediction benchmark (Task 4), where we achieved state-of-the-art performance. We also compare the performance of our model trained individually for each language to a variant trained for all languages at once. We show that the latter model reaches slightly worse - but still acceptable - ... : appearing at WWW 2017 - 26th International World Wide Web Conference ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; I.2.7; Information Retrieval cs.IR; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.1703.02504 https://arxiv.org/abs/1703.02504
|
|
BASE
|
|
Hide details
|
|
2 |
Leveraging large amounts of weakly supervised data for multi-language sentiment classification ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Leveraging large amounts of weakly supervised data for multi-language sentiment classification ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|