Inducing Multilingual Text Analysis Tools Using Bidirectional Recurrent Neural Networks
This work addresses the challenge of creating multilingual text analysis tools for resource-poor languages, which is incremental as it builds on existing RNN methods with novel cross-lingual adaptations.
The paper tackles the problem of rapidly developing linguistic annotation tools for resource-poor languages by using bidirectional recurrent neural networks with cross-lingual annotation projection, achieving results that demonstrate validity and genericity for inducing POS and super sense taggers.
This work focuses on the rapid development of linguistic annotation tools for resource-poor languages. We experiment several cross-lingual annotation projection methods using Recurrent Neural Networks (RNN) models. The distinctive feature of our approach is that our multilingual word representation requires only a parallel corpus between the source and target language. More precisely, our method has the following characteristics: (a) it does not use word alignment information, (b) it does not assume any knowledge about foreign languages, which makes it applicable to a wide range of resource-poor languages, (c) it provides truly multilingual taggers. We investigate both uni- and bi-directional RNN models and propose a method to include external information (for instance low level information from POS) in the RNN to train higher level taggers (for instance, super sense taggers). We demonstrate the validity and genericity of our model by using parallel corpora (obtained by manual or automatic translation). Our experiments are conducted to induce cross-lingual POS and super sense taggers.