Empirical Evaluation of Character-Based Model on Neural Named-Entity Recognition in Indonesian Conversational Texts
share
Despite the long history of named-entity recognition (NER) task in the natural language processing community, previous work rarely studied the task on conversational texts. Such texts are challenging because they contain a lot of word variations which increase the number of out-of-vocabulary (OOV) words. The high number of OOV words poses a difficulty for word-based neural models. Meanwhile, there are plenty of evidence to the effectiveness of character-based neural models in mitigating this OOV problem. Therefore, in this work, we report an empirical evaluation of neural sequence labeling models with character embedding to tackle NER task in Indonesian conversational texts. To our best knowledge, this work is the first to employ neural networks for Indonesian NER and evaluate them on a large and manually annotated datasets. Our experiments show that (1) character models outperform word embedding-only models by up to 4 F_1 points, (2) character models perform better in OOV cases with an improvement of as high as 15 F_1 points, and (3) character models are robust against a very high OOV rate.
READ FULL TEXT