Toward Mention Detection Robustness with Recurrent Neural Networks
This work addresses robustness in mention detection for NLP applications, showing incremental improvements in cross-domain and multilingual settings.
The paper tackled the problem of mention detection robustness across domains and languages using recurrent neural networks (RNNs), achieving up to 9% relative error reduction in English and up to 22% in Dutch compared to traditional methods.
One of the key challenges in natural language processing (NLP) is to yield good performance across application domains and languages. In this work, we investigate the robustness of the mention detection systems, one of the fundamental tasks in information extraction, via recurrent neural networks (RNNs). The advantage of RNNs over the traditional approaches is their capacity to capture long ranges of context and implicitly adapt the word embeddings, trained on a large corpus, into a task-specific word representation, but still preserve the original semantic generalization to be helpful across domains. Our systematic evaluation for RNN architectures demonstrates that RNNs not only outperform the best reported systems (up to 9\% relative error reduction) in the general setting but also achieve the state-of-the-art performance in the cross-domain setting for English. Regarding other languages, RNNs are significantly better than the traditional methods on the similar task of named entity recognition for Dutch (up to 22\% relative error reduction).