Toward Mention Detection Robustness with Recurrent Neural Networks
arXiv:1602.07749
Abstract
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).
13 pages, 11 tables, 3 figures
References in corpus (7)
- Efficient Estimation of Word Representations in Vector Space
- ADADELTA: An Adaptive Learning Rate Method
- On the difficulty of training Recurrent Neural Networks
- Frustratingly Easy Domain Adaptation
- A Convolutional Neural Network for Modelling Sentences
- Classifying Relations by Ranking with Convolutional Neural Networks
- Multilingual Language Processing From Bytes
Cited by in corpus (5)
- Deep Active Learning for Named Entity Recognition
- Learning for Biomedical Information Extraction: Methodological Review of Recent Advances
- Neural Entity Reasoner for Global Consistency in NER
- Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures
- Natural Language Processing for EHR-Based Computational Phenotyping