Toward Mention Detection Robustness with Recurrent Neural Networks

By Thien Huu Nguyen, Avirup Sil, Georgiana Dinu, Radu Florian. 2016

38 citations recorded by the source corpus.

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).

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Natural Language Processing for EHR-Based Computational Phenotyping (2018, background): “tion [146], semantic analysis [147], [148], information retrieval [149], [150], entity recognition [151], [152], relation extraction [153], [154], [155], [156], and event detection [157], [158].”
Deep Active Learning for Named Entity Recognition (2017, methodology): “While the use of RNNs tag decoders has been explored (Mesnil et al., 2013; Nguyen et al., 2016; Zhai et al., 2017), we demonstrate for the first time that models using RNNs instead of CRFs for tag decoder can achieve state-of-the-art performance.”
A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, unknown): “Hence, many models consider bi-directional RNNs, such as the Bi-LSTM-CRF-based in [9] and the GRU-based NER model in [103].”
A Survey on Deep Learning for Named Entity Recognition (2018, methodology): “[87] used word2vec toolkit to learn word embeddings for English from the Gigaword corpus augmented with newsgroups”
Text feature extraction based on deep learning: a review (2017, background): “Deep learning technology is applied in common NLP (natural language processing) tasks, such as semantic parsing [43], information retrieval [44, 45], semantic role labeling [46, 47], sentimental analysis [48], question answering [49–52], machine translation [53–56], text classification [57], summari”