LSTM-CRF Models for Named Entity Recognition
TLDR
This study proposes L STM conditional random fields (LSTM-CRF), an LSTMbased RNN model that uses output-label dependencies with transition features and a CRF-like sequence-level objective function to attain state-of-the-art performance for named entity recognition.Abstract:
Recurrent neural networks (RNNs) are a powerful model for sequential data. RNNs that use long short-term memory (LSTM) cells have proven effective in handwriting recognition, language modeling, speech recognition, and language comprehension tasks. In this study, we propose LSTM conditional random fields (LSTM-CRF); it is an LSTMbased RNN model that uses output-label dependencies with transition features and a CRF-like sequence-level objective function. We also propose variations to the LSTM-CRF model using a gate recurrent unit (GRU) and structurally constrained recurrent network (SCRN). Empirical results reveal that our proposed models attain state-of-the-art performance for named entity recognition. key words: LSTM-CRF, LSTM RNN, recurrent neural network, name entity recognitionread more
Citations
More filters
Journal ArticleDOI
Information extraction from scientific articles: a survey
TL;DR: In this article, the authors present the overall progress concerning automatic information extraction from scientific articles and classify the information insights extracted from scientific documents into two broad categories i.e. metadata and key-insights.
Journal ArticleDOI
Knowledge graph based on domain ontology and natural language processing technology for Chinese intangible cultural heritage
TL;DR: The knowledge graph for ICH could foster support for organization, management and protection of the intangible cultural heritage knowledge, and the public can also obtain the ICH knowledge quickly and discover the linked knowledge.
Journal ArticleDOI
Named Entity Recognition and Relation Extraction: State-of-the-Art
TL;DR: In this paper, the authors present an overview of approaches that can be applied to extract key insights from textual data in a structured way, namely, named entity recognition and relation extraction.
Journal ArticleDOI
Semantic vector learning for natural language understanding
TL;DR: This work proposes a framework that learns to embed semantic correspondence between text and its extracted semantic knowledge, called semantic frame, and demonstrates three key areas where the embedding model can be effective: visualization, distance based semantic search, similarity-based intent classification and re-ranking.
Journal ArticleDOI
A Deep Machine Learning Method for Concurrent and Interleaved Human Activity Recognition.
TL;DR: This paper proposes a two-phase hybrid deep machine learning approach using bi-directional Long-Short Term Memory (BiLSTM) and Skip-Chain Conditional random field (SCCRF) to recognize the complex activity.
References
More filters
Proceedings ArticleDOI
Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation
Kyunghyun Cho,Bart van Merriënboer,Caglar Gulcehre,Dzmitry Bahdanau,Fethi Bougares,Holger Schwenk,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio +8 more
TL;DR: In this paper, the encoder and decoder of the RNN Encoder-Decoder model are jointly trained to maximize the conditional probability of a target sequence given a source sequence.
Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
Proceedings ArticleDOI
Speech recognition with deep recurrent neural networks
TL;DR: This paper investigates deep recurrent neural networks, which combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs.
Posted Content
Improving neural networks by preventing co-adaptation of feature detectors
TL;DR: The authors randomly omits half of the feature detectors on each training case to prevent complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors.