Open-Domain Name Error Detection using a Multi-Task RNN

By Hao Cheng, Hao Fang, Mari Ostendorf. 2015

48 citations recorded by the source corpus.

Out-of-vocabulary name errors in speech recognition create significant problems for downstream language processing, but the fact that they are rare poses challenges for automatic detection, particularly in an open-domain scenario. To address this problem, a multi-task recurrent neural network language model for sentence-level name detection is proposed for use in combination with out-of-vocabulary word detection. The sentence-level model is also effective for leveraging external text data. Experiments show a 26% improvement in name-error detection F-score over a system using n-gram lexical features.

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

Semi-supervised Multitask Learning for Sequence Labeling (2017, background): “Cheng et al. (2015) described a system for detecting out-of-vocabulary names by also predicting the next word in the sequence.”
When is multitask learning effective? Semantic sequence prediction under varying data conditions (2016, methodology): “Multitask learning has been recently explored by a number of studies, including name error recognition (Cheng et al., 2015), tagging and chunking (Collobert et al.”
Bootstrapping Generators from Noisy Data (2018, background): “, 2016; Plank, 2016), name error detection (Cheng et al., 2015), and machine translation (Luong et al.”
Strong Baselines for Neural Semi-Supervised Learning under Domain Shift (2018, background): “Recent NLP conferences witnessed a “tsunami” of deep learning papers (Manning, 2015), followed by what we call a multi-task learning “wave”: MTL has been successfully applied to a wide range of NLP tasks (Cohn and Specia, 2013; Cheng et al., 2015; Luong et al., 2015; Plank et al., 2016; Fang and Coh”
Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss (2016, background): “A related study is Cheng et al. (2015) who propose a multi-task RNN for named entity recognition by jointly predicting the next token and current to-ken’s name label.”
Multitask learning for semantic sequence prediction under varying data conditions (2016, methodology): “Multitask learning has been recently explored by a number of studies, including name error recognition (Cheng et al., 2015), tagging and chunking (Collobert et al.”
Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices (2019, background): “There are often also performance gains seen from adding auxiliary tasks to improve representation learning objectives [8, 33].”