Chinese Dialogue Intention Classification Based on Multi-Model Ensemble
Manshu Tu,Bing Wang,Xuemin Zhao +2 more
TLDR
This paper defines the DA task on multiple round conversations between humans, and proposes a hybrid neural network-based ensemble model for solving this problem, which can achieve state-of-the-art accuracy on the experimental dialogue corpus.Abstract:
In dialogue systems, understanding the user utterances is crucial for providing appropriate responses. A traditional dialogue act classification (DA) task is to classify each user reply into “ACCEPT, REJECT, PROPOSE, and others”. In contrast, in this paper, we define the DA task on multiple round conversations between humans. The re-defined task is to classify a full dialogue according to the intention of one participant. We term this task as intention classification (IC). We, then, propose a hybrid neural network-based ensemble model for solving this problem. Two novel ensemble schemes are introduced for combining the classification results or features from various classifiers. One is ensembling features from each individual classifier using stacking, and we term this scheme as SFE. The other is adding wrong examples' weight to loss functions of each individual classifier using the AdaBoost scheme, and we term this scheme as MN-Ada. We have empirically examined the performance of the proposed ensemble schemes by using three popular deep neural networks, as well as one newly modified networks for IC. Extensive experiments have been conducted on a Chinese dialogue corpus. Our model can achieve state-of-the-art accuracy on the experimental dialogue corpus.read more
Citations
More filters
Journal ArticleDOI
Intention Detection Based on Siamese Neural Network With Triplet Loss
Fuji Ren,Siyuan Xue +1 more
TL;DR: A triplet training framework based on the multiclass classification approach to conduct the training for the intention detection task is proposed and a Siamese neural network architecture with metric learning is utilized to construct a robust and discriminative utterance feature embedding model.
Patent
Intention recognition method and device applied to intelligent customer service robot
TL;DR: In this article, an intention recognition method and device applied to an intelligent customer service robot is described, which belongs to the technical field of artificial intelligence, and can quickly and accurately identify the intention of the user and guarantee for the robot to accurately answer the user question.
Proceedings ArticleDOI
A Concurrent Intelligent Natural Language Understanding Model for an Automated Inquiry System
TL;DR: The work is intended to tackle a vital field that lies at the intersection of speech processing and natural language processing: Spoken Language Understanding (SLU).
References
More filters
Posted Content
Convolutional Neural Networks for Sentence Classification
TL;DR: In this article, CNNs are trained on top of pre-trained word vectors for sentence-level classification tasks and a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks.
Proceedings ArticleDOI
Hierarchical Attention Networks for Document Classification
TL;DR: Experiments conducted on six large scale text classification tasks demonstrate that the proposed architecture outperform previous methods by a substantial margin.
Proceedings ArticleDOI
A Convolutional Neural Network for Modelling Sentences
TL;DR: A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations.
Journal ArticleDOI
Popular ensemble methods: an empirical study
David W. Opitz,Richard Maclin +1 more
TL;DR: This work suggests that most of the gain in an ensemble's performance comes in the first few classifiers combined; however, relatively large gains can be seen up to 25 classifiers when Boosting decision trees.
Journal ArticleDOI
Multi-class AdaBoost ∗
TL;DR: A new algorithm is proposed that naturally extends the original AdaBoost algorithm to the multiclass case without reducing it to multiple two-class problems and is extremely easy to implement and is highly competitive with the best currently available multi-class classification methods.
Related Papers (5)
Tree-Based Ensemble Multi-Task Learning Method for Classification and Regression
Jaak Simm,Masashi Sugiyama +1 more