Moath Al Ali, Bassel Zaity, P. Drobintsev, H. Wannous, Igor Chernoruckiy, A. Filchenkov
We investigate the usage of hybrid convolutional and long- short-term memory neural networks for joint slot filling and intent detection in spoken language understanding. We propose a novel model that combines between convolutional neural networks, for their ability to detect complex features in the input sequences by applying filters to frames of these inputs, and recurrent neural networks taking in account the fact, that they can keep track of the long- and short- term dependencies in the input sequences. We choose to build a model for joint slot filling and intent detection, because we believe, that there is a strong relation between the intent and the semantic slots. A joint model can reflect this relation, figure it out and make use of it to enhance the prediction results. We use the Airline Travel Information System (ATIS) dataset to measure the performance of our model and compare it with the results of other models, as this dataset has become one of the most popular datasets for spoken language understanding problem.
{"title":"Joint Slot Filling and Intent Detection in Spoken Language Understanding by Hybrid CNN-LSTM Model","authors":"Moath Al Ali, Bassel Zaity, P. Drobintsev, H. Wannous, Igor Chernoruckiy, A. Filchenkov","doi":"10.1145/3437802.3437822","DOIUrl":"https://doi.org/10.1145/3437802.3437822","url":null,"abstract":"We investigate the usage of hybrid convolutional and long- short-term memory neural networks for joint slot filling and intent detection in spoken language understanding. We propose a novel model that combines between convolutional neural networks, for their ability to detect complex features in the input sequences by applying filters to frames of these inputs, and recurrent neural networks taking in account the fact, that they can keep track of the long- and short- term dependencies in the input sequences. We choose to build a model for joint slot filling and intent detection, because we believe, that there is a strong relation between the intent and the semantic slots. A joint model can reflect this relation, figure it out and make use of it to enhance the prediction results. We use the Airline Travel Information System (ATIS) dataset to measure the performance of our model and compare it with the results of other models, as this dataset has become one of the most popular datasets for spoken language understanding problem.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133374702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Elastic-search is a distributed search engine which is used to process large amount of data widely. It has a vast number of configuration parameters which are extremely difficult to manually tune to achieve optimal throughput and latency. This paper presents an auto-tuning method to improve the performance of Elastic-search based on random forest and gradient boosting regression trees. By analyzing the working process of Elastic-search, performance-sensitive configuration parameters are selected to establish a machine learning model with high accuracy, so as to accurately predict the performance of Elastic-search with different configurations. With the help of performance prediction, the genetic algorithm finds the optimal configuration of Elastic-search under given system conditions. Three data sets with different sizes and structures are selected for evaluation and the benchmarking tool EsRally tests the performance of index and query operation. Experimental results show that our proposed method can improve the performance by 2.73 times on average and up to 7.02 times compared to the default configuration of Elastic-search.
{"title":"On the Auto-Tuning of Elastic-search based on Machine Learning","authors":"Zhenyan Lu, Chao Chen, Jinhan Xin, Zhibin Yu","doi":"10.1145/3437802.3437828","DOIUrl":"https://doi.org/10.1145/3437802.3437828","url":null,"abstract":"Elastic-search is a distributed search engine which is used to process large amount of data widely. It has a vast number of configuration parameters which are extremely difficult to manually tune to achieve optimal throughput and latency. This paper presents an auto-tuning method to improve the performance of Elastic-search based on random forest and gradient boosting regression trees. By analyzing the working process of Elastic-search, performance-sensitive configuration parameters are selected to establish a machine learning model with high accuracy, so as to accurately predict the performance of Elastic-search with different configurations. With the help of performance prediction, the genetic algorithm finds the optimal configuration of Elastic-search under given system conditions. Three data sets with different sizes and structures are selected for evaluation and the benchmarking tool EsRally tests the performance of index and query operation. Experimental results show that our proposed method can improve the performance by 2.73 times on average and up to 7.02 times compared to the default configuration of Elastic-search.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121441958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Error correction for automatic speech recognition text is an indispensable part of artificial intelligence. At present, speech to text (STT) has widely requirements for the processing of pragmatic information. The text correct rate in STT is the foundation for NLP. Aiming at the text error problems of traditional error correction methods that cannot understand semantics and sentence meanings well. The proposed method used the long and short-term memory neural network (LSTM) algorithm with monte-carlo tree search in this paper. The text error leads to mistake in semantic slot filling for NLP. Therefore, the proposed combined algorithm and optimization method solved the problem by experiments. The results verified the accuracy increased 25% for the telephone inquiry by text error correction.
{"title":"Research on Text Error Correction Algorithm after Automatic Speech Recognition Based on Pragmatic Information","authors":"Yiming Y. Sun, Tianyu Xiao, Chen Yang, Wei Liu","doi":"10.1145/3437802.3437830","DOIUrl":"https://doi.org/10.1145/3437802.3437830","url":null,"abstract":"Error correction for automatic speech recognition text is an indispensable part of artificial intelligence. At present, speech to text (STT) has widely requirements for the processing of pragmatic information. The text correct rate in STT is the foundation for NLP. Aiming at the text error problems of traditional error correction methods that cannot understand semantics and sentence meanings well. The proposed method used the long and short-term memory neural network (LSTM) algorithm with monte-carlo tree search in this paper. The text error leads to mistake in semantic slot filling for NLP. Therefore, the proposed combined algorithm and optimization method solved the problem by experiments. The results verified the accuracy increased 25% for the telephone inquiry by text error correction.","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132221489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper we propose to use generative adversarial network (GAN) for respiratory sound data augmentation. We present a GAN based approach that requires moderate amount of time and computing resources and capable to greatly increase performance of lung sound classification tasks. We also present a conditioned version of GAN, which is flexible and outperforms competitor augmentation methods. As a result, the GAN based augmentation method is able to boost RNN classifier performance by 10-15
{"title":"Generative Adversarial Networks for Respiratory Sound Augmentation","authors":"Kirill Kochetov, A. Filchenkov","doi":"10.1145/3437802.3437821","DOIUrl":"https://doi.org/10.1145/3437802.3437821","url":null,"abstract":"In this paper we propose to use generative adversarial network (GAN) for respiratory sound data augmentation. We present a GAN based approach that requires moderate amount of time and computing resources and capable to greatly increase performance of lung sound classification tasks. We also present a conditioned version of GAN, which is flexible and outperforms competitor augmentation methods. As a result, the GAN based augmentation method is able to boost RNN classifier performance by 10-15","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128806049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
ACM Reference Format: Deguang Peng, Bohui Hao, Xianlun Tang, Yingjie Chen, and Jian Sun. 2020. Learning Long-text Semantic Similarity with Multi-Granularity Semantic Embedding Based on Knowledge Enhancement. In 2020 International Conference on Control, Robotics and Intelligent System (CCRIS 2020), October 27–29, 2020, Xiamen, China. ACM, New York, NY, USA, 7 pages. https://doi.org/10.1145/3437802.3437806
{"title":"Learning Long-text Semantic Similarity with Multi-Granularity Semantic Embedding Based on Knowledge Enhancement","authors":"Deguang Peng, Bohui Hao, Xianlun Tang, Yingjie Chen, Jian Sun, Runzhu Wang","doi":"10.1145/3437802.3437806","DOIUrl":"https://doi.org/10.1145/3437802.3437806","url":null,"abstract":"ACM Reference Format: Deguang Peng, Bohui Hao, Xianlun Tang, Yingjie Chen, and Jian Sun. 2020. Learning Long-text Semantic Similarity with Multi-Granularity Semantic Embedding Based on Knowledge Enhancement. In 2020 International Conference on Control, Robotics and Intelligent System (CCRIS 2020), October 27–29, 2020, Xiamen, China. ACM, New York, NY, USA, 7 pages. https://doi.org/10.1145/3437802.3437806","PeriodicalId":429866,"journal":{"name":"Proceedings of the 2020 1st International Conference on Control, Robotics and Intelligent System","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129725491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：