检索结果-内蒙古大学图书馆

31st Chinese Control And Decision Conference (CCDC)

作者： Wang, Tianzhi Cai, Meng Li, Jianxun Shanghaijiaotong Univ Dept Automat Shanghai 200240 Peoples R China Luoyang Inst Electroopt Equipment AVIC Dept Automat Luoyang 471009 Peoples R China

ISBN: (纸本)9781728101057

sequence-to-sequence neural conversational model generates responses tend to be safe and commonplace(e.g.. I don't know. I'm not sure, I'm sorry), meanwhile the more diversity-promoting and conform responses to queries are not scored higher probably in the N-best lists. We suggest the Maximum Mutual Information(MMI) for diversifying the responses combing with Word Mover's Distances(WMD) for relating the responses to queries as the objective function to rerank N-best lists based on the Seq2Seq with attention mechanism. Experimental results prove that the MMI-WMD model generates more diverse, meaningful, relevant and appropriate responses to queries. The model performs well in human evaluations and BLEU scores in cornell movie dialogue datasets.

关键词： sequence-to-sequence attention mechansim MMI WMD

来源：评论

学校读者我要写书评

暂无评论

Advanced Customer Activity Prediction based on Deep Hierarchic Encoder-Decoders 22

Advanced Customer Activity Prediction based on Deep Hierarch...

引用

22nd International Conference on Control Systems and Computer Science (CSCS)

作者： Damian, Andrei Ionut Tapus, Nicolae Piciu, Laurentiu Turlea, Sergiu Lummetry AI Bucharest Romania Univ Politehn Bucuresti Bucharest Romania

ISBN: (纸本)9781728123318

Product recommender systems and customer profiling techniques have always been a priority in online retail. Recent machine learning research advances and also wide availability of massive parallel numerical computing has enabled various approaches and directions of recommender systems advancement. Worth to mention is the fact that in past years multiple traditional "offline" retail business are gearing more and more towards employing inferential and even predictive analytics both to stock-related problems such as predictive replenishment but also to enrich customer interaction experience. One of the most important areas of recommender systems research and development is that of Deep Learning based models which employ representational learning to model consumer behavioral patterns. Current state of the art in Deep Learning based recommender systems uses multiple approaches ranging from already classical methods such as the ones based on learning product representation vector, to recurrent analysis of customer transactional time-series and up to generative models hosed on adversarial training. Each of these methods has multiple advantages and inherent weaknesses such as inability of understanding the actual user-journey, ability to propose only single product recommendation or top-k product recommendations without prediction of actual next-best-offer. In our work we will present a new and innovative architectural approach of applying state-of-the-art hierarchical multi-module encoder-decoder architecture in order to solve several of current state-of-the-art recommender systems issues. Our approach will also produce by-products such as product need-based segmentation and customer behavioral segmentation all in an end-to-end trainable approach.

关键词： recommender systems sequence-to-sequence hierarchical recurrent encoder-decoder deep learning big-data

来源：评论

学校读者我要写书评

暂无评论

MODALITY ATTENTION FOR END-TO-END AUDIO-VISUAL SPEECH RECOGNITION 44

MODALITY ATTENTION FOR END-TO-END AUDIO-VISUAL SPEECH RECOGN...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Zhou, Pan Yang, Wenwen Chen, Wei Wang, Yanfeng Jia, Jia Tsinghua Univ Dept Comp Sci & Technol Beijing Peoples R China Sogou Inc Voice Interact Technol Ctr Beijing Peoples R China

ISBN: (纸本)9781479981311

Audio-visual speech recognition ( AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance. Our method is realized using state-of-the-art sequence-to-sequence ( Seq2seq) architectures. Experimental results show that relative improvements from 2% up to 36% over the auditory modality alone are obtained depending on the different signal-to-noise-ratio ( SNR). Compared to the traditional feature concatenation methods, our proposed approach can achieve better recognition performance under both clean and noisy conditions. We believe modality attention based end-to-end method can be easily generalized to other multimodal tasks with correlated information.

关键词： multimodal attention audio-visual speech recognition lipreading sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines 16th

Automatic Acrostic Couplet Generation with Three-Stage Neura...

引用

16th Pacific Rim International Conference on Artificial Intelligence (PRICAI)

作者： Fan, Haoshen Wang, Jie Zhuang, Bojin Wang, Shaojun Xiao, Jing Univ Sci & Technol China Hefei Peoples R China Ping An Technol Shenzhen Co Ltd Shenzhen Peoples R China

ISBN: (纸本)9783030299088;9783030299071

As one of the quintessence of Chinese traditional culture, couplet compromises two syntactically symmetric clauses equal in length, namely, an antecedent and subsequent clause. Moreover, corresponding characters and phrases at the same position of the two clauses are paired with each other under certain constraints of semantic and/or syntactic relatedness. Automatic couplet generation is recognized as a challenging problem even in the Artificial Intelligence field. In this paper, we comprehensively study on automatic generation of acrostic couplet with the first characters defined by users. The complete couplet generation is mainly divided into three stages, that is, antecedent clause generation pipeline, subsequent clause generation pipeline and clause re-ranker. To realize semantic and/or syntactic relatedness between two clauses, attention-based sequence-to-sequence (S2S) neural network is employed. Moreover, to provide diverse couplet candidates for re-ranking, a cluster-based beam search approach is incorporated into the S2S network. Both BLEU metrics and human judgments have demonstrated the effectiveness of our proposed method. Eventually, a mini-program based on this generation system is developed and deployed on Wechat for real users.

关键词： Natural language generation Couplet generation sequence-to-sequence Language model Attention

来源：评论

学校读者我要写书评

暂无评论

Attention-based Surgical Phase Boundaries Detection in Laparoscopic Videos 6

Attention-based Surgical Phase Boundaries Detection in Lapar...

引用

6th Annual Conference on Computational Science and Computational Intelligence (CSCI)

作者： Namazi, Babak Sankaranarayanan, Ganesh Devarajan, Venkat Univ Texas Arlington Dept Elect Engn Arlington TX 76019 USA Baylor Univ Med Ctr Dept Surg Dallas TX 75246 USA

ISBN: (纸本)9781728155845

A new deep learning-based method is proposed for identifying the boundaries of all surgical phases in a laparoscopic video. The model is designed based on the sequence-to-sequence architecture with an attention mechanism, to map the extracted visual features to the frame numbers of the beginning and the ending of each phase. The main novelty is that the alignment vectors for each phase are taken as the outputs, and are trained directly to select the indices. We evaluated our model using a large publicly available dataset of laparoscopic cholecystectomy procedure and obtained the Mean Absolute Error (MAE) of 48 seconds.

关键词： surgical phase detection sequence-to-sequence attention mechanism RNN CNN

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Automatic Diacritics Restoration in Romanian 15

Deep Learning for Automatic Diacritics Restoration in Romani...

引用

IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP)

作者： Nutu, Maria Lorincz, Beata Stan, Adriana Tech Univ Cluj Napoca Commun Dept Cluj Napoca Romania Babes Bolyai Univ Dept Comp Sci Cluj Napoca Romania

ISBN: (纸本)9781728149141

In this paper we address the issue of automatic diacritics restoration (ADR) for Romanian using deep learning strategies. We compare 6 separate architectures with various mixtures of recurrent and convolutional layers. The input consists in sequences of consecutive words stripped of their diacritic symbols. The network's task is to learn to restore the diacritics for the entire sequence. No additional linguistic or semantic information is used as input to the networks. The best results were obtained with a CNN-based architecture and achieved an accuracy of 97% at word level. At diacritic-level the accuracy of the same architecture is 89%.

关键词： automatic diacritics restoration deep neural networks LSTM CNN sequence-to-sequence Romanian

来源：评论

学校读者我要写书评

暂无评论

A Novel Chinese Sign Language Recognition Method Based on Keyframe-Centered Clips

引用

IEEE SIGNAL PROCESSING LETTERS 2018年第3期25卷 442-446页

作者： Huang, Shiliang Mao, Chensi Tao, Jinxu Ye, Zhongfu Univ Sci & Technol China Dept Elect Engn & Informat Sci Hefei 230027 Anhui Peoples R China Natl Engn Lab Speech & Language Informat Proc Hefei 230027 Anhui Peoples R China

Isolated sign language recognition (SLR) is a long-standing research problem. The existing methods consider inclusively ambiguous data to represent a sign and ignore the fact that only scarce key information can represent the sign efficiently since most information are redundant. Furthermore, inclusion of redundant information may result in inefficiency and difficulty in modeling the long-term dependency for SLR. This letter delivers a novel sequence-to-sequence learning method based on keyframe centered clips (KCCs) for Chinese SLR. Different from conventional methods, only key information is considered to represent a sign significantly. The frames-to-word task is transformed into a KCCs-to-subwords task successfully, to allow for different attention in the input data. The empirical results of the proposed method outperform significantly the state-of-the-art SLR systems on our dataset containing 310 Chinese sign language words.

关键词： Efficient keyframe centered clip (KCC) key information sequence-to-sequence sign language recognition (SLR)

来源：评论

学校读者我要写书评

暂无评论

Attention for Implicit Discourse Relation Recognition 11

Attention for Implicit Discourse Relation Recognition

引用

11th International Conference on Language Resources and Evaluation (LREC)

作者： Cianflone, Andre Kosseim, Leila Concordia Univ Dept Engn & Comp Sci Montreal PQ Canada

ISBN: (纸本)9791095546009

Implicit discourse relation recognition remains a challenging task as state-of-the-art approaches reach F1 scores ranging from 9.95% to 37.67% on the 2016 CoNLL shared task. In our work, we explore the use of a neural network which exploits the strong correlation between pairs of words across two discourse arguments that implicitly signal a discourse relation. We present a novel approach to Implicit Discourse Relation Recognition that uses an encoder-decoder model with attention. Our approach is based on the assumption that a discourse argument is "generated" from a previous argument and conditioned on a latent discourse relation, which we detect. Experiments show that our model achieves an F1 score of 38.25% on fine-grained classification, outperforming previous approaches and performing comparatively with state-of-the-art on coarse-grained classification, while computing alignment parameters without the need for additional pooling and fully connected layers.

关键词： discourse relation recognition sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

Mongolian Grapheme to Phoneme Conversion by Using Hybrid Approach 7th

Mongolian Grapheme to Phoneme Conversion by Using Hybrid App...

引用

7th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC

作者： Liu, Zhinan Bao, Feilong Gao, Guanglai Suburi Inner Mongolia Univ Coll Comp Sci Hohhot 010021 Peoples R China Inner Mongolia Publ Secur Dept Hohhot 010021 Peoples R China

ISBN: (纸本)9783319994956;9783319994949

Grapheme to phoneme (G2P) conversion is the assignment of converting word to its pronunciation. It has important applications in text-to-speech (TTS), speech recognition and sounds-like queries in textual databases. In this paper, we present the first application of sequence-to-sequence (Seq2Seq) Long Short-Term Memory (LSTM) model with the attention mechanism for Mongolian G2P conversion. Furthermore, we propose a novel hybrid approach of combining rules with Seq2Seq LSTM model for Mongolian G2P conversion, and implement the Mongolian G2P conversion system. The experimental results show that: Adopting Seq2Seq LSTM model can obtain better performance than traditional methods of Mongolian G2P conversion, and the hybrid approach further improves G2P conversion performance. The word error rate (WER) relatively reduces by 10.8% and the phoneme error rate (PER) approximately reduces by 1.6% through comparing with the Mongolian G2P conversion method being used based on the joint-sequence models, which completely meets the practical requirements of Mongolian G2P conversion.

关键词： Mongolian Grapheme-to-phoneme sequence-to-sequence LSTM

来源：评论

学校读者我要写书评

暂无评论

Towards Temporal Modelling of Categorical Speech Emotion Recognition 19

Towards Temporal Modelling of Categorical Speech Emotion Rec...

引用

19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018)

作者： Han, Wenjing Ruan, Huabin Chen, Xiaomin Wang, Zhixiang Li, Haifeng Schuller, Bjoern Samsung Res Inst China Beijing SRC B Beijing Peoples R China Tsinghua Univ Prot Res Technol Ctr Beijing Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin Heilongjiang Peoples R China Imperial Coll London GLAM London England Univ Augsburg ZD B Chair Embedded Intelligence Hlth Care & Well Augsburg Germany

ISBN: (纸本)9781510872219

To model the categorical speech emotion recognition task in a temporal manner, the first challenge arising is how to transfer the categorical label for each utterance into a label sequence. To settle this, we make a hypothesis that an utterance is consisting of emotional and non-emotional segments, and these non-emotional segments correspond to silent regions, short pauses, transitions between phonemes;unvoiced phonemes, etc. With this hypothesis, we propose to treat an utterance's label sequence as a chain of two states: the emotional state denoting the emotional frame and Null denoting the non-emotional frame. Then, we exploit a recurrent neural network based connectionist temporal classification model to automatically label and align an utterance's emotional segments with emotional labels, while non-emotional segments with Nulls. Experimental results on the IEMOCAP corpus validate our hypothesis and also demonstrate the effectiveness of our proposed method compared to the state-of-the-art algorithms.

关键词： speech emotion recognition recurrent neural network connectionist temporal classification sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：