检索结果-内蒙古大学图书馆

35th IEEE/ACM International Conference on Automated Software Engineering (ASE)

作者： Ding, Yangruibo Ray, Baishakhi Devanbu, Premkumar Hellendoorn, Vincent J. Columbia Univ New York NY 10027 USA Univ Calif Davis Davis CA 95616 USA

ISBN: (纸本)9781450367684

Machine Learning models from other fields, like Computational Linguistics, have been transplanted to Software Engineering tasks, often quite successfully. Yet a transplanted model's initial success at a given task does not necessarily mean it is well-suited for the task. In this work, we examine a common example of this phenomenon: the conceit that "software patching is like language translation". We demonstrate empirically that there are subtle, but critical distinctions between sequence-to-sequence models and translation model: while program repair benefits greatly from the former, general modeling architecture, it actually suffers from design decisions built into the latter, both in terms of translation accuracy and diversity. Given these findings, we demonstrate how a more principled approach to model design, based on our empirical findings and general knowledge of software development, can lead to better solutions. Our findings also lend strong support to the recent trend towards synthesizing edits of code conditional on the buggy context, to repair bugs. We implement such models ourselves as "proof-of-concept" tools and empirically confirm that they behave in a fundamentally different, more effective way than the studied translation-based architectures. Overall, our results demonstrate the merit of studying the intricacies of machine learned models in software engineering: not only can this help elucidate potential issues that may be overshadowed by increases in accuracy;it can also help innovate on these models to raise the state-of-the-art further. We will publicly release our replication data and materials at https://***/ARiSE- Lab/Patch-as-translation.

关键词： neural machine translation big code sequence-to-sequence model automated program repair

来源：评论

学校读者我要写书评

暂无评论

Question Generation Through Transfer Learning 33rd

Question Generation Through Transfer Learning

引用

33rd International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE)

作者： Liao, Yin-Hsiang Koh, Jia-Ling Natl Taiwan Normal Univ Dept Comp Sci & Informat Engn Taipei Taiwan

ISBN: (纸本)9783030557881;9783030557898

An automatic question generation (QG) system aims to produce questions from a text, such as a sentence or a paragraph. Traditional approaches are mainly based on heuristic, hand-crafted rules to transduce a declarative sentence to a related interrogative sentence. However, creating such a set of rules requires deep linguistic knowledge and most of these rules are language-specific. Although a data-driven approach reduces the participation of linguistic experts, to get sufficient labeled data for QG model training is still a difficult task. In this paper, we applied a neural sequence-to-sequence pointer-generator network with various transfer learning strategies to capture the underlying information of making a question, on a target domain with rare training pairs. Our experiment demonstrates the viability of domain adaptation in QG task. We also show the possibility that transfer learning is helpful in a semi-supervised approach when the amount of training pairs in the target QG dataset is not large enough.

关键词： Question generation sequence-to-sequence model Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Personalized Query Suggestions 20

Personalized Query Suggestions

引用

43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Zhong, Jianling Guo, Weiwei Gao, Huiji Long, Bo LinkedIn Corp San Francisco CA 94105 USA

ISBN: (纸本)9781450380164

With the exponential growth of information on the internet, users have been relying on search engines for finding the precise documents. However, user queries are often short. The inherent ambiguity of short queries imposes great challenges for search engines to understand user intent. Query suggestion is one key technique for search engines to augment user queries so that they can better understand user intent. In the past, query suggestions have been relying on either term-frequency-based methods with little semantic understanding of the query, or word-embedding-based methods with little personalization efforts. Here, we present a sequence-to-sequence-model-based query suggestion framework that is capable of modeling structured, personalized features and unstructured query texts naturally. This capability opens up the opportunity to better understand query semantics and user intent at the same time. As the largest professional network, LINKEDIN has the advantage of utilizing a rich amount of accurate member profile information to personalize query suggestions. We applied this framework in the LINKEDIN production traffic and showed that personalized query suggestions significantly improved member search experience as measured by key business metrics at LINKEDIN.

关键词： Query suggestion sequence-to-sequence model Personalization Deep learning model deployment

来源：评论

学校读者我要写书评

暂无评论

High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency 21

High Quality Streaming Speech Synthesis with Low, Sentence-L...

引用

Interspeech Conference

作者： Ellinas, Nikolaos Vamvoukakis, Georgios Markopoulos, Konstantinos Chalamandaris, Aimilios Maniati, Georgia Kakoulidis, Panos Raptis, Spyros Sung, June Sig Park, Hyoungmin Tsiakoulis, Pirros Samsung Elect Innoet Attica Greece Samsung Elect Mobile Commun Business Suwon Gyeonggi Do South Korea

ISBN: (纸本)9781713820697

This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based sequence-to-sequence acoustic model and the LPCNet vocoder for waveform generation. An acoustic model architecture that adopts modules from both the Tacotron 1 and 2 models is proposed, while stability is ensured by using a recently proposed purely location-based attention mechanism, suitable for arbitrary sentence length generation. During inference, the decoder is unrolled and acoustic feature generation is performed in a streaming manner, allowing for a nearly constant latency which is independent from the sentence length. Experimental results show that the acoustic model can produce feature sequences with minimal latency about 31 times faster than real-time on a computer CPU and 6.5 times on a mobile CPU, enabling it to meet the conditions required for real-time applications on both devices. The full end-to-end system can generate almost natural quality speech, which is verified by listening tests.

关键词： Text-to-speech synthesis real-time sequence-to-sequence model streaming inference end-to-end TTS

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMER-BASED TEXT-TO-SPEECH WITH WEIGHTED FORCED ATTENTION

TRANSFORMER-BASED TEXT-TO-SPEECH WITH WEIGHTED FORCED ATTENT...

引用

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

作者： Okamoto, Takuma Toda, Tomoki Shiga, Yoshinori Kawai, Hisashi Natl Inst Informat & Commun Technol Tokyo Japan Nagoya Univ Informat Technol Ctr Nagoya Aichi Japan

ISBN: (纸本)9781509066315

This paper investigates state-of-the-art Transformer- and FastSpeech-based high-fidelity neural text-to-speech (TTS) with full-context label input for pitch accent languages. The aim is to realize faster training than conventional Tacotron-based models. Introducing phoneme durations into Tacotron-based TTS models improves both synthesis quality and stability. Therefore, a Transformer-based acoustic model with weighted forced attention obtained from phoneme durations is proposed to improve synthesis accuracy and stability, where both encoder-decoder attention and forced attention are used with a weighting factor. Furthermore, FastSpeech without a duration predictor, in which the phoneme durations are predicted by another conventional model, is also investigated. The results of experiments using a Japanese female corpus and the WaveGlow vocoder indicate that the proposed Transformer using forced attention with a weighting factor of 0.5 outperforms other models, and removing the duration predictor from FastSpeech improves synthesis quality, although the proposed weighted forced attention does not improve synthesis stability.

关键词： Speech synthesis sequence-to-sequence model Transformer forced alignment weighted forced attention

来源：评论

学校读者我要写书评

暂无评论

Text-to-SQL Generation for Question Answering on Electronic Medical Records 20

Text-to-SQL Generation for Question Answering on Electronic ...

引用

29th World Wide Web Conference (WWW)

作者： Wang, Ping Shi, Tian Reddy, Chandan K. Virginia Tech Dept Comp Sci Arlington VA 22203 USA

ISBN: (纸本)9781450370233

Electronic medical records (EMR) contain comprehensive patient information and are typically stored in a relational database with multiple tables. Effective and efficient patient information retrieval from EMR data is a challenging task for medical experts. Question-to-SQL generation methods tackle this problem by first predicting the SQL query for a given question about a database, and then, executing the query on the database. However, most of the existing approaches have not been adapted to the healthcare domain due to a lack of healthcare Question-to-SQL dataset for learning models specific to this domain. In addition, wide use of the abbreviation of terminologies and possible typos in questions introduce additional challenges for accurately generating the corresponding SQL queries. In this paper, we tackle these challenges by developing a deep learning based TRanslate-Edit model for Question-to-SQL (TREQS) generation, which adapts the widely used sequence-to-sequence model to directly generate the SQL query for a given question, and further performs the required edits using an attentive-copying mechanism and task-specific look-up tables. Based on the widely used publicly available electronic medical database, we create a new large-scale Question-SQL pair dataset, named MIMICSQL, in order to perform the Question-to-SQL generation task in healthcare domain. An extensive set of experiments are conducted to evaluate the performance of our proposed model on MIMICSQL. Both quantitative and qualitative experimental results indicate the flexibility and efficiency of our proposed method in predicting condition values and its robustness to random questions with abbreviations and typos.

关键词： sequence-to-sequence model attention mechanism pointer-generator network electronic medical records SQL query

来源：评论

学校读者我要写书评

暂无评论

EFFECT OF CHOICE OF PROBABILITY DISTRIBUTION, RANDOMNESS, AND SEARCH METHODS FOR ALIGNMENT modelING IN sequence-TO-sequence TEXT-TO-SPEECH SYNTHESIS USING HARD ALIGNMENT

EFFECT OF CHOICE OF PROBABILITY DISTRIBUTION, RANDOMNESS, AN...

引用

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

作者： Yasuda, Yusuke Wang, Xin Yamagishi, Junichi Natl Inst Informat Chiyoda City Tokyo Japan SOKENDAI Miura Dist Kanagawa Japan

ISBN: (纸本)9781509066315

sequence-to-sequence text-to-speech (TTS) is dominated by soft-attention-based methods. Recently, hard-attention-based methods have been proposed to prevent fatal alignment errors, but their sampling method of discrete alignment is poorly investigated. This research investigates various combinations of sampling methods and probability distributions for alignment transition modeling in a hard-alignment-based sequence-to-sequence TTS method called SSNT-TTS. We clarify the common sampling methods of discrete variables including greedy search, beam search, and random sampling from a Bernoulli distribution in a more general way. Furthermore, we introduce the binary Concrete distribution to model discrete variables more properly. The results of a listening test shows that deterministic search is more preferable than stochastic search, and the binary Concrete distribution is robust with stochastic search for natural alignment transition.

关键词： speech synthesis deep learning sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Patching as translation: the data and the metaphor 20

Patching as translation: the data and the metaphor

引用

Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering

作者： Yangruibo Ding Baishakhi Ray Premkumar Devanbu Vincent J. Hellendoorn Columbia University University of California

ISBN: (纸本)9781450367684

Machine Learning models from other fields, like Computational Linguistics, have been transplanted to Software Engineering tasks, often quite successfully. Yet a transplanted model's initial success at a given task does not necessarily mean it is well-suited for the task. In this work, we examine a common example of this phenomenon: the conceit that "software patching is like language translation". We demonstrate empirically that there are subtle, but critical distinctions between sequence-to-sequence models and translation model: while program repair benefits greatly from the former, general modeling architecture, it actually suffers from design decisions built into the latter, both in terms of translation accuracy and diversity. Given these findings, we demonstrate how a more principled approach to model design, based on our empirical findings and general knowledge of software development, can lead to better solutions. Our findings also lend strong support to the recent trend towards synthesizing edits of code conditional on the buggy context, to repair bugs. We implement such models ourselves as "proof-of-concept" tools and empirically confirm that they behave in a fundamentally different, more effective way than the studied translation-based architectures. Overall, our results demonstrate the merit of studying the intricacies of machine learned models in software engineering: not only can this help elucidate potential issues that may be overshadowed by increases in accuracy; it can also help innovate on these models to raise the state-of-the-art further. We will publicly release our replication data and materials at https://***/ARiSE-Lab/Patch-as-translation.

关键词： big code automated program repair neural machine translation sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Overview of the sixth dialog system technology challenge: DSTC6

引用

COMPUTER SPEECH AND LANGUAGE 2019年 55卷 1-25页

作者： Horia, Chiori Perez, Julien Higashinakac, Ryuichiro Horia, Takaaki Boureau, Y-Lan Inabae, Michimasa Tsunomorif, Yuiko Takahashig, Tetsuro Yoshinoh, Koichiro Kim, Seokhwan Mitsubishi Elect Res Lab Cambridge MA USA Naver Labs Europe Grenoble France NTT Corp NTT Media Intelligence Labs 1-1 Hikarinooka Yokosuka Kanagawa 2390847 Japan Facebook AI Res New York NY USA Hiroshima City Univ Grad Sch Informat Sci Asaminami Ku 3-4-1 Ozukahigashi Hiroshima 7313194 Japan NTT DOCOMO INC Serv Dev Grp Minato Ku 4-5 Akasaka 2 Chome Tokyo 1079992 Japan Fujitsu Labs LTD AI Deployment Project Nakahara Ku 4-1-1 Kamikodanaka Kawasaki Kanagawa 2118588 Japan Nara Inst Sci & Technol Nara Japan Adobe Res San Jose CA USA

This paper describes the experimental setups and the evaluation results of the sixth Dialog System Technology Challenges (DSTC6) aiming to develop end-to-end dialogue systems. Neural network models have become a recent focus of investigation in dialogue technologies. Previous models required training data to be manually annotated with word meanings and dialogue states, but end-to-end neural network dialogue systems learn to directly output natural-language system responses without needing training data to be manually annotated. Thus, this approach allows us to scale up the size of training data and cover more dialog domains. In addition, dialogue systems require a meta-function to avoid deploying inappropriate responses generated by themselves. To challenge such issues, the DSTC6 consists of three tracks, (1). End-to-End Goal Oriented dialogue Learning to select system responses, (2). End-to-End Conversation modeling to generate system responses using Natural Language Generation (NLG) and (3). Dialogue Breakdown Detection. Since each domain has different issues to be addressed to develop dialogue systems, we targeted restaurant retrieval dialogues to fill slot-value in Track 1, customer services on Twitter by combining goal-oriented dialogues and ChitChat in Track 2 and human-machine dialogue data for ChitChat in Track 3. DSTC6 had 141 people declaring their interests and 23 teams submitted their final results. 18 scientific papers were presented in the wrap-up workshop. We find the blending end-to-end trainable models associated to meaningful prior knowledge performs the best for the restaurant retrieval for Track 1. Indeed, Hybrid Code Network and Memory Network have been the best models for this task. In Track 2, 78.5% of the system responses automatically generated by the best system were rated better than acceptable by humans and this achieves 89% of the number of the human responses rated in the same class. In Track3, the dialogue breakdown detection technolog

关键词： DSTC End-to-end dialogue system Conversation model sequence-to-sequence model Natural Language Generation Dialogue breakdown

来源：评论

学校读者我要写书评

暂无评论

Multistep speed prediction on traffic networks: A deep learning approach considering spatio-temporal dependencies

引用

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES 2019年第Aug.期105卷 297-322页

作者： Zhang, Zhengchao Li, Meng Lin, Xi Wang, Yinhai He, Fang Tsinghua Univ Dept Civil Engn Beijing 100084 Peoples R China Tsinghua Univ Tsinghua Daimler Joint Res Ctr Sustainable Transp Beijing 100084 Peoples R China Univ Washington Dept Civil & Environm Engn Seattle WA 98195 USA Tsinghua Univ Dept Ind Engn Beijing 100084 Peoples R China

Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial correlations in multistep traffic-condition prediction, we propose a novel deep learning framework named attention graph convolutional sequence-to-sequence model (AGC-Seq2Seq). In the proposed deep learning framework, spatial and temporal dependencies are modeled through the Seq2Seq model and graph convolution network separately, and the attention mechanism along with a newly designed training method based on the Seq2Seq architecture is proposed to overcome the difficulty in multistep prediction and further capture the temporal heterogeneity of traffic pattern. We conduct numerical tests to compare AGC-Seq2Seq with other benchmark models using two real-world datasets. The results indicate that our model yields the best prediction performance in terms of various prediction error measures. Furthermore, the variations of spatio-temporal correlations of traffic conditions under different perdition steps and road segments are revealed.

关键词： Traffic forecasting Deep learning Attention mechanism Graph convolution Multistep prediction sequence-to-sequence model

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：