检索结果-内蒙古大学图书馆

Syntax-aware data augmentation for neural machine translation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Duan, Sufeng Zhao, Hai Zhang, Dongdong Wang, Rui Department of Computer Science and Engineering Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence Ai Institute Shanghai Jiao Tong University Microsoft Research Asia Beijing China Kyoto Japan

Data augmentation is an effective performance enhancement in neural machine translation (NMT) by generating additional bilin-gual data. In this paper, we propose a novel data augmentation enhancement strat-egy for neural machine translation. Differ-ent from existing data augmentation methods which simply choose words with the same probability across different sentences for mod-ification, we set sentence-specific probabil-ity for word selection by considering their roles in sentence. We use dependency parse tree of input sentence as an effective clue to determine selecting probability for ev-ery words in each sentence. Our proposed method is evaluated on WMT14 English-to-German dataset and IWSLT14 German-to-English dataset. The result of extensive experiments show our proposed syntax-aware data augmentation method may effectively boost existing sentence-independent methods for sig-nificant translation performance improvement. Copyright © 2020, The Authors. All rights reserved.

关键词： Neural machine translation

Improving context modelling in multimodal dialogue generation 11

学校读者我要写书评

暂无评论

Improving context modelling in multimodal dialogue generatio...

11th International Natural Language Generation Conference, INLG 2018

作者： Agarwal, Shubham Dušek, Ondrej Konstas, Ioannis Rieser, Verena Interaction Lab Department of Computer Science Heriot-Watt University Edinburgh United Kingdom Adeptmind Inc. Toronto Canada

ISBN: (纸本)9781948087865

In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system. Our work is based on the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017) in the fashion domain. We introduce a multimodal extension to the Hierarchical Recurrent Encoder-Decoder (HRED) model and show that this extension outperforms strong baselines in terms of text-based similarity metrics. We also showcase the shortcomings of current vision and language models by performing an error analysis on our system’s output. © 2018 Association for Computational Linguistics.

关键词： Speech processing

A new and more informative subtyping scheme for breast cancer based on co-expression of metabolic genes

学校读者我要写书评

暂无评论

Genes & Diseases 2025年

作者： Chongren Pei Yuzhe Zhang Jun Xiao Qing He Wenyong Zhang Ying Xu Systems Biology Lab for Metabolic Reprogramming Department of Human Cell Biology and Genetics School of Medicine Southern University of Science and Technology Shenzhen Guangdong 518055 China The First Laboratory of Cancer Institute The First Hospital of China Medical University Shenyang Liaoning 110001 China Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun Jilin 130012 China The Third People's Hospital of Shenzhen Shenzhen Guangdong 518112 China School of Medicine Southern University of Science and Technology Shenzhen Guangdong 518055 China

A Knowledge-Grounded Multimodal Search-Based Conversational Agent 2

学校读者我要写书评

暂无评论

A Knowledge-Grounded Multimodal Search-Based Conversational ...

2nd International Workshop on Search-Oriented Conversational AI, SCAI 2018

作者： Agarwal, Shubham Dušek, Ondřej Konstas, Ioannis Rieser, Verena The Interaction Lab Department of Computer Science Heriot-Watt University Edinburgh United Kingdom Adeptmind Inc. Toronto Canada

ISBN: (纸本)9781948087759

Multimodal search-based dialogue is a challenging new task: It extends visually grounded question answering systems into multi-turn conversations with access to an external database. We address this new challenge by learning a neural response generation system from the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017). We introduce a knowledge-grounded multimodal conversational model where an encoded knowledge base (KB) representation is appended to the decoder input. Our model substantially outperforms strong baselines in terms of text-based similarity measures (over 9 BLEU points, 3 of which are solely due to the use of additional information from the KB). © 2018 Association for Computational Linguistics

关键词： Knowledge based systems

Capsule-Transformer for Neural Machine Translation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Duan, Sufeng Cao, Juncheng Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

Transformer hugely benefits from its key design of the multi-head self-attention network (SAN), which extracts information from various perspectives through transforming the given input into different subspaces. However, its simple linear transformation aggregation strategy may still potentially fail to fully capture deeper contextualized information. In this paper, we thus propose the capsule-Transformer, which extends the linear transformation into a more general capsule routing algorithm by taking SAN as a special case of capsule network. So that the resulted capsule-Transformer is capable of obtaining a better attention distribution representation of the input sequence via information aggregation among different heads and words. Specifically, we see groups of attention weights in SAN as low layer capsules. By applying the iterative capsule routing algorithm they can be further aggregated into high layer capsules which contain deeper contextualized information. Experimental results on the widely-used machine translation datasets show our proposed capsule-Transformer outperforms strong Transformer baseline significantly. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

Head-Driven Phrase Structure Grammar Parsing on Penn Treebank

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhou, Junru Zhao, Hai Department of Computer Science and Engineering Key Lab of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China

Head-driven phrase structure grammar (HPSG) enjoys a uniform formalism representing rich contextual syntactic and even semantic meanings. This paper makes the first attempt to formulate a simplified HPSG by integrating constituent and dependency formal representations into head-driven phrase structure. Then two parsing algorithms are respectively proposed for two converted tree representations, division span and joint span. As HPSG encodes both constituent and dependency structure information, the proposed HPSG parsers may be regarded as a sort of joint decoder for both types of structures and thus are evaluated in terms of extracted or converted constituent and dependency parsing trees. Our parser achieves new state-of-the-art performance for both parsing tasks on Penn Treebank (PTB) and Chinese Penn Treebank, verifying the effectiveness of joint learning constituent and dependency structures. In details, we report 96.33 F1 of constituent parsing and 97.20% UAS of dependency parsing on PTB. Copyright © 2019, The Authors. All rights reserved.

关键词： Computational grammars

Graph-to-sequence neural machine translation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Duan, Sufeng Zhao, Hai Wang, Rui Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Kyoto Japan

Neural machine translation (NMT) usually works in a seq2seq learning way by viewing either source or target sentence as a linear sequence of words, which can be regarded as a special case of graph, taking words in the sequence as nodes and relationships between words as edges. In the light of the current NMT models more or less capture graph information among the sequence in a latent way, we present a graph-to-sequence model facilitating explicit graph information capturing. In detail, we propose a graph-based SAN-based NMT model called Graph-Transformer by capturing information of subgraphs of different orders in every layers. Subgraphs are put into different groups according to their orders, and every group of subgraphs respectively reflect different levels of dependency between words. For fusing subgraph representations, we empirically explore three methods which weight different groups of subgraphs of different orders. Results of experiments on WMT14 English-German and IWSLT14 German-English show that our method can effectively boost the Transformer with an improvement of 1.1 BLEU points on WMT14 English-German dataset and 1.0 BLEU points on IWSLT14 German-English dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Neural machine translation

A labanotation based ontology for representing Vietnamese folk dances 3

学校读者我要写书评

暂无评论

A labanotation based ontology for representing Vietnamese fo...

3rd International Conference on Digital Arts, Media and Technology, ICDAMT 2018

作者： Chau, Ma Thi Thuy, Nguyen Thanh Human Machine Interaction Laboratory University of Engineering and Technology Hanoi Viet Nam Computer Science Department University of Engineering and Technology Hanoi Viet Nam

ISBN: (纸本)9781509052097

This paper aims at designing and constructing an ontology, representing and allowing Vietnamese folk dances annotation. An effective approach proposed is based on movement analysis. It is possible to divide Vietnamese folk dances into basic units, then movement phrases, movement primitives and dance poses. Studying deeply Vietnamese folk dances features and characteristics allows to find out 5 different types of relationships between main dance components. Typical relationships could be written in the form of logical predicates. For enriching ontologies, a formal encoding of the ontology expertise knowledge in the domain is performed by DL-Lite. The paper uses OWL-2 for building, organizing and visualizing ontologies. A case study-Mo folk dance with a knowledge base, is structured simply but effectively, with reasoning in DL-Lite and answering queries in SPARQL. © 2018 IEEE.

关键词： Ontology

DATA AUGMENTATION FOR END-TO-END CODE-SWITCHING SPEECH RECOGNITION

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Du, Chenpeng Li, Hao Lu, Yizhou Wang, Lan Qian, Yanmin MoE Key Lab of Artificial Intelligence SpeechLab Department of Computer Science and Engineering AI Institute Shanghai Jiao Tong University Shanghai China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China

Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data augmentation. Specifically, they are audio splicing with the existing code-switching data, and TTS with new code-switching texts generated by word translation or word insertion. Our experiments on 200 hours Mandarin-English code-switching dataset show that all the three proposed approaches yield significant improvements on code-switching ASR individually. Moreover, all the proposed approaches can be combined with recent popular SpecAugment, and an addition gain can be obtained. WER is significantly reduced by relative 24.0% compared to the system without any data augmentation, and still relative 13.0% gain compared to the system with only SpecAugment. Copyright © 2020, The Authors. All rights reserved.

关键词： Speech recognition