检索结果-内蒙古大学图书馆

Document-level neural machine translation with document embeddings

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jiang, Shu Zhao, Hai Li, Zuchao Lu, Bao-Liang 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 Shanghai China

Standard neural machine translation (NMT) is on the assumption of document-level context independent. Most existing document-level NMT methods are satisfied with a smattering sense of brief document-level information, while this work focuses on exploiting detailed document-level context in terms of multiple forms of document embeddings, which is capable of sufficiently modeling deeper and richer document-level context. The proposed document-aware NMT is implemented to enhance the Transformer baseline by introducing both global and local document-level clues on the source end. Experiments show that the proposed method significantly improves the translation performance over strong baselines and other related studies. Copyright © 2020, The Authors. All rights reserved.

关键词： Neural machine translation

Advances in multi-turn dialogue comprehension: A survey

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Zhuosheng Zhao, Hai 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 Shanghai China

Training machines to understand natural language and interact with humans is an elusive and essential task of artificial intelligence. A diversity of dialogue systems has been designed with the rapid development of deep learning techniques, especially the recent pre-trained language models (PrLMs). Among these studies, the fundamental yet challenging type of task is dialogue comprehension whose role is to teach the machines to read and comprehend the dialogue context before responding. In this paper, we review the previous methods from the technical perspective of dialogue modeling for the dialogue comprehension task. We summarize the characteristics and challenges of dialogue comprehension in contrast to plain-text reading comprehension. Then, we discuss three typical patterns of dialogue modeling. In addition, we categorize dialogue-related pretraining techniques which are employed to enhance PrLMs in dialogue scenarios. Finally, we highlight the technical advances in recent years and point out the lessons from the empirical analysis and the prospects towards a new frontier of researches. Copyright © 2021, The Authors. All rights reserved.

关键词： Speech processing

Document-level neural machine translation with associated memory network

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Jiang, Shu Wang, Rui Li, Zuchao Utiyama, Masao Chen, Kehai Sumita, Eiichiro Zhao, Hai Lu, Bao-Liang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China National Institute of Information and Communications Technology Kyoto-shi6190289 Japan

Standard neural machine translation (NMT) is on the assumption that the document-level context is independent. Most existing document-level NMT approaches are satisfied with a smattering sense of global document-level information, while this work focuses on exploiting detailed document-level context in terms of a memory network. The capacity of the memory network that detecting the most relevant part of the current sentence from memory renders a natural solution to model the rich document-level context. In this work, the proposed document-aware memory network is implemented to enhance the Transformer NMT baseline. Experiments on several tasks show that the proposed method significantly improves the NMT performance over strong Transformer baselines and other related studies. © 2019, CC BY.

关键词： Neural machine translation

Learning Physical Graph Representations from Visual Scenes

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bear, Daniel M. Fan, Chaofei Mrowca, Damian Li, Yunzhu Alter, Seth Nayebi, Aran Schwartz, Jeremy Fei-Fei, Li Wu, Jiajun Tenenbaum, Joshua B. Yamins, Daniel L.K. Department of Psychology Stanford University United States Department of Computer Science Stanford University United States Wu Tsai Neurosciences Institute Stanford University United States MIT CSAIL MIT Brain and Cognitive Sciences Neurosciences Ph.D. Program Stanford University United States

Convolutional Neural Networks (CNNs) have proved exceptional at learning representations for visual object categorization. However, CNNs do not explicitly encode objects, parts, and their physical properties, which has limited CNNs’ success on tasks that require structured understanding of visual scenes. To overcome these limitations, we introduce the idea of "Physical Scene Graphs" (PSGs), which represent scenes as hierarchical graphs, with nodes in the hierarchy corresponding intuitively to object parts at different scales, and edges to physical connections between parts. Bound to each node is a vector of latent attributes that intuitively represent object properties such as surface shape and texture. We also describe PSGNet, a network architecture that learns to extract PSGs by reconstructing scenes through a PSG-structured bottleneck. PSGNet augments standard CNNs by including: recurrent feedback connections to combine low and high-level image information;graph pooling and vectorization operations that convert spatially-uniform feature maps into object-centric graph structures;and perceptual grouping principles to encourage the identification of meaningful scene elements. We show that PSGNet outperforms alternative self-supervised scene representation algorithms at scene segmentation tasks, especially on complex real-world images, and generalizes well to unseen object types and scene arrangements. PSGNet is also able learn from physical motion, enhancing scene estimates even for static images. We present a series of ablation studies illustrating the importance of each component of the PSGNet architecture, analyses showing that learned latent attributes capture intuitive scene properties, and illustrate the use of PSGs for compositional scene inference. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

Grammatical Error Correction as GAN-like sequence labeling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Parnow, Kevin Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China 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 China

In Grammatical Error Correction (GEC), sequence labeling models enjoy fast inference compared to sequence-to-sequence models;however, inference in sequence labeling GEC models is an iterative process, as sentences are passed to the model for multiple rounds of correction, which exposes the model to sentences with progressively fewer errors at each round. Traditional GEC models learn from sentences with fixed error rates. Coupling this with the iterative correction process causes a mismatch between training and inference that affects final performance. In order to address this mismatch, we propose a GAN-like sequence labeling model, which consists of a grammatical error detector as a discriminator and a grammatical error labeler with Gumbel-Softmax sampling as a generator. By sampling from real error distributions, our errors are more genuine compared to traditional synthesized GEC errors, thus alleviating the aforementioned mismatch and allowing for better training. Our results on several evaluation benchmarks demonstrate that our proposed approach is effective and improves the previous state-of-the-art baseline. Copyright © 2021, The Authors. All rights reserved.

关键词： Error correction

Impact of fabrication methods on binder distribution and charge transport in composite cathodes of all-solid-state batteries

学校读者我要写书评

暂无评论

材料展望（英文）

材料展望（英文） 2023年第4期 121-129页

作者： Benjamin Emley Chaoshan Wu Lihong Zhao Qing Ai Yanliang Liang Zhaoyang Chen Liqun Guo Tanguy Terlier Jun Lou Zheng Fan Yan Yao Materials Science and Engineering Program and Texas Center for Superconductivity at the University of Houston University of Houston4726 Calhoun RdHoustonTX 77204United States of America Materials Science and Engineering Program and Texas Center for Superconductivity at the University of Houston University of Houston4726 Calhoun RdHoustonTX 77204United States of America Department of Electrical and Computer Engineering University of Houston4726 Calhoun RdHoustonTX 77204United States of America Department of Materials Science and Nano Engineering Rice University6100 Main StreetHoustonTX 77005United States of America SIMS Laboratory Shared Equipment AuthorityRice UniversityHoustonTX 77005United States of America Department of Engineering Technology University of HoustonHoustonTX 77204United States of America

The manufacturing process of all-solid-state batteries necessitates the use of polymer ***,these binders,being ionic insulators by nature,can adversely affect charge transport within composite cathodes,thereby impacting the rate performance of the *** this work,we aim to investigate the impact of fabrication methods,specifically the solvent-free dry process versus the slurry-cast wet process,on binder distribution and charge transport in composite cathodes of solid-state *** the dry process,the binder forms a fibrous network,while the wet process results in binder coverage on the surface of cathode active *** difference in microstructure leads to a notable 20-fold increase in ionic conductivity in the dry-processed ***,the cells processed via the dry method exhibit higher capacity retention of 89％and 83％at C/3 and C/2 rates,respectively,in comparison to 68％and 58％for the wet-processed cells at the same *** findings provide valuable insights into the influence of fabrication methods on binder distribution and charge transport,contributing to a better understanding of the binder's role in manufacturing of all-solid-state batteries.

关键词： solid-state battery solvent-free dry process polymer binder lithium thiophosphate electrolyte

Enhancing Pre-trained Language Model with Lexical Simplification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bao, Rongzhou Wang, Jiayi Zhang, Zhuosheng Zhao, Hai 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 Shanghai China

For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given sentences. By substituting complex words with simple alternatives, lexical simplification (LS) is a recognized method to reduce such lexical diversity, and therefore to improve the understandability of sentences. In this paper, we leverage LS and propose a novel approach which can effectively improve the performance of PrLMs in text classification. A rule-based simplification process is applied to a given sentence. PrLMs are encouraged to predict the real label of the given sentence with auxiliary inputs from the simplified version. Using strong PrLMs (BERT and ELECTRA) as baselines, our approach can still further improve the performance in various text classification tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kim, Nayeon Piao, Yinhua Kim, Sun Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Computer Science and Engineering Seoul National University Korea Republic of Institute of Computer Technology Seoul National University Korea Republic of AIGENDRUG Co. Ltd Korea Republic of

Leveraging knowledge from electronic health records (EHRs) to predict a patient’s condition is essential to the effective delivery of appropriate care. Clinical notes of patient EHRs contain valuable information from healthcare professionals, but have been underused due to their difficult contents and complex hierarchies. Recently, hypergraph-based methods have been proposed for document classifications. Directly adopting existing hypergraph methods on clinical notes cannot sufficiently utilize the hierarchy information of the patient, which can degrade clinical semantic information by (1) frequent neutral words and (2) hierarchies with imbalanced distribution. Thus, we propose a taxonomy-aware multi-level hypergraph neural network (TM-HGNN), where multi-level hypergraphs assemble useful neutral words with rare keywords via note and taxonomy level hyperedges to retain the clinical semantic information. The constructed patient hypergraphs are fed into hierarchical message passing layers for learning more balanced multi-level knowledge at the note and taxonomy levels. We validate the effectiveness of TM-HGNN by conducting extensive experiments with MIMIC-III dataset on benchmark in-hospital-mortality prediction. Copyright © 2023, The Authors. All rights reserved.

关键词： Taxonomies

Novel action of biphasic electric current in vitro osteogenesis of human bone marrow mesenchymal stromal cells coupled with VEGF production

学校读者我要写书评

暂无评论

Novel action of biphasic electric current in vitro osteogene...

International Conference on Osteoporosis and Bone Research 2008(2008国际骨质疏松和骨矿疾病学术会议)

作者： In Sook Kim JongKeun Song Yun MiSong Tae Hyung Lee Tae Hyung Cho Shin Saeng Lim Hui Pan Sung June Kim Soon Jung Hwang Dental Research Institute Seoul National UniversityBrain Korea 21 2nd Program for Craniomaxillofacial Life ScienceKorea School of Electrical Engineering and Computer ScienceSeoul National UniversitySeoulKorea Department of Maxillofacial Cell and Developmental BiologyDepartment of Oral and Maxillofacial SurgerySchool of DentistrySeoul National UniversityBrain Korea 21 2nd Program for Craniomaxillofacial Life ScienceSeoulKorea