Filters








228,424 Hits in 4.1 sec

Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing [article]

Yadollah Yaghoobzadeh, Hinrich Schütze
2018 arXiv   pre-print
Knowledge bases (KBs) are paramount in NLP. We employ multiview learning for increasing accuracy and coverage of entity type information in KBs. We rely on two metaviews: language and representation.  ...  For representation, we consider representations based on the context distribution of the entity (i.e., on its embedding), on the entity's name (i.e., on its surface form) and on its description in Wikipedia  ...  Hazen and the anonymous reviewers for their helpful feedback on earlier drafts. This work was partially supported by the European Research Council, Advanced Grant NonSequeToR # 740516.  ... 
arXiv:1810.10499v1 fatcat:u4koeg6km5fabms7yfx2qalj54

Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing

Yadollah Yaghoobzadeh, Hinrich Schütze
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
Knowledge bases (KBs) are paramount in NLP. We employ multiview learning for increasing accuracy and coverage of entity type information in KBs. We rely on two metaviews: language and representation.  ...  For representation, we consider representations based on the context distribution of the entity (i.e., on its embedding), on the entity's name (i.e., on its surface form) and on its description in Wikipedia  ...  Hazen and the anonymous reviewers for their helpful feedback on earlier drafts. This work was partially supported by the European Research Council, Advanced Grant NonSequeToR # 740516.  ... 
doi:10.18653/v1/d18-1343 dblp:conf/emnlp/YaghoobzadehS18 fatcat:iz6le43puvb47feoswngprcjby

MetaMIML: Meta Multi-Instance Multi-Label Learning [article]

Yuanlin Yang, Guoxian Yu, Jun Wang, Lei Liu, Carlotta Domeniconi, Maozu Guo
2021 arXiv   pre-print
MetaMIML introduces the context learner with network embedding to capture semantic information of objects of different types, and the task learner to extract the meta knowledge for fast adapting to new  ...  To effectively mine interdependent MIML objects of different types, we propose a network embedding and meta learning based approach (MetaMIML).  ...  with a task learner for acquiring knowledge from multiple context tasks.  ... 
arXiv:2111.04112v1 fatcat:rnugpdpl5vdpfn3zhnvyckhwyu

KnowAugNet: Multi-Source Medical Knowledge Augmented Medication Prediction Network with Multi-Level Graph Contrastive Learning [article]

Yang An, Bo Jin, Xiaopeng Wei
2022 arXiv   pre-print
Therefore, to address these limitations, this paper proposes KnowAugNet, a multi-sourced medical knowledge augmented medication prediction network which can fully capture the diverse relations between  ...  medical codes and predict medications for patients.  ...  While for each specific prediction task, it has different task-specific requirements for the medical codes embedding vectors.  ... 
arXiv:2204.11736v2 fatcat:vvncqo2tejgwrbpo2cxpstqdt4

Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment [article]

Yuan Gong, Ziyi Chen, Iek-Heng Chu, Peng Chang, James Glass
2022 arXiv   pre-print
Specifically, we train a Goodness Of Pronunciation feature-based Transformer (GOPT) with multi-task learning.  ...  In this work, we explore modeling multi-aspect pronunciation assessment at multiple granularities.  ...  To our knowledge, this is the first work studying multi-aspect L2 speaker pronunciation assessment in a multi-granularity fashion.  ... 
arXiv:2205.03432v1 fatcat:jjj7grjgbjalzh62fg3fpyyare

3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition [article]

Zhao You, Shulin Feng, Dan Su, Dong Yu
2022 arXiv   pre-print
In this paper, based on our prior work, we identify and integrate several approaches to achieve further improvements for ASR tasks, which we denote as multi-loss, multi-path and multi-level, summarized  ...  Recently, Conformer based CTC/AED model has become a mainstream architecture for ASR.  ...  The embedding training loss provides reliable embeddings for the routers.  ... 
arXiv:2204.03178v2 fatcat:t75odzgsrndjzc22c5sptevmt4

MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning [article]

Lu Zhang, Mo Yu, Tian Gao, Yue Yu
2020 arXiv   pre-print
Multi-hop reasoning approaches over knowledge graphs infer a missing relationship between entities with a multi-hop rule, which corresponds to a chain of relationships.  ...  Empirical results show that our multi-chain multi-hop (MCMH) rules result in superior results compared to the standard single-chain approaches, justifying both our formulation of generalized rules and  ...  Conclusion We propose a new approach of multi-chain multihop rule learning for knowledge graph completion tasks.  ... 
arXiv:2010.01735v1 fatcat:s2bbbdo37nc2pekfvip3afea6a

Knowledge Guided Multi-instance Multi-label Learning via Neural Networks in Medicines Prediction

Junyuan Shang, Shenda Hong, Yuxi Zhou, Meng Wu, Hongyan Li
2018 Asian Conference on Machine Learning  
Predicting medicines for patients with co-morbidity has long been recognized as a hard task due to complex dependencies between diseases and medicines.  ...  In this paper, we formulate the medicines prediction task in multi-instance multi-label learning framework considering the multi-diagnoses as input instances and multi-medicines as output labels.  ...  Acknowledgment This work was supported by Peking University Medicine Seed Fund for Interdisciplinary Research. We also thank NVIDIA for the support of a GPU.  ... 
dblp:conf/acml/ShangHZWL18 fatcat:b4eaowe2ijavndrsi2ocxfhv5a

GMH: A General Multi-hop Reasoning Model for KG Completion [article]

Yao Zhang, Hongru Liang, Adam Jatowt, Wenqiang Lei, Xin Wei, Ning Jiang, Zhenglu Yang
2021 arXiv   pre-print
We argue that there are two key issues for a general multi-hop reasoning model: i) where to go, and ii) when to stop.  ...  This results in research efforts on multi-hop reasoning task, which can be formulated as a search process and current models typically perform short distance reasoning.  ...  Acknowledgements We sincerely thank Jun Wang and Xu Zhang for their constructive suggestions on this paper. This work was supported by the China Postdoctoral Science Foundation (No.2021TQ0222).  ... 
arXiv:2010.07620v3 fatcat:d56bqdmtcfeppdfoevlwjmruei

Multi-source knowledge fusion: a survey

Xiaojuan Zhao, Yan Jia, Aiping Li, Rong Jiang, Yichen Song
2020 World wide web (Bussum)  
On the one hand, the process of multi-source knowledge reasoning can detect conflicts and provide help for knowledge evaluation and verification; on the other hand, the new knowledge acquired by knowledge  ...  On this basis, the challenges and future research directions of multisource knowledge fusion in a large-scale knowledge base environment are discussed.  ...  Multi-source knowledge fusion is a challenging task.  ... 
doi:10.1007/s11280-020-00811-0 fatcat:ef5j2sna6fai7k2455yihrrfuq

Adversarial Encoder-Multi-Task-Decoder for Multi-Stage Processes [article]

Andre Mendes, Julian Togelius, Leandro dos Santos Coelho
2020 arXiv   pre-print
We address both cases by introducing a framework that combines adversarial autoencoders (AAE), multi-task learning (MTL), and multi-label semi-supervised learning (MLSSL).  ...  In multi-stage processes, decisions occur in an ordered sequence of stages.  ...  In MTL, multiple related tasks are learned simultaneously so that knowledge can be shared among them.  ... 
arXiv:2003.06899v1 fatcat:4d4sdhr6xzfd7lzwk4mw3brl5y

Multi-hop Attention Graph Neural Network [article]

Guangtao Wang, Rex Ying, Jing Huang, Jure Leskovec
2021 arXiv   pre-print
On knowledge graph completion MAGNA advances state-of-the-art on WN18RR and FB15k-237 across four different performance metrics.  ...  Experimental results on node classification as well as the knowledge graph completion benchmarks show that MAGNA achieves state-of-the-art results: MAGNA achieves up to 5.7 percent relative error reduction  ...  We then define the task of knowledge graph completion: Definition 2.  ... 
arXiv:2009.14332v5 fatcat:vbtttkitzzdezllnx5chtxn3su

MMKG: Multi-Modal Knowledge Graphs [article]

Ye Liu, Hui Li, Alberto Garcia-Duran, Mathias Niepert, Daniel Onoro-Rubio, David S. Rosenblum
2019 arXiv   pre-print
We believe this data set has the potential to facilitate the development of novel multi-modal learning approaches for knowledge graphs.We validate the utility ofMMKG in the sameAs link prediction task  ...  We present MMKG, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs.  ...  Technical Quality of MMKG We provide empirical evidence that knowledge graph completion related tasks can benefit from the multi-modal data of MMKG.  ... 
arXiv:1903.05485v1 fatcat:mapil3zlcjbipnkzgskufclcaa

μKG: A Library for Multi-source Knowledge Graph Embeddings and Applications [article]

Xindi Luo and Zequn Sun and Wei Hu
2022 arXiv   pre-print
We show that the jointly learned embeddings can greatly help knowledge-powered downstream tasks, such as multi-hop knowledge graph question answering.  ...  It is useful for a thorough comparison and analysis of various embedding models and tasks.  ...  The joint KG embeddings have demonstrated useful for a variety of downstream tasks such as entity typing and multi-source KG completion [11, 35] .  ... 
arXiv:2207.11442v2 fatcat:7jbreysht5fjrksczcavb4c7fm

Learning for Multi-Model and Multi-Type Fitting [article]

Xun Xu, Loong-Fah Cheong, Zhuwen Li
2019 arXiv   pre-print
Comparisons are also made on single-type multi-model fitting tasks with promising results as well.  ...  For inference, we apply K-means to cluster the data in the embedded feature space and model selection is enabled by analyzing the K-means residuals.  ...  and multi-ellipse segmentation tasks.  ... 
arXiv:1901.10254v1 fatcat:ap6hpcgohveolajm74mo7m2cyq
« Previous Showing results 1 — 15 out of 228,424 results