Filters








1,859 Hits in 4.9 sec

Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

Hongyu Lin, Le Sun, Xianpei Han
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
In this paper, we propose a multi-knowledge reasoning method, which can exploit heterogeneous knowledge for commonsense machine comprehension.  ...  Reasoning with commonsense knowledge is critical for natural language understanding.  ...  Moreover, we sincerely thank the reviewers for their valuable comments.  ... 
doi:10.18653/v1/d17-1216 dblp:conf/emnlp/LinSH17 fatcat:22cujx67tfcfvpnsmkepyms36q

Cross-platform Functional Consistency Validation for the Event-Driven Systems: An Ontology-Based Approach

Fahim T. Imam
2016 Formal Ontology in Information Systems  
• Can we incorporate the AI-based commonsense reasoning mechanisms for the functional behavior reasoning?  ...  Despite the unavoidable heterogeneity issues with multiple platforms, the systems developed for those platforms must confirm that their intended set of functionalities are consistently implemented across  ...  The EFBO provides an effective representational facility to model the functional behavior of any event-based systems that can be comprehensible for both humans and machines.  ... 
dblp:conf/fois/Imam16 fatcat:q7y2qgkz2fbmffnzkgplfhvj3q

Cognitive Reasoning: A Personal View

Ulrich Furbach, Steffen Hölldobler, Marco Ragni, Claudia Schon, Frieder Stolzenburg
2019 Künstliche Intelligenz  
We briefly introduce relevant approaches and methods from cognitive modeling, commonsense reasoning, and subsymbolic approaches.  ...  Therefore we start with a brief review of the notion and define what we mean by cognitive reasoning.  ...  Most of the teams participating in the machine comprehension task used neural approaches in combination with ontological knowledge like ConceptNet [81] .  ... 
doi:10.1007/s13218-019-00603-3 fatcat:hpouamzdmvddromtsnom7cswnu

Commonsense Knowledge Supported Intelligent News Analysis for Portfolio Risk Prediction

Kun Chen, Zonghang Yang, Huaiqing Wang, Libo Liu
2011 2011 44th Hawaii International Conference on System Sciences  
To automate such a reasoning process by computers, a description logic based knowledge mediator is designed and plugged in the system to dynamically provide the required commonsense knowledge for case  ...  In this paper, we present a commonsense knowledge supported intelligent news analysis system for portfolio risk prediction.  ...  With the case based reasoning method, a news analysis system is developed for portfolio risk prediction based on the commonsense knowledge mediator.  ... 
doi:10.1109/hicss.2011.116 dblp:conf/hicss/ChenYWL11 fatcat:vhpttc6zgvamllb5ld36atiw3q

Neuro-symbolic Architectures for Context Understanding [article]

Alessandro Oltramari, Jonathan Francis, Cory Henson, Kaixin Ma, and Ruwan Wickramarachchi
2020 arXiv   pre-print
Computational context understanding refers to an agent's ability to fuse disparate sources of information for decision-making and is, therefore, generally regarded as a prerequisite for sophisticated machine  ...  Data-driven and knowledge-driven methods are two classical techniques in the pursuit of such machine sense-making capability.  ...  Sense-making is not only a key for improving machine autonomy, but is a precondition for enabling seamless interaction with humans.  ... 
arXiv:2003.04707v1 fatcat:3bbg6kapvbcbnjkekqppin4bhm

Interpretable Visual Understanding with Cognitive Attention Network [article]

Xuejiao Tang, Wenbin Zhang, Yi Yu, Kea Turner, Tyler Derr, Mengyu Wang, Eirini Ntoutsi
2021 arXiv   pre-print
, which calls for exploiting the multi-source information as well as learning different levels of understanding and extensive commonsense knowledge.  ...  In this paper, we propose a novel Cognitive Attention Network (CAN) for visual commonsense reasoning to achieve interpretable visual understanding.  ...  as prior knowledge for inference.  ... 
arXiv:2108.02924v2 fatcat:iqtxzkuym5bmjd6wdf4cadhpjm

MKGN: A Multi-Dimensional Knowledge Enhanced Graph Network for Multi-Hop Question and Answering

Ying ZHANG, Fandong MENG, Jinchao ZHANG, Yufeng CHEN, Jinan XU, Jie ZHOU
2022 IEICE transactions on information and systems  
Machine reading comprehension with multi-hop reasoning always suffers from reasoning path breaking due to the lack of world knowledge, which always results in wrong answer detection.  ...  In this paper, we analyze what knowledge the previous work lacks, e.g., dependency relations and commonsense.  ...  Foundation of China (No. 61976016, 61976015, and 61876198) and the Key Technologies Research and Development Program of China (2019YFB1405200), and the authors would like to thank the anonymous reviewers for  ... 
doi:10.1587/transinf.2021edp7154 fatcat:t7zhidxuyjdqpargsqtmdohe6q

Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering [article]

Shangwen Lv, Daya Guo, Jingjing Xu, Duyu Tang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Songlin Hu
2020 arXiv   pre-print
Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question.  ...  In this work, we propose to automatically extract evidence from heterogeneous knowledge sources, and answer questions based on the extracted evidence.  ...  We thank the anonymous reviewers for providing valuable suggestions.  ... 
arXiv:1909.05311v2 fatcat:3owy3iv5xzgaphczq342iuf6ji

Natural Language QA Approaches using Reasoning with External Knowledge [article]

Chitta Baral, Pratyay Banerjee, Kuntal Kumar Pal, Arindam Mitra
2020 arXiv   pre-print
use in various NLQA models have brought the issue of NLQA using "reasoning" with external knowledge to the forefront.  ...  While Machine Learning has been the go-to approach in NL processing as well as NL question answering (NLQA) for the last 30 years, recently there has been an increasingly emphasized thread on NLQA where  ...  Free text Knowledge and Mixed Reasoners: There have been few approaches in bringing the neural and symbolic approaches together for commonsense reasoning with knowledge represented in text.  ... 
arXiv:2003.03446v1 fatcat:5ssmvcdzajc5flasg3s5hsfxsu

Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering

Shangwen Lv, Daya Guo, Jingjing Xu, Duyu Tang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Songlin Hu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question.  ...  In this work, we propose to automatically extract evidence from heterogeneous knowledge sources, and answer questions based on the extracted evidence.  ...  We thank the anonymous reviewers for providing valuable suggestions.  ... 
doi:10.1609/aaai.v34i05.6364 fatcat:crpcbk3mvjgcvd4c6wew3kr5xi

A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets [article]

Changchang Zeng, Shaobo Li, Qin Li, Jie Hu, Jianjun Hu
2020 arXiv   pre-print
Machine Reading Comprehension (MRC) is a challenging Natural Language Processing(NLP) research field with wide real-world applications.  ...  This shows the need for improving existing datasets, evaluation metrics, and models to move current MRC models toward "real" understanding.  ...  Commonsense and World Knowledge Commonsense and world knowledge are the main bottlenecks in machine reading comprehension.  ... 
arXiv:2006.11880v2 fatcat:auup4gvsuzf4dkjb2n6nzyfl3m

A Survey on Machine Reading Comprehension—Tasks, Evaluation Metrics and Benchmark Datasets

Changchang Zeng, Shaobo Li, Qin Li, Jie Hu, Jianjun Hu
2020 Applied Sciences  
Machine Reading Comprehension (MRC) is a challenging Natural Language Processing (NLP) research field with wide real-world applications.  ...  This shows the need for improving existing datasets, evaluation metrics, and models to move current MRC models toward "real" understanding.  ...  Commonsense and World Knowledge Commonsense and world knowledge are the main bottlenecks in machine reading comprehension.  ... 
doi:10.3390/app10217640 fatcat:e6rioqqdnbdqpimpxzvowhgv7a

Causal Reasoning Meets Visual Representation Learning: A Prospective Study [article]

Yang Liu, Yushen Wei, Hong Yan, Guanbin Li, Liang Lin
2022 arXiv   pre-print
In this paper, we conduct a comprehensive review of existing causal reasoning methods for visual representation learning, covering fundamental theories, models, and datasets.  ...  with good cognitive ability.  ...  and multi-sensor [15] [16] [17] [18] [19] data, deep learning based methods have shown promising performance for various computer vision and machine learning tasks, for example, the visual comprehension  ... 
arXiv:2204.12037v6 fatcat:upidzcsgubf2nkm5gieudz6jbu

Virtual Humans: Evolving with Common Sense [chapter]

Weizi Li, Jan M. Allbeck
2012 Lecture Notes in Computer Science  
An agent then learns environment specific knowledge through its own perception and communication with other agents. Ultimately, agents' commonsense knowledge is then refined by their own experiences.  ...  In this paper we present a method that uses commonsense knowledge to establish a baseline of concepts and relationships between objects.  ...  We are using Cyc for the following reasons. First of all, Cyc is the world's largest and most complete general knowledge base and commonsense reasoning engine [1] .  ... 
doi:10.1007/978-3-642-34710-8_17 fatcat:ogm7ypudgncxlkhsnyfk2p4nji

Social Commonsense Reasoning with Multi-Head Knowledge Attention [article]

Debjit Paul, Anette Frank
2020 arXiv   pre-print
Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills.  ...  In this work we propose a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell.  ...  We thank our annotators for their valuable annotations. We also thank NVIDIA Corporation for donating GPUs used in this research.  ... 
arXiv:2010.05587v1 fatcat:g3rb54etq5ao5jsibfskvax54e
« Previous Showing results 1 — 15 out of 1,859 results