The Experts below are selected from a list of 200718 Experts worldwide ranked by ideXlab platform
Si Wei - One of the best experts on this subject based on the ideXlab platform.
-
Natural Language Inference with External Knowledge
2017Co-Authors: Qian Chen, Xiaodan Zhu, Zhen-hua Ling, Diana Inkpen, Si WeiAbstract:Modeling informal inference in natural language is very challenging. With the recent availability of large annotated data, it has become feasible to train complex models such as neural networks to perform natural language inference (NLI), which have achieved state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all Knowledge needed to perform NLI from the data? If not, how can NLI models benefit from External Knowledge and how to build NLI models to leverage it? In this paper, we aim to answer these questions by enriching the state-of-the-art neural natural language inference models with External Knowledge. We demonstrate that the proposed models with External Knowledge further improve the state of the art on the Stanford Natural Language Inference (SNLI) dataset.
-
neural natural language inference models enhanced with External Knowledge
arXiv: Computation and Language, 2017Co-Authors: Qian Chen, Xiaodan Zhu, Zhen-hua Ling, Diana Inkpen, Si WeiAbstract:Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all Knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from External Knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with External Knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.
Shaker A. Zahra - One of the best experts on this subject based on the ideXlab platform.
-
the role of External Knowledge sources and organizational design in the process of opportunity exploitation
Strategic Management Journal, 2013Co-Authors: Jacob Lyngsie, Shaker A. ZahraAbstract:Research highlights the role of External Knowledge sources in the recognition of strategic opportunities, but is less forthcoming with respect to the role of such sources during the process of exploiting or realizing opportunities. We build on the Knowledge-based view to propose that realizing opportunities often involves significant interactions with External Knowledge sources. Organizational design can facilitate a firm’s interactions with these sources, while achieving coordination among organizational members engaged in opportunity exploitation. Our analysis of a double-respondent survey involving 536 Danish firms shows that the use of External Knowledge sources is positively associated with opportunity exploitation, but the strength of this association is significantly influenced by organizational designs that enable the firm to access External Knowledge during the process of exploiting opportunities.
Qian Chen - One of the best experts on this subject based on the ideXlab platform.
-
Natural Language Inference with External Knowledge
2017Co-Authors: Qian Chen, Xiaodan Zhu, Zhen-hua Ling, Diana Inkpen, Si WeiAbstract:Modeling informal inference in natural language is very challenging. With the recent availability of large annotated data, it has become feasible to train complex models such as neural networks to perform natural language inference (NLI), which have achieved state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all Knowledge needed to perform NLI from the data? If not, how can NLI models benefit from External Knowledge and how to build NLI models to leverage it? In this paper, we aim to answer these questions by enriching the state-of-the-art neural natural language inference models with External Knowledge. We demonstrate that the proposed models with External Knowledge further improve the state of the art on the Stanford Natural Language Inference (SNLI) dataset.
-
neural natural language inference models enhanced with External Knowledge
arXiv: Computation and Language, 2017Co-Authors: Qian Chen, Xiaodan Zhu, Zhen-hua Ling, Diana Inkpen, Si WeiAbstract:Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all Knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from External Knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with External Knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.
Yangqiu Song - One of the best experts on this subject based on the ideXlab platform.
-
Incorporating Context and External Knowledge for Pronoun Coreference Resolution
arXiv: Computation and Language, 2019Co-Authors: Hongming Zhang, Yan Song, Yangqiu SongAbstract:Linking pronominal expressions to the correct references requires, in many cases, better analysis of the contextual information and External Knowledge. In this paper, we propose a two-layer model for pronoun coreference resolution that leverages both context and External Knowledge, where a Knowledge attention mechanism is designed to ensure the model leveraging the appropriate source of External Knowledge based on different context. Experimental results demonstrate the validity and effectiveness of our model, where it outperforms state-of-the-art models by a large margin.
-
NAACL-HLT (1) - Incorporating Context and External Knowledge for Pronoun Coreference Resolution
Proceedings of the 2019 Conference of the North, 2019Co-Authors: Hongming Zhang, Yan Song, Yangqiu SongAbstract:Linking pronominal expressions to the correct references requires, in many cases, better analysis of the contextual information and External Knowledge. In this paper, we propose a two-layer model for pronoun coreference resolution that leverages both context and External Knowledge, where a Knowledge attention mechanism is designed to ensure the model leveraging the appropriate source of External Knowledge based on different context. Experimental results demonstrate the validity and effectiveness of our model, where it outperforms state-of-the-art models by a large margin.
Stefania Mariano - One of the best experts on this subject based on the ideXlab platform.
-
External Knowledge search paths in open innovation processes of small and medium enterprises
European Journal of Innovation Management, 2019Co-Authors: Preecha Chaochotechuang, Farhad Daneshgar, Stefania MarianoAbstract:The purpose of this paper is to advance Knowledge by exploring how small and medium enterprises (SMEs) search for External Knowledge in their open innovation processes, and how the search can be advanced.,This exploratory research employs a qualitative multiple case study design. A literature review of open innovation in SMEs and External Knowledge search is used to build the premises of this study. Semi-structured interviews with eight SMEs are employed to collect subsequent exploratory empirical data.,This exploratory study revealed that SMEs adopted a combination of cognitive and experiential search heuristics where cognitive search was practiced during the innovation research process when searching for External Knowledge, whilst experiential search was practiced during the innovation development process. Concerning the search space, this study found that SMEs mainly explored local Knowledge, and occasionally pursued distant Knowledge when confronted with complex problems. The reason for the above behavior was explained to be related to the reduction of costs and risks associated with innovation activities.,External Knowledge plays a pivotal role in open innovation. Although extant studies have shed some light on how large firms search for External Knowledge, however, it is not clear how SMEs search for External Knowledge. Moreover, this study focuses on learning about both the search space and the search heuristics at both the research and the development stages of the innovation process.
