scholarly journals CorMet: A Computational, Corpus-Based Conventional Metaphor Extraction System

2004 ◽  
Vol 30 (1) ◽  
pp. 23-44 ◽  
Author(s):  
Zachary J. Mason
Keyword(s):  
Knowledge Base ◽  
Linguistic Analysis ◽  
Knowledge Bases ◽  
Semantic Knowledge ◽  
Target Domain ◽  
Source Domain ◽  
Domain Specific ◽  
Small Hand ◽  
Selectional Preferences ◽  
Transfer Structure

CorMet is a corpus-based system for discovering metaphorical mappings between concepts. It does this by finding systematic variations in domain-specific selectional preferences, which are inferred from large, dynamically mined Internet corpora. Metaphors transfer structure from a source domain to a target domain, making some concepts in the target domain metaphorically equivalent to concepts in the source domain. The verbs that select for a concept in the source domain tend to select for its metaphorical equivalent in the target domain. This regularity, detectable with a shallow linguistic analysis, is used to find the metaphorical interconcept mappings, which can then be used to infer the existence of higher-level conventional metaphors. Most other computational metaphor systems use small, hand-coded semantic knowledge bases and work on a few examples. Although Cor Met's only knowledge base is Word Net (Fellbaum 1998) it can find the mappings constituting many conventional metaphors and in some cases recognize sentences instantiating those mappings. CorMet is tested on its ability to find a subset of the Master Metaphor List (Lakoff, Espenson, and Schwartz 1991).

Knowledge Base Refinement Using Limited Amount of Efforts from Experts

2014 ◽  
Vol 4 (2) ◽  
pp. 1-19 ◽  
Author(s):  
Ki Chan ◽  
Wai Lam ◽  
Tak-Lam Wong
Keyword(s):  
Knowledge Base ◽  
Domain Knowledge ◽  
Pattern Mining ◽  
Knowledge Bases ◽  
Target Domain ◽  
Markov Logic ◽  
Source Domain ◽  
Construction Of Knowledge ◽  
Knowledge Base Refinement ◽  
Intelligent Information

Knowledge bases are essential for supporting decision making during intelligent information processing. Automatic construction of knowledge bases becomes infeasible without labeled data, a complete table of data records including answers to queries. Preparing such information requires huge efforts from experts. The authors propose a new knowledge base refinement framework based on pattern mining and active learning using an existing available knowledge base constructed from a different domain (source domain) solving the same task as well as some data collected from the target domain. The knowledge base investigated in this paper is represented by a model known as Markov Logic Networks. The authors' proposed method first analyzes the unlabeled target domain data and actively asks the expert to provide labels (or answers) a very small amount of automatically selected queries. The idea is to identify the target domain queries whose underlying relations are not sufficiently described by the existing source domain knowledge base. Potential relational patterns are discovered and new logic relations are constructed for the target domain by exploiting the limited amount of labeled target domain data and the unlabeled target domain data. The authors have conducted extensive experiments by applying our approach to two different text mining applications, namely, pronoun resolution and segmentation of citation records, demonstrating consistent improvements.

scholarly journals End-user development of knowledge bases for semi-automated formation of task cards

2021 ◽  
Author(s):  
N.O. Dorodnykh ◽  
Y.V. Kotlov ◽  
O.A. Nikolaychuk ◽  
V.M. Popov ◽  
A.Y. Yurin
Keyword(s):  
Knowledge Base ◽  
Intelligent Systems ◽  
Knowledge Bases ◽  
Visual Programming ◽  
Event Tree ◽  
End User ◽  
Model Driven ◽  
Domain Specific ◽  
Problem Situations ◽  
Event Trees

The complexity of creating artificial intelligence applications remains high. One of the factors that cause such complexity is the high qualification requirements for developers in the field of programming. Development complexity can be reduced by using methods and tools based on a paradigm known as End-user development. One of the problems that requires the application of the methods of this paradigm is the development of intelligent systems for supporting the search and troubleshooting onboard aircraft. Some tasks connected with this problem are identified, including the task of dynamic formation of task cards for troubleshooting in terms of forming a list of operations. This paper presents a solution to this problem based on some principles of End-user development: model-driven development, visual programming, and wizard form-filling. In particular, an extension of the Prototyping expert systems based on transformations technology, which implements the End-user development, is proposed in the context of the problem to be solved for Sukhoi Superjet aircraft. The main contribution of the work is as follows: expanded the main technology method by supporting event trees formalism (as a popular expert method for formalizing scenarios for the development of problem situations and their localization); created a domain-specific tool (namely, Extended event tree editor) for building standard and extended event trees, including for diagnostic tasks; developed a module for supporting transformations of XML-like event tree representation format for the knowledge base prototyping system – Personal knowledge base designer. A description of the proposed extension and the means of its implementation, as well as an illustrative example, are provided.

scholarly journals Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

2020 ◽  
Vol 34 (04) ◽  
pp. 6243-6250 ◽  
Author(s):  
Qian Wang ◽  
Toby Breckon
Keyword(s):  
Domain Adaptation ◽  
Feature Space ◽  
Structured Prediction ◽  
Target Domain ◽  
Source Domain ◽  
Domain Specific ◽  
Unsupervised Domain Adaptation ◽  
Deep Feature ◽  
Significant Performance ◽  
Error Accumulation

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two domains. As a result, classifiers trained from labeled samples in the source domain suffer from significant performance drop when directly applied to the samples from the target domain. To address this issue, different approaches have been proposed to learn domain-invariant features or domain-specific classifiers. In either case, the lack of labeled samples in the target domain can be an issue which is usually overcome by pseudo-labeling. Inaccurate pseudo-labeling, however, could result in catastrophic error accumulation during learning. In this paper, we propose a novel selective pseudo-labeling strategy based on structured prediction. The idea of structured prediction is inspired by the fact that samples in the target domain are well clustered within the deep feature space so that unsupervised clustering analysis can be used to facilitate accurate pseudo-labeling. Experimental results on four datasets (i.e. Office-Caltech, Office31, ImageCLEF-DA and Office-Home) validate our approach outperforms contemporary state-of-the-art methods.

Knowledge Extraction from Domain-Specific Documents

2017 ◽  
pp. 106-123
Author(s):  
Ram Kumar ◽  
Shailesh Jaloree ◽  
R. S. Thakur
Keyword(s):  
Knowledge Representation ◽  
Knowledge Base ◽  
Knowledge Bases ◽  
Domain Ontology ◽  
Knowledge Based Systems ◽  
Domain Specific ◽  
Knowledge Based ◽  
Representation Systems ◽  
Terminological Confusion ◽  
Knowledge Representation Systems

Knowledge-based systems have become widespread in modern years. Knowledge-base developers need to be able to share and reuse knowledge bases that they build. As a result, interoperability among different knowledge-representation systems is essential. Domain ontology seeks to reduce conceptual and terminological confusion among users who need to share various kind of information. This paper shows how these structures make it possible to bridge the gap between standard objects and Knowledge-based Systems.

scholarly journals Domain Adaptation for Semantic Parsing

2020 ◽  
Author(s):  
Zechang Li ◽  
Yuxuan Lai ◽  
Yansong Feng ◽  
Dongyan Zhao
Keyword(s):  
Domain Adaptation ◽  
Specific Information ◽  
Semantic Parsing ◽  
Target Domain ◽  
Source Domain ◽  
Domain Specific ◽  
The Difference ◽  
Two Stages ◽  
Coarse To Fine ◽  
Target Data

Recently, semantic parsing has attracted much attention in the community. Although many neural modeling efforts have greatly improved the performance, it still suffers from the data scarcity issue. In this paper, we propose a novel semantic parser for domain adaptation, where we have much fewer annotated data in the target domain compared to the source domain. Our semantic parser benefits from a two-stage coarse-to-fine framework, thus can provide different and accurate treatments for the two stages, i.e., focusing on domain invariant and domain specific information, respectively. In the coarse stage, our novel domain discrimination component and domain relevance attention encourage the model to learn transferable domain general structures. In the fine stage, the model is guided to concentrate on domain related details. Experiments on a benchmark dataset show that our method consistently outperforms several popular domain adaptation strategies. Additionally, we show that our model can well exploit limited target data to capture the difference between the source and target domain, even when the target domain has far fewer training instances.

Exploiting Linked Data for Open and Configurable Named Entity Extraction

2015 ◽  
Vol 24 (02) ◽  
pp. 1540012 ◽  
Author(s):  
Pavlos Fafalios ◽  
Manolis Baritakis ◽  
Yannis Tzitzikas
Keyword(s):  
Linked Data ◽  
Question Answering ◽  
Knowledge Bases ◽  
Semantic Knowledge ◽  
Configuration Model ◽  
Generic Model ◽  
Entity Extraction ◽  
Named Entity ◽  
Domain Specific ◽  
Named Entity Extraction

Named Entity Extraction (NEE) is the process of identifying entities in texts and, very commonly, linking them to related (Web) resources. This task is useful in several applications, e.g. for question answering, annotating documents, post-processing of search results, etc. However, existing NEE tools lack an open or easy configuration although this is very important for building domain-specific applications. For example, supporting a new category of entities, or specifying how to link the detected entities with online resources, is either impossible or very laborious. In this paper, we show how we can exploit semantic information (Linked Data) at real-time for configuring (handily) a NEE system and we propose a generic model for configuring such services. To explicitly define the semantics of the proposed model, we introduce an RDF/S vocabulary, called “Open NEE Configuration Model”, which allows a NEE service to describe (and publish as Linked Data) its entity mining capabilities, but also to be dynamically configured. To allow relating the output of a NEE process with an applied configuration, we propose an extension of the Open Annotation Data Model which also enables an application to run advanced queries over the annotated data. As a proof of concept, we present X-Link, a fully-configurable NEE framework that realizes this approach. Contrary to the existing tools, X-Link allows the user to easily define the categories of entities that are interesting for the application at hand by exploiting one or more semantic Knowledge Bases. The user is also able to update a category and specify how to semantically link and enrich the identified entities. This enhanced configurability allows X-Link to be easily configured for different contexts for building domain-specific applications. To test the approach, we conducted a task-based evaluation with users that demonstrates its usability, and a case study that demonstrates its feasibility.

scholarly journals Domain Adaptation via Tree Kernel Based Maximum Mean Discrepancy for User Consumption Intention Identification

2018 ◽  
Author(s):  
Xiao Ding ◽  
Bibo Cai ◽  
Ting Liu ◽  
Qiankun Shi
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Reproducing Kernel ◽  
Kernel Method ◽  
Reproducing Kernel Hilbert Space ◽  
Target Domain ◽  
Source Domain ◽  
Domain Specific ◽  
Tree Kernel ◽  
The Mean

Identifying user consumption intention from social media is of great interests to downstream applications. Since such task is domain-dependent, deep neural networks have been applied to learn transferable features for adapting models from a source domain to a target domain. A basic idea to solve this problem is reducing the distribution difference between the source domain and the target domain such that the transfer error can be bounded. However, the feature transferability drops dramatically in higher layers of deep neural networks with increasing domain discrepancy. Hence, previous work has to use a few target domain annotated data to train domain-specific layers. In this paper, we propose a deep transfer learning framework for consumption intention identification, to reduce the data bias and enhance the transferability in domain-specific layers. In our framework, the representation of the domain-specific layer is mapped to a reproducing kernel Hilbert space, where the mean embeddings of different domain distributions can be explicitly matched. By using an optimal tree kernel method for measuring the mean embedding matching, the domain discrepancy can be effectively reduced. The framework can learn transferable features in a completely unsupervised manner with statistical guarantees. Experimental results on five different domain datasets show that our approach dramatically outperforms state-of-the-art baselines, and it is general enough to be applied to more scenarios. The source code and datasets can be found at http://ir.hit.edu.cn/$\scriptsize{\sim}$xding/index\_english.htm.

scholarly journals Transfer Value Iteration Networks

2020 ◽  
Vol 34 (04) ◽  
pp. 5676-5683
Author(s):  
Junyi Shen ◽  
Hankz Hankui Zhuo ◽  
Jin Xu ◽  
Bin Zhong ◽  
Sinno Pan
Keyword(s):  
Performance Improvement ◽  
Feature Space ◽  
Training Data ◽  
Value Iteration ◽  
Target Domain ◽  
Kernel Size ◽  
Source Domain ◽  
Domain Specific ◽  
Learning Tasks ◽  
Feature Spaces

Value iteration networks (VINs) have been demonstrated to have a good generalization ability for reinforcement learning tasks across similar domains. However, based on our experiments, a policy learned by VINs still fail to generalize well on the domain whose action space and feature space are not identical to those in the domain where it is trained. In this paper, we propose a transfer learning approach on top of VINs, termed Transfer VINs (TVINs), such that a learned policy from a source domain can be generalized to a target domain with only limited training data, even if the source domain and the target domain have domain-specific actions and features. We empirically verify that our proposed TVINs outperform VINs when the source and the target domains have similar but not identical action and feature spaces. Furthermore, we show that the performance improvement is consistent across different environments, maze sizes, dataset sizes as well as different values of hyperparameters such as number of iteration and kernel size.

Open Knowledge Base: Resources and Units of Knowledge

2020 ◽  
Author(s):  
Matheus Pereira Lobo
Keyword(s):  
Knowledge Base ◽  
Knowledge Bases

This paper is about highlighting two categories of knowledge bases, one built as a repository of links, and other based on units of knowledge.

The Concept of Animals in Balinese Proverbs

2017 ◽  
Vol 3 (1) ◽  
pp. 87
Author(s):  
I Wayan Budiarta ◽  
Ni Wayan Kasni
Keyword(s):  
Short Story ◽  
Cognitive Processes ◽  
Qualitative Data ◽  
Syntactic Structure ◽  
The Body ◽  
Biological Characteristic ◽  
Speech Community ◽  
Target Domain ◽  
Source Domain ◽  
Mapping Process

This research is aimed to figure out the syntactic structure of Balinese proverbs, the relation of meaning between the name of the animals and the meaning of the proverbs, and how the meanings are constructed in logical dimension. This research belongs to a qualitative as the data of this research are qualitative data which taken from a book entitled Basita Paribahasa written by Simpen (1993) and a book of Balinese short story written by Sewamara (1977). The analysis shows that the use of concept of animals in Balinese proverbs reveal similar characteristics, whether their form, their nature, and their condition. Moreover, the cognitive processes which happen in resulting the proverb is by conceptualizing the experience which is felt by the body, the nature, and the characteristic which owned by the target with the purpose of describing event or experience by the speech community of Balinese. Analogically, the similarity of characteristic in the form of shape of source domain can be proved visually, while the characteristic of the nature and the condition can be proved through bodily and empirical experiences. Ecolinguistics parameters are used to construct of Balinese proverbs which happen due to cross mapping process. It is caused by the presence of close characteristic or biological characteristic which is owned by the source domain and target domain, especially between Balinese with animal which then are verbally recorded and further patterned in ideological, biological, and sociological dimensions.

Sign in / Sign up

Export Citation Format

Share Document