The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform
Guodong Zhou - One of the best experts on this subject based on the ideXlab platform.
-
semantic role labeling of chinese nominal predicates with dependency driven constituent Parse Tree structure
Journal of Computer Science and Technology, 2013Co-Authors: Hongling Wang, Guodong ZhouAbstract:This paper explores a Tree kernel based method for semantic role labeling (SRL) of Chinese nominal predicates via a convolution Tree kernel. In particular, a new Parse Tree representation structure, called dependency-driven constituent Parse Tree (D-CPT), is proposed to combine the advantages of both constituent and dependence Parse Trees. This is achieved by directly representing various kinds of dependency relations in a CPT-style structure, which employs dependency relation types instead of phrase labels in CPT (Constituent Parse Tree). In this way, D-CPT not only keeps the dependency relationship information in the dependency Parse Tree (DPT) structure but also retains the basic hierarchical structure of CPT style. Moreover, several schemes are designed to extract various kinds of necessary information, such as the shortest path between the nominal predicate and the argument candidate, the support verb of the nominal predicate and the head argument modifled by the argument candidate, from D-CPT. This largely reduces the noisy information inherent in D-CPT. Finally, a convolution Tree kernel is employed to compute the similarity between two Parse Trees. Besides, we also implement a feature-based method based on D-CPT. Evaluation on Chinese NomBank corpus shows that our Tree kernel based method on D-CPT performs signiflcantly better than other Tree kernel-based ones and achieves comparable performance with the state-of-the-art feature-based ones. This indicates the efiectiveness of the novel D-CPT structure in representing various kinds of dependency relations in a CPT-style structure and our Tree kernel based method in exploring the novel D-CPT structure. This also illustrates that the kernel-based methods are competitive and they are complementary with the feature- based methods on SRL.
-
chinese semantic role labeling with dependency driven constituent Parse Tree structure
International conference natural language processing, 2012Co-Authors: Hongling Wang, Bukang Wang, Guodong ZhouAbstract:This paper explores a Tree kernel-based method for nominal semantic role labeling (SRL). In particular, a new dependency-driven constituent Parse Tree (D-CPT) structure is proposed to better represent the dependency relations in a CPT-style structure, which employs dependency relation types instead of phrase labels in CPT. In this way, D-CPT not only keeps the dependency relationship information in the dependency Parse Tree (DPT) structure but also retains the basic structure of CPT. Moreover, several schemes are designed to extract various kinds of necessary information, such as the shortest path between the nominal predicate and the argument candidate, the support verb of the nominal predicate and the head argument modified by the argument candidate, from D-CPT . Evaluation on Chinese NomBank shows that our Tree kernel-based method on D-CPT achieves comparable performance with the state-of-art feature-based ones. This indicates the effectiveness of the novel D-CPT structure for better representation of dependency relations in Tree kernel-based methods. To our knowledge, this is the first research of Tree kernel-based SRL on effectively exploring dependency relationship information, which achieves comparable performance with the state-of-the-art feature-based ones.
-
Tree kernel based semantic role labeling with enriched Parse Tree structure
Information Processing and Management, 2011Co-Authors: Guodong Zhou, Jianxi Fan, Qiaoming ZhuAbstract:Shallow semantic parsing assigns a simple structure (such as WHO did WHAT to WHOM, WHEN, WHERE, WHY, and HOW) to each predicate in a sentence. It plays a critical role in event-based information extraction and thus is important for deep information processing and management. This paper proposes a Tree kernel method for a particular shallow semantic parsing task, called semantic role labeling (SRL), with an enriched Parse Tree structure. First, a new Tree kernel is presented to effectively capture the inherent structured knowledge in a Parse Tree by enabling the standard convolution Tree kernel with context-sensitiveness via considering ancestral information of substructures and approximate matching via allowing insertion/deletion/substitution of Tree nodes in the substructures. Second, an enriched Parse Tree structure is proposed to both well preserve the necessary structured information and effectively avoid noise by differentiating various portions of the Parse Tree structure. Evaluation on the CoNLL'2005 shared task shows that both the new Tree kernel and the enriched Parse Tree structure contribute much in SRL and our Tree kernel method significantly outperforms the state-of-the-art Tree kernel methods. Moreover, our Tree kernel method is proven rather complementary to the state-of-the-art feature-based methods in that it can better capture structural Parse Tree information.
-
kernel based semantic relation detection and classification via enriched Parse Tree structure
Journal of Computer Science and Technology, 2011Co-Authors: Guodong Zhou, Qiaoming ZhuAbstract:This paper proposes a Tree kernel method of semantic relation detection and classification (RDC) between named entities. It resolves two critical problems in previous Tree kernel methods of RDC. First, a new Tree kernel is presented to better capture the inherent structural information in a Parse Tree by enabling the standard convolution Tree kernel with context-sensitiveness and approximate matching of sub-Trees. Second, an enriched Parse Tree structure is proposed to well derive necessary structural information, e.g., proper latent annotations, from a Parse Tree. Evaluation on the ACE RDC corpora shows that both the new Tree kernel and the enriched Parse Tree structure contribute significantly to RDC and our Tree kernel method much outperforms the state-of-the-art ones.
-
Tree kernel based semantic relation extraction with rich syntactic and semantic information
Information Sciences, 2010Co-Authors: Guodong Zhou, Longhua Qian, Jianxi FanAbstract:This paper proposes a novel Tree kernel-based method with rich syntactic and semantic information for the extraction of semantic relations between named entities. With a Parse Tree and an entity pair, we first construct a rich semantic relation Tree structure to integrate both syntactic and semantic information. And then we propose a context-sensitive convolution Tree kernel, which enumerates both context-free and context-sensitive sub-Trees by considering the paths of their ancestor nodes as their contexts to capture structural information in the Tree structure. An evaluation on the Automatic Content Extraction/Relation Detection and Characterization (ACE RDC) corpora shows that the proposed Tree kernel-based method outperforms other state-of-the-art methods.
Jianxi Fan - One of the best experts on this subject based on the ideXlab platform.
-
Tree kernel based semantic role labeling with enriched Parse Tree structure
Information Processing and Management, 2011Co-Authors: Guodong Zhou, Jianxi Fan, Qiaoming ZhuAbstract:Shallow semantic parsing assigns a simple structure (such as WHO did WHAT to WHOM, WHEN, WHERE, WHY, and HOW) to each predicate in a sentence. It plays a critical role in event-based information extraction and thus is important for deep information processing and management. This paper proposes a Tree kernel method for a particular shallow semantic parsing task, called semantic role labeling (SRL), with an enriched Parse Tree structure. First, a new Tree kernel is presented to effectively capture the inherent structured knowledge in a Parse Tree by enabling the standard convolution Tree kernel with context-sensitiveness via considering ancestral information of substructures and approximate matching via allowing insertion/deletion/substitution of Tree nodes in the substructures. Second, an enriched Parse Tree structure is proposed to both well preserve the necessary structured information and effectively avoid noise by differentiating various portions of the Parse Tree structure. Evaluation on the CoNLL'2005 shared task shows that both the new Tree kernel and the enriched Parse Tree structure contribute much in SRL and our Tree kernel method significantly outperforms the state-of-the-art Tree kernel methods. Moreover, our Tree kernel method is proven rather complementary to the state-of-the-art feature-based methods in that it can better capture structural Parse Tree information.
-
Tree kernel based semantic relation extraction with rich syntactic and semantic information
Information Sciences, 2010Co-Authors: Guodong Zhou, Longhua Qian, Jianxi FanAbstract:This paper proposes a novel Tree kernel-based method with rich syntactic and semantic information for the extraction of semantic relations between named entities. With a Parse Tree and an entity pair, we first construct a rich semantic relation Tree structure to integrate both syntactic and semantic information. And then we propose a context-sensitive convolution Tree kernel, which enumerates both context-free and context-sensitive sub-Trees by considering the paths of their ancestor nodes as their contexts to capture structural information in the Tree structure. An evaluation on the Automatic Content Extraction/Relation Detection and Characterization (ACE RDC) corpora shows that the proposed Tree kernel-based method outperforms other state-of-the-art methods.
Shigeki Matsubara - One of the best experts on this subject based on the ideXlab platform.
-
sentence compression by removing recursive structure from Parse Tree
Pacific Rim International Conference on Artificial Intelligence, 2008Co-Authors: Seiji Egawa, Yoshihide Kato, Shigeki MatsubaraAbstract:Sentence compression is a task of generating a grammatical short sentence from an original sentence, retaining the most important information. The existing methods of removing the constituents in the Parse Tree of an original sentence cannot deal with recursive structures which appear in the Parse Tree. This paper proposes a method to remove such structure and generate a grammatical short sentence. Compression experiments have shown the method to provide an ability to sentence compression comparable to the existing methods and generate good compressed sentences for sentences including recursive structures, which the previous methods failed to compress.
-
sentence compression by structural conversion of Parse Tree
International Conference on Digital Information Management, 2008Co-Authors: Seiji Egawa, Yoshihide Kato, Shigeki MatsubaraAbstract:Sentence compression is the task of generating a grammatical short sentence from an original sentence, retaining important information. The existing methods of only removing the constituents in the Parse Tree of an original sentence cannot emulate human compression that changes structures of the Parse Tree. This paper proposes a method to remove recursive structures, one example of such structural conversions, and generate a grammatical short sentence. In order to remove a recursive structure, our method detects the constituents forming the structure and removes them as a unit. Compression experiments have shown that our method generates more grammatical compressed sentences than the previous method.
Alon Lavie - One of the best experts on this subject based on the ideXlab platform.
-
improving syntax driven translation models by re structuring divergent and nonisomorphic Parse Tree structures
Conference of the Association for Machine Translation in the Americas, 2008Co-Authors: Vamshi Ambati, Alon LavieAbstract:Syntax-based approaches to statistical MT require syntax-aware methods for acquiring their underlying translation models from parallel data. This acquisition process can be driven by syntactic Trees for either the source or target language, or by Trees on both sides. Work to date has demonstrated that using Trees for both sides suffers from severe coverage problems. This is primarily due to the highly restrictive space of constituent segmentations that the Trees on two sides introduce, which adversely affects the recall of the resulting translation models. Approaches that project from Trees on one side, on the other hand, have higher levels of recall, but suffer from lower precision, due to the lack of syntactically-aware word alignments. In this paper we explore the issue of lexical coverage of the translation models learned in both of these scenarios. We specifically look at how the non-isomorphic nature of the Parse Trees for the two languages affects recall and coverage. We then propose a novel technique for restructuring target Parse Trees, that generates highly isomorphic target Trees that preserve the syntactic boundaries of constituents that were aligned in the original Parse Trees. We evaluate the translation models learned from these restructured Trees and show that they are significantly better than those learned using Trees on both sides and Trees on one side.
Seong-bae Park - One of the best experts on this subject based on the ideXlab platform.
-
Computation of Program Source Code Similarity by Composition of Parse Tree and Call Graph
Hindawi Limited, 2015Co-Authors: Hyunje Song, Seong-bae Park, Se-young ParkAbstract:This paper proposes a novel method to compute how similar two program source codes are. Since a program source code is represented as a structural form, the proposed method adopts convolution kernel functions as a similarity measure. Actually, a program source code has two kinds of structural information. One is syntactic information and the other is the dependencies of function calls lying on the program. Since the syntactic information of a program is expressed as its Parse Tree, the syntactic similarity between two programs is computed by a Parse Tree kernel. The function calls within a program provide a global structure of a program and can be represented as a graph. Therefore, the similarity of function calls is computed with a graph kernel. Then, both structural similarities are reflected simultaneously into comparing program source codes by composing the Parse Tree and the graph kernels based on a cyclomatic complexity. According to the experimental results on a real data set for program plagiarism detection, the proposed method is proved to be effective in capturing the similarity between programs. The experiments show that the plagiarized pairs of programs are found correctly and thoroughly by the proposed method
-
an application for plagiarized source code detection based on a Parse Tree kernel
Engineering Applications of Artificial Intelligence, 2013Co-Authors: Jeong Woo Son, Taegil Noh, Hyunje Song, Seong-bae ParkAbstract:Program plagiarism detection is a task of detecting plagiarized code pairs among a set of source codes. In this paper, we propose a code plagiarism detection system that uses a Parse Tree kernel. Our Parse Tree kernel calculates a similarity value between two source codes in terms of their Parse Tree similarity. Since Parse Trees contain the essential syntactic structure of source codes, the system effectively handles structural information. The contributions of this paper are two-fold. First, we propose a Parse Tree kernel that is optimized for program source code. The evaluation shows that our system based on this kernel outperforms well-known baseline systems. Second, we collected a large number of real-world Java source codes from a university programming class. This test set was manually analyzed and tagged by two independent human annotators to mark plagiarized codes. It can be used to evaluate the performance of various detection systems in real-world environments. The experiments with the test set show that the performance of our plagiarism detection system reaches to 93% level of human annotators.
-
dependency analysis of clauses using Parse Tree kernels
International Conference on Computational Linguistics, 2009Co-Authors: Sangsoo Kim, Seong-bae Park, Sangjo LeeAbstract:Identification of dependency relation among clauses is one of the most critical parts in parsing Korean sentences because it generates severe ambiguities. The resolution of the ambiguities involves both syntactic and semantic information. This paper proposes a method to determine the dependency relation among Korean clauses using Parse Tree kernels. The Parse Tree used in this paper provides the method with the syntactic information, and the endings (Eomi) do with the semantic information. In addition, the Parse Tree kernel for handling Parse Trees has benefits that it minimizes the information loss occurred during transforming a Parse Tree into a feature vector, and can obtain, as a result, very accurate similarity between Parse Trees. The experimental results on a standard Korean data set show 89.12% of accuracy, which implies that the proposed method is plausible for the dependency analysis of clauses.
-
ontology alignment based on Parse Tree kernel usig structural and semantic information
Journal of KIISE:Software and Applications, 2009Co-Authors: Jeong Woo Son, Seong-bae ParkAbstract:The ontology alignment has two kinds of major problems. First, the features used for ontology alignment are usually defined by experts, but it is highly possible for some critical features to be excluded from the feature set. Second, the semantic and the structural similarities are usually computed independently, and then they are combined in an ad-hoc way where the weights are determined heuristically. This paper proposes the modified Parse Tree kernel (MPTK) for ontology alignment. In order to compute the similarity between entities in the ontologies, a Tree is adopted as a representation of an ontology. After transforming an ontology into a set of Trees, their similarity is computed using MPTK without explicit enumeration of features. In computing the similarity between Trees, the approximate string matching is adopted to naturally reflect not only the structural information but also the semantic information. According to a series of experiments with a standard data set, the kernel method outperforms other structural similarities such as GMO. In addition, the proposed method shows the state-of-the-art performance in the ontology alignment.
-
An ontology alignment based on Parse Tree kernel for combining structural and semantic information without explicit enumeration of features
Proceedings - 2008 IEEE WIC ACM International Conference on Web Intelligence WI 2008, 2008Co-Authors: Jeong Woo Son, Seong-bae Park, Se-young ParkAbstract:The ontology alignment has two kinds of major problems. First, the features used for ontology alignment are usually defined by experts, but it is highly possible for some critical features to be excluded from the feature set. Second, the semantic and the structural similarities are usually computed independently, and then they are combined in an ad-hoc way where the weights are determined heuristically. This paper proposes the modified Parse Tree kernel (MPTK) for ontology alignment. In order to compute the similarity between entities in the ontologies, a Tree is adopted as a representation of an ontology. After transforming an ontology into a set of Trees, their similarity is computed using MPTK without explicit enumeration of features. In computing the similarity between Trees,the approximate string matching is adopted to naturally reflect not only the structural information but also the semantic information. According to a series of experiments with a standard data set, the kernel method outperforms other structural similarities such as GMO. In addition, the proposed method shows the state-of-the-art performance in the ontology alignment.
