The Experts below are selected from a list of 18804 Experts worldwide ranked by ideXlab platform
Pierre Nugues - One of the best experts on this subject based on the ideXlab platform.
-
The effect of Syntactic Representation on semantic role labeling
Proceedings of the 22nd International Conference on Computational Linguistics - COLING '08, 2008Co-Authors: Richard Johansson, Pierre NuguesAbstract:Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a Syntactic structure from the sentence being analyzed. This makes the choice of Syntactic Representation an essential design decision. In this paper, we study the influence of Syntactic Representation on the performance of SRL systems. Specifically, we compare constituent-based and dependency-based Representations for SRL of English in the FrameNet paradigm. Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependency-based systems perform slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data.
-
COLING - The Effect of Syntactic Representation on Semantic Role Labeling
Proceedings of the 22nd International Conference on Computational Linguistics - COLING '08, 2008Co-Authors: Richard Johansson, Pierre NuguesAbstract:Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a Syntactic structure from the sentence being analyzed. This makes the choice of Syntactic Representation an essential design decision. In this paper, we study the influence of Syntactic Representation on the performance of SRL systems. Specifically, we compare constituent-based and dependency-based Representations for SRL of English in the FrameNet paradigm. Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependency-based systems perform slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data.
-
Syntactic Representations Considered for Frame-semantic Analysis
2007Co-Authors: Richard Johansson, Pierre NuguesAbstract:We address the question of which Syntactic Representation is best suited for FrameNet-based semantic analysis of English text. We compare analyzers based on dependencies and constituents, and a dependency syntax with a rich set of grammatical functions with one with a smaller set. Our study demonstrates that dependency-based and constituent-based analyzers give roughly equivalent performance, and that a richer set of functions has a positive influence on argument classification for verbs.
Richard Johansson - One of the best experts on this subject based on the ideXlab platform.
-
The effect of Syntactic Representation on semantic role labeling
Proceedings of the 22nd International Conference on Computational Linguistics - COLING '08, 2008Co-Authors: Richard Johansson, Pierre NuguesAbstract:Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a Syntactic structure from the sentence being analyzed. This makes the choice of Syntactic Representation an essential design decision. In this paper, we study the influence of Syntactic Representation on the performance of SRL systems. Specifically, we compare constituent-based and dependency-based Representations for SRL of English in the FrameNet paradigm. Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependency-based systems perform slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data.
-
COLING - The Effect of Syntactic Representation on Semantic Role Labeling
Proceedings of the 22nd International Conference on Computational Linguistics - COLING '08, 2008Co-Authors: Richard Johansson, Pierre NuguesAbstract:Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a Syntactic structure from the sentence being analyzed. This makes the choice of Syntactic Representation an essential design decision. In this paper, we study the influence of Syntactic Representation on the performance of SRL systems. Specifically, we compare constituent-based and dependency-based Representations for SRL of English in the FrameNet paradigm. Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependency-based systems perform slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data.
-
Dependency-based Semantic Analysis of Natural-language Text
2008Co-Authors: Richard JohanssonAbstract:Semantic roles, logical relations such as Agent or Instrument that hold between events and their participants and circumstances, need to be determined automatically by several types of applications in natural language processing. This process is referred to as semantic role labeling. This dissertation describes how to construct statistical models for semantic role labeling of English text, and how role semantics is related to surface syntax. It is generally agreed that the problem of semantic role labeling is closely tied to Syntactic analysis. Most previous implementations of semantic role labelers have used constituents as the Syntactic input, while dependency Representations, in which the Syntactic structure is viewed as a graph of labeled word-to-word relations, has received very little attention in comparison. Contrary to previous claims, this work demonstrates empirically that dependency Representations can serve as the input for semantic role labelers and achieve similar results. This is important theoretically since it makes the Syntactic-semantic interface conceptually simpler and more intuitive, but also has practical significance since there are languages for which constituent annotation is infeasible. The dissertation devotes considerable effort to investigating the relation between Syntactic Representation and semantic role labeling performance. Apart from the main result that dependency-based semantic role labeling rivals its constituent-based counterpart, the empirical experiments support two findings: First, that the dependency-Syntactic Representation has to be well-designed in order to achieve a good performance in semantic role labeling. Secondly, that the choice of Syntactic Representation affects the substages of the semantic role labeling task differently; above all, the role classification task, which relies strongly on lexical features, is shown to benefit from dependency Representations. The systems presented in this work have been evaluated in two international open evaluations, in both of which they achieved the top result. (Less)
-
Syntactic Representations Considered for Frame-semantic Analysis
2007Co-Authors: Richard Johansson, Pierre NuguesAbstract:We address the question of which Syntactic Representation is best suited for FrameNet-based semantic analysis of English text. We compare analyzers based on dependencies and constituents, and a dependency syntax with a rich set of grammatical functions with one with a smaller set. Our study demonstrates that dependency-based and constituent-based analyzers give roughly equivalent performance, and that a richer set of functions has a positive influence on argument classification for verbs.
Shiyong Kang - One of the best experts on this subject based on the ideXlab platform.
-
CLSW - Lexical Semantic Restrictions on the Syntactic Representation of the Semantic Roles of Pinjie Class
Lecture Notes in Computer Science, 2014Co-Authors: Zhen Tian, Shiyong KangAbstract:Based on semantic roles, this paper describes the building process of the Database of Lexical Semantic Constraints on the Syntactic Representation of the Semantic Role Instrument (LSCI). All the head words of optional arguments in the annotated corpus of Chinese text books of primary and middle schools are extracted and then tagged with semantic categories, Syntactic categories and semantic roles. Based on this database, we investigate the semantic roles of instrument, material, manner, cause and goal, and quantify the dependency strength of semantic categories on Syntactic positions.
-
lexical semantic restrictions on the Syntactic Representation of the semantic roles of pinjie class
Workshop on Chinese Lexical Semantics, 2014Co-Authors: Zhen Tian, Shiyong KangAbstract:Based on semantic roles, this paper describes the building process of the Database of Lexical Semantic Constraints on the Syntactic Representation of the Semantic Role Instrument (LSCI). All the head words of optional arguments in the annotated corpus of Chinese text books of primary and middle schools are extracted and then tagged with semantic categories, Syntactic categories and semantic roles. Based on this database, we investigate the semantic roles of instrument, material, manner, cause and goal, and quantify the dependency strength of semantic categories on Syntactic positions.
Martin J. Pickering - One of the best experts on this subject based on the ideXlab platform.
-
Syntactic Representation is independent of semantics in Mandarin: evidence from Syntactic priming
Language Cognition and Neuroscience, 2019Co-Authors: Xuemei Chen, Holly P. Branigan, Suiping Wang, Jian Huang, Martin J. PickeringAbstract:ABSTRACTTheories of language processing generally assume that speakers construct independent Representations for Syntactic and semantic information, based largely on evidence from English and relat...
-
It is there whether you hear it or not: Syntactic Representation of missing arguments
Cognition, 2014Co-Authors: Zhenguang G. Cai, Martin J. Pickering, Ruiming Wang, Holly P. BraniganAbstract:Many languages allow arguments to be omitted when they are recoverable from the context, but how do people comprehend sentences with a missing argument? We contrast a Syntactically-represented account whereby people postulate a Syntactic Representation for the missing argument, with a Syntactically-non-represented account whereby people do not postulate any Syntactic Representation for it. We report two structural priming experiments in Mandarin Chinese that showed that comprehension of a dative sentence with a missing direct-object argument primed the production of a full-form dative sentence (relative to an intransitive) and that it behaved similarly to a corresponding full-form dative sentence. The results suggest that people construct the same constituent structure for missing-argument sentences and full-form sentences, in accord with the Syntactically-represented account. We discuss the implications for Syntactic Representations in language processing.
-
Syntactic Representation in the lemma stratum.
The Behavioral and brain sciences, 2004Co-Authors: Holly P. Branigan, Martin J. PickeringAbstract:Levelt, Roelofs, & Meyer (henceforth Levelt et al. 1999) propose a model of production incorporating a lemma stratum, which is concerned with the Syntactic characteristics of lexical entries. We suggest that Syntactic priming experiments provide evidence about how such Syntactic information is represented, and that this evidence can be used to extend Levelt et al.'s model. Evidence from Syntactic priming experiments also supports Levelt et al.'s conjecture that the lemma stratum is shared between the production and comprehension systems.
Zhen Tian - One of the best experts on this subject based on the ideXlab platform.
-
CLSW - Lexical Semantic Restrictions on the Syntactic Representation of the Semantic Roles of Pinjie Class
Lecture Notes in Computer Science, 2014Co-Authors: Zhen Tian, Shiyong KangAbstract:Based on semantic roles, this paper describes the building process of the Database of Lexical Semantic Constraints on the Syntactic Representation of the Semantic Role Instrument (LSCI). All the head words of optional arguments in the annotated corpus of Chinese text books of primary and middle schools are extracted and then tagged with semantic categories, Syntactic categories and semantic roles. Based on this database, we investigate the semantic roles of instrument, material, manner, cause and goal, and quantify the dependency strength of semantic categories on Syntactic positions.
-
lexical semantic restrictions on the Syntactic Representation of the semantic roles of pinjie class
Workshop on Chinese Lexical Semantics, 2014Co-Authors: Zhen Tian, Shiyong KangAbstract:Based on semantic roles, this paper describes the building process of the Database of Lexical Semantic Constraints on the Syntactic Representation of the Semantic Role Instrument (LSCI). All the head words of optional arguments in the annotated corpus of Chinese text books of primary and middle schools are extracted and then tagged with semantic categories, Syntactic categories and semantic roles. Based on this database, we investigate the semantic roles of instrument, material, manner, cause and goal, and quantify the dependency strength of semantic categories on Syntactic positions.
