Difference between revisions of "Gildea and Jurafsky Computational Linguistics 2002"
PastStudents (talk | contribs) |
PastStudents (talk | contribs) |
||
| Line 9: | Line 9: | ||
== Summary == | == Summary == | ||
| − | The [[Category::paper]] presents a system for [[AddressesProblem::Semantic Role Labeling]]. | + | The [[Category::paper]] presents a system for [[AddressesProblem::Semantic Role Labeling]]. This paper describes the process of semantic role labeling in detail, and is very helpful to understand the whole process. Their job is mainly divided into two tasks: finding the frame boundaries and assigning the semantic role to the frames. |
| − | They | + | They define semantic roles at the frame level. They use the FrameNet database including nouns and adjectives as well as verbs. In addition, they also did experiments on more general semantic role (thematic role) labeling. |
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | + | Features used in this system include phrase type, governing category, parse tree path, position, voice, and head word. They built a classifier by combining probabilities from distributions conditioned on a variety of subsets of the features because they will have seen the combination of all features only a small number of times, providing a poor estimate of the probability. To combine the strengths of the various distributions, they used various ways to obtain an estimate of the full distribution, such as linear interpolation, EM linear interpolation, geometric mean, backoff linear interpolation, and backoff geometric mean. | |
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| + | To generalize lexical statistics, they compared three different approaches: automatic clustering, use of a hand-built ontological resource, WordNet, and boostrapping. Automatic clustering and WordNet hierarchy were used only for noun phrases. | ||
| − | + | The system gives 82% accuracy in identifying the semantic role of pre-segmented constituents, 65% precision and 61% recall in both segmenting constituents and identifying their semantic role. In this paper, they did many various experiments to find out which features, algorithms, and techniques affect the performance of the system. | |
== Related papers == | == Related papers == | ||
An interesting follow-up paper is [[RelatedPaper::Denecke and Bernauer AIME 2007]] which uses semantic structures to extract medical information. | An interesting follow-up paper is [[RelatedPaper::Denecke and Bernauer AIME 2007]] which uses semantic structures to extract medical information. | ||
Revision as of 02:02, 31 October 2010
Citation
Daniel Gildea and Daniel Jurafsky. 2002. Automatic Labeling of Semantic Roles. Computational Linguistics, 28(3):245-288.
Online version
Summary
The paper presents a system for Semantic Role Labeling. This paper describes the process of semantic role labeling in detail, and is very helpful to understand the whole process. Their job is mainly divided into two tasks: finding the frame boundaries and assigning the semantic role to the frames.
They define semantic roles at the frame level. They use the FrameNet database including nouns and adjectives as well as verbs. In addition, they also did experiments on more general semantic role (thematic role) labeling.
Features used in this system include phrase type, governing category, parse tree path, position, voice, and head word. They built a classifier by combining probabilities from distributions conditioned on a variety of subsets of the features because they will have seen the combination of all features only a small number of times, providing a poor estimate of the probability. To combine the strengths of the various distributions, they used various ways to obtain an estimate of the full distribution, such as linear interpolation, EM linear interpolation, geometric mean, backoff linear interpolation, and backoff geometric mean.
To generalize lexical statistics, they compared three different approaches: automatic clustering, use of a hand-built ontological resource, WordNet, and boostrapping. Automatic clustering and WordNet hierarchy were used only for noun phrases.
The system gives 82% accuracy in identifying the semantic role of pre-segmented constituents, 65% precision and 61% recall in both segmenting constituents and identifying their semantic role. In this paper, they did many various experiments to find out which features, algorithms, and techniques affect the performance of the system.
Related papers
An interesting follow-up paper is Denecke and Bernauer AIME 2007 which uses semantic structures to extract medical information.
