Difference between revisions of "Gildea and Jurafsky Computational Linguistics 2002"
PastStudents (talk | contribs) (Created page with '== Citation == Daniel Gildea and Daniel Jurafsky. 2002. Automatic Labeling of Semantic Roles. Computational Linguistics, 28(3):245-288. == Online version == [http://delivery.a…') |
PastStudents (talk | contribs) |
||
| (10 intermediate revisions by the same user not shown) | |||
| Line 5: | Line 5: | ||
== Online version == | == Online version == | ||
| − | [http:// | + | [http://www.mitpressjournals.org/doi/pdf/10.1162/089120102760275983 MIT Press] |
== Summary == | == Summary == | ||
| − | The [[Category::paper]] presents a | + | The [[Category::paper]] presents a system for [[AddressesProblem::Semantic Role Labeling]], whose roles are defined at the level of semantic frames of the type. For instance, the JUDGEMENT frame contains roles like JUDGE, EVALUEE, and REASON, amd tje STATEMENT frame contains roles like SPEAKER, ADDRESSEE, and MESSAGE. |
| − | + | (1) [She''/Judge''] '''blames''' [the Government''/Evaluee''][for failing to do enough to help''/Reason'']. | |
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | + | (2) ["I'll knock on your door at quarter to six"''/Message''][Susan''/Speaker''] '''said'''. | |
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | + | They define semantic roles at the frame level. They use the [[UsesDataset::FrameNet]] database including nouns and adjectives as well as verbs. However, they also did experiments on more general semantic role (thematic role) labeling. | |
| + | |||
| + | |||
| + | Their job is mainly divided into two tasks: finding the frame boundaries and assigning the semantic role to the frames. | ||
| + | |||
| + | |||
| + | Features used for probability estimation for roles 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 [[UsesMethod::linear interpolation]][http://en.wikipedia.org/wiki/Linear_interpolation], EM linear interpolation, geometric mean [http://en.wikipedia.org/wiki/Geometric_mean], backoff lineanr 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. | ||
| + | |||
| + | == Key Contribution == | ||
| + | This system is the first statistical model on FrameNet solving the semantic role labeling problem, and future systems use the features introduced in this paper as a baseline. This paper is also very worth to read in that it describes the whole process of semantic role labeling in detail. In addition, 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::Palmer et al Computational Linguistics 2005]] which applies the features and the probability model here to the PropBank dataset. | |
| − | An interesting follow-up paper is [[RelatedPaper:: | ||
Latest revision as of 22:21, 30 November 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, whose roles are defined at the level of semantic frames of the type. For instance, the JUDGEMENT frame contains roles like JUDGE, EVALUEE, and REASON, amd tje STATEMENT frame contains roles like SPEAKER, ADDRESSEE, and MESSAGE.
(1) [She/Judge] blames [the Government/Evaluee][for failing to do enough to help/Reason].
(2) ["I'll knock on your door at quarter to six"/Message][Susan/Speaker] said.
They define semantic roles at the frame level. They use the FrameNet database including nouns and adjectives as well as verbs. However, they also did experiments on more general semantic role (thematic role) labeling.
Their job is mainly divided into two tasks: finding the frame boundaries and assigning the semantic role to the frames.
Features used for probability estimation for roles 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[1], EM linear interpolation, geometric mean [2], backoff lineanr 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.
Key Contribution
This system is the first statistical model on FrameNet solving the semantic role labeling problem, and future systems use the features introduced in this paper as a baseline. This paper is also very worth to read in that it describes the whole process of semantic role labeling in detail. In addition, 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 Palmer et al Computational Linguistics 2005 which applies the features and the probability model here to the PropBank dataset.
