| other,24-2-J05-1003,ak | initial <term> ranking </term> of these <term> | parses | </term> . A second <term> model </term> then | #8052 The base parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initial ranking of theseparses. | |
| other,23-7-J05-1003,ak | evidence from an additional 500,000 <term> | features | </term> over <term> parse trees </term> that | #8187 The method combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000features over parse trees that were not included in the original model. | |
| other,10-3-J05-1003,ak | attempts to improve upon this initial <term> | ranking | </term> , using additional <term> features </term> | #8064 A second model then attempts to improve upon this initialranking, using additional features of the tree as evidence. | |
| other,26-4-J05-1003,ak | , without concerns about how these <term> | features | </term> interact or overlap and without the | #8101 The strength of our approach is that it allows a tree to be represented as an arbitrary set of features, without concerns about how thesefeatures interact or overlap and without the need to define a derivation or a generative model which takes these features into account. | |
| model,40-4-J05-1003,ak | define a <term> derivation </term> or a <term> | generative model | </term> which takes these <term> features </term> | #8115 The strength of our approach is that it allows a tree to be represented as an arbitrary set of features, without concerns about how these features interact or overlap and without the need to define a derivation or agenerative model which takes these features into account. | |
| tech,43-12-J05-1003,ak | <term> machine translation </term> , or <term> | natural language generation | </term> . We present a novel method for discovering | #8344 Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, ornatural language generation. | |
| model,18-8-J05-1003,ak | <term> F-measure error </term> over the <term> | baseline model ’s | </term> score of 88.2 % . The article also | #8218 The new model achieved 89.75% F-measure, a 13% relative decrease in F-measure error over thebaseline model ’s score of 88.2%. | |
| model,2-3-J05-1003,ak | these <term> parses </term> . A second <term> | model | </term> then attempts to improve upon this | #8056 A secondmodel then attempts to improve upon this initial ranking, using additional features of the tree as evidence. | |
| other,10-4-J05-1003,ak | of our approach is that it allows a <term> | tree | </term> to be represented as an arbitrary | #8085 The strength of our approach is that it allows atree to be represented as an arbitrary set of features, without concerns about how these features interact or overlap and without the need to define a derivation or a generative model which takes these features into account. | |
| tech,1-2-J05-1003,ak | <term> probabilistic parser </term> . The <term> | base parser | </term> produces a set of <term> candidate | #8029 Thebase parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initial ranking of these parses. | |
| other,16-9-J05-1003,ak | </term> which takes advantage of the <term> | sparsity | </term> of the <term> feature space </term> in | #8242 The article also introduces a new algorithm for the boosting approach which takes advantage of thesparsity of the feature space in the parsing data. | |
| tech,23-12-J05-1003,ak | should be applicable to many other <term> | NLP problems | </term> which are naturally framed as <term> | #8324 Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many otherNLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation. | |
| other,37-4-J05-1003,ak | overlap and without the need to define a <term> | derivation | </term> or a <term> generative model </term> | #8112 The strength of our approach is that it allows a tree to be represented as an arbitrary set of features, without concerns about how these features interact or overlap and without the need to define aderivation or a generative model which takes these features into account. | |
| tech,8-12-J05-1003,ak | experiments in this article are on <term> | natural language parsing ( NLP ) | </term> , the approach should be applicable | #8309 Although the experiments in this article are onnatural language parsing ( NLP ), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation. | |
| other,16-2-J05-1003,ak | input sentence </term> , with associated <term> | probabilities | </term> that define an initial <term> ranking | #8044 The base parser produces a set of candidate parses for each input sentence, with associatedprobabilities that define an initial ranking of these parses. | |
| other,7-5-J05-1003,ak | We introduce a new method for the <term> | reranking task | </term> , based on the <term> boosting approach | #8131 We introduce a new method for thereranking task, based on the boosting approach to ranking problems described in Freund et al. (1998). | |
| tech,9-9-J05-1003,ak | a new <term> algorithm </term> for the <term> | boosting approach | </term> which takes advantage of the <term> | #8235 The article also introduces a new algorithm for theboosting approach which takes advantage of the sparsity of the feature space in the parsing data. | |
| tech,15-10-J05-1003,ak | the obvious implementation of the <term> | boosting approach | </term> . We argue that the method is an | #8267 Experiments show significant efficiency gains for the new algorithm over the obvious implementation of theboosting approach. | |
| other,17-3-J05-1003,ak | additional <term> features </term> of the <term> | tree | </term> as evidence . The strength of our | #8071 A second model then attempts to improve upon this initial ranking, using additional features of thetree as evidence. | |
| other,25-7-J05-1003,ak | additional 500,000 <term> features </term> over <term> | parse trees | </term> that were not included in the original | #8189 The method combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features overparse trees that were not included in the original model. |
