4 |
Structured generative models for unsupervised named-entity clustering
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking
|
|
|
|
Abstract:
Discriminative reranking is one method for constructing high-performance statistical parsers (Collins, 2000). A discriminative reranker requires a source of candidate parses for each sentence. This paper describes a simple yet novel method for constructing sets of 50-best parses based on a coarse-to-fine generative parser (Charniak, 2000). This method generates 50-best lists that are of substantially higher quality than previously obtainable. We used these parses as the input to a MaxEnt reranker (Johnson et al., 1999; Riezler et al., 2002) that selects the best parse from the set of parses for each sentence, obtaining an f-score of 91.0% on sentences of length 100 or less. ; 8 page(s)
|
|
Keyword:
080100 Artificial Intelligence and Image Processing; 200400 Linguistics
|
|
URL: http://hdl.handle.net/1959.14/154926
|
|
BASE
|
|
Hide details
|
|
17 |
Sentence-Internal Prosody Does not Help Parsing the Way Punctuation Does
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Noun-phrase co-occurrence statistics for semi-automatic semantic lexicon construction ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|