DE eng

Search in the Catalogues and Directories

Hits 1 – 16 of 16

1
Induction of probabilistic synchronous tree-insertion grammars for machine translation
In: http://www.mt-archive.info/amta-2006-nesson.pdf (2006)
BASE
Show details
2
Induction of probabilistic synchronous tree-insertion grammars for machine translation
In: http://www.eecs.harvard.edu/~shieber/Biblio/Papers/Nesson-2006-IPS.pdf (2006)
BASE
Show details
3
The LinGO Redwoods Treebank -- Motivation and Preliminary Applications
In: http://nlp.stanford.edu/cmanning/papers/Coling2002.ps (2002)
BASE
Show details
4
The LinGO Redwoods Treebank -- Motivation and Preliminary Applications
In: http://www.stanford.edu/~krist/papers/Coling2002.pdf (2002)
BASE
Show details
5
The LinGO Redwoods Treebank -- Motivation and Preliminary Applications
In: http://lingo.stanford.edu/pubs/oe/coling2002.ps (2002)
BASE
Show details
6
Anaphoric Dependencies in Ellipsis
In: http://www.ai.sri.com/~kehler/Papers/ellipsis-squib.ps.gz (1997)
BASE
Show details
7
Anaphoric Dependencies in Ellipsis
In: http://www.eecs.harvard.edu/~shieber/papers/ellipsis-prag-squib.ps.gz (1997)
BASE
Show details
8
History Review
In: http://wing.comp.nus.edu.sg/~antho/J/J05/J05-3006.pdf (1986)
BASE
Show details
9
and Applied Sciences Harvard University
In: http://tagplus9.cs.sfu.ca/papers/NessonShieber.pdf
BASE
Show details
10
Referring-Expression Generation Using a Transformation-Based Learning Approach
In: http://www.aaai.org/Papers/FLAIRS/2006/Flairs06-016.pdf
BASE
Show details
11
Squibs and Discussions: Anaphoric Dependencies in Ellipsis
In: http://acl.ldc.upenn.edu/J/J97/J97-3005.pdf
BASE
Show details
12
Unifying Annotated Discourse Hierarchies to Create a Gold Standard
In: http://www.eecs.harvard.edu/~gal/cgsg.pdf
Abstract: Human annotation of discourse corpora typically results in segmentation hierarchies that vary in their degree of agreement. This paper presents several techniques for unifying multiple discourse annotations into a single hierarchy, deemed a "gold standard" --- the segmentation that best captures the underlying linguistic structure of the discourse. It proposes and analyzes methods that consider the level of embeddedness of a segmentation as well as methods that do not. A corpus containing annotated hierarchical discourses, the Boston Directions Corpus, was used to evaluate the "goodness" of each technique, by comparing the similarity of the segmentation it derives to the original annotations in the corpus. Several metrics of similarity between hierarchical segmentations are computed: precision/recall of matching utterances, pairwise inter-reliability scores ( ), and non-crossing-brackets. A novel method for unification that minimizes conflicts among annotators outperforms methods that require consensus among a majority for the and precision metrics, while capturing much of the structure of the discourse. When high recall is preferred, methods requiring a majority are preferable to those that demand full consensus among annotators.
URL: http://www.eecs.harvard.edu/~gal/cgsg.pdf
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.9357
BASE
Hide details
13
A Context Free TAG Variant
In: http://aclweb.org/anthology/P/P13/P13-1030.pdf
BASE
Show details
14
Unifying Annotated Discourse Hierarchies to Create a Gold Standard
In: http://www.eecs.harvard.edu/~mcarbone/pub/cgsg.pdf
BASE
Show details
15
The LinGO Redwoods Treebank -- Motivation and Preliminary Applications
In: http://acl.ldc.upenn.edu/C/C02/C02-2025.pdf
BASE
Show details
16
2004) Unifying annotated discourse hierarchies to create a gold standard
In: http://www.sigdial.org/workshops/workshop5/proceedings/pdf/carbone.pdf
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
16
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern