Sciweavers

70 search results - page 9 / 14
» Automatic Evaluation of Linguistic Quality in Multi-Document...
Sort
View
NAACL
2010
13 years 5 months ago
Time-Efficient Creation of an Accurate Sentence Fusion Corpus
Sentence fusion enables summarization and question-answering systems to produce output by combining fully formed phrases from different sentences. Yet there is little data that ca...
Kathleen McKeown, Sara Rosenthal, Kapil Thadani, C...
COLING
2010
13 years 2 months ago
Learning Summary Content Units with Topic Modeling
In the field of multi-document summarization, the Pyramid method has become an important approach for evaluating machine-generated summaries. The method is based on the manual ann...
Leonhard Hennig, Ernesto William De Luca, Sahin Al...
LREC
2010
141views Education» more  LREC 2010»
13 years 9 months ago
Evaluating Distributional Properties of Tagsets
We investigate which distributional properties should be present in a tagset by examining different mappings of various current part-ofspeech tagsets, looking at English, German, ...
Markus Dickinson, Charles Jochim
COLING
2010
13 years 2 months ago
Extraction of Multi-word Expressions from Small Parallel Corpora
We present a general methodology for extracting multi-word expressions (of various types), along with their translations, from small parallel corpora. We automatically align the p...
Yulia Tsvetkov, Shuly Wintner
LREC
2008
141views Education» more  LREC 2008»
13 years 9 months ago
New Resources for Document Classification, Analysis and Translation Technologies
The goal of the DARPA MADCAT (Multilingual Automatic Document Classification Analysis and Translation) Program is to automatically convert foreign language text images into Englis...
Stephanie Strassel, Lauren Friedman, Safa Ismael, ...