@inproceedings{007732d293f54c6f89de774f00aa47ef,
title = "Collaborative entity extraction and translation",
abstract = "Entity extraction is the task of identifying names and nominal phrases ('mentions') in a text and linking coreferring mentions. We propose the use of a new source of data for improving entity extraction: the information gleaned from large bitexts and captured by a statistical, phrase-based machine translation system. We translate the individual mentions and test properties of the translated mentions, as well as comparing the translations of coreferring mentions. The results provide feedback to improve source language entity extraction. Experiments on Chinese and English show that this approach can significantly improve Chinese entity extraction (2.2%-relative improvement in name tagging F-measure, representing a 15.0% error reduction), as well as Chinese to English entity translation (9.1% relative improvement in F-measure), over state-of-the-art entity extraction and machine translation systems.",
keywords = "Joint inference, Machine translation, Named entities",
author = "Heng Ji and Ralph Grishman",
year = "2007",
language = "English (US)",
series = "International Conference Recent Advances in Natural Language Processing, RANLP",
publisher = "Association for Computational Linguistics (ACL)",
pages = "303--309",
editor = "Galia Angelova and Kalina Bontcheva and Ruslan Mitkov and Nicolas Nicolov and Nikolai Nikolov",
booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings",
note = "International Conference Recent Advances in Natural Language Processing, RANLP 2007 ; Conference date: 27-09-2007 Through 29-09-2007",
}