A Document-Level SMT System with Integrated Pronoun Prediction

Christian Hardmeier

doi:10.18653/v1/W15-2510

A Document-Level SMT System with Integrated Pronoun Prediction

Christian Hardmeier

Uppsala University

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

This paper describes one of Uppsala University’s submissions to the pronoun-focused machine translation (MT) shared task at DiscoMT 2015. The system is based on phrase-based statistical MT implemented with the document-level decoder Docent. It includes a neural network for pronoun prediction trained with latent anaphora resolution. At translation time, coreference information is obtained from the Stanford CoreNLP system.

Original language	English
Title of host publication	Proceedings of the Second Workshop on Discourse in Machine Translation
Publication date	21 Sept 2015
ISBN (Print)	978-1-941643-32-7
DOIs	https://doi.org/10.18653/v1/W15-2510
Publication status	Published - 21 Sept 2015
Externally published	Yes

Keywords

machine translation
pronoun-focused machine translation
document-level machine translation
coreference resolution
latent anaphora resolution

Access to Document

10.18653/v1/W15-2510

Cite this

@inproceedings{90515cb454ea4ae39b8e59f26f691563,

title = "A Document-Level SMT System with Integrated Pronoun Prediction",

abstract = "This paper describes one of Uppsala University{\textquoteright}s submissions to the pronoun-focused machine translation (MT) shared task at DiscoMT 2015. The system is based on phrase-based statistical MT implemented with the document-level decoder Docent. It includes a neural network for pronoun prediction trained with latent anaphora resolution. At translation time, coreference information is obtained from the Stanford CoreNLP system.",

keywords = "machine translation, pronoun-focused machine translation, document-level machine translation, coreference resolution, latent anaphora resolution",

author = "Christian Hardmeier",

year = "2015",

month = sep,

day = "21",

doi = "10.18653/v1/W15-2510",

language = "English",

isbn = "978-1-941643-32-7",

booktitle = "Proceedings of the Second Workshop on Discourse in Machine Translation",

}

TY - GEN

T1 - A Document-Level SMT System with Integrated Pronoun Prediction

AU - Hardmeier, Christian

PY - 2015/9/21

Y1 - 2015/9/21

N2 - This paper describes one of Uppsala University’s submissions to the pronoun-focused machine translation (MT) shared task at DiscoMT 2015. The system is based on phrase-based statistical MT implemented with the document-level decoder Docent. It includes a neural network for pronoun prediction trained with latent anaphora resolution. At translation time, coreference information is obtained from the Stanford CoreNLP system.

AB - This paper describes one of Uppsala University’s submissions to the pronoun-focused machine translation (MT) shared task at DiscoMT 2015. The system is based on phrase-based statistical MT implemented with the document-level decoder Docent. It includes a neural network for pronoun prediction trained with latent anaphora resolution. At translation time, coreference information is obtained from the Stanford CoreNLP system.

KW - machine translation

KW - pronoun-focused machine translation

KW - document-level machine translation

KW - coreference resolution

KW - latent anaphora resolution

U2 - 10.18653/v1/W15-2510

DO - 10.18653/v1/W15-2510

M3 - Article in proceedings

SN - 978-1-941643-32-7

BT - Proceedings of the Second Workshop on Discourse in Machine Translation

ER -

A Document-Level SMT System with Integrated Pronoun Prediction

Abstract

Keywords

Access to Document

Fingerprint

Cite this