Pronoun Prediction with Latent Anaphora Resolution

Christian Hardmeier

doi:10.18653/v1/W16-2350

Pronoun Prediction with Latent Anaphora Resolution

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

Abstract

This paper describes the UU-Hardmeier submissions to the WMT 2016 shared task on cross-lingual pronoun prediction. Our model is a system combination of two different approaches, one based on a neural network with latent anaphora resolution and the other one on an n-gram model with an additional dependency on the source pronoun. The combination of the two models results in an improvement over each individual system, but it appears that the contribution of the neural network is more likely due to its context modelling capacities than to the anaphora resolution subnetwork.

Originalsprog	Engelsk
Titel	Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers
Antal sider	5
Publikationsdato	12 aug. 2016
DOI	https://doi.org/10.18653/v1/W16-2350
Status	Udgivet - 12 aug. 2016
Udgivet eksternt	Ja

Adgang til dokumentet

10.18653/v1/W16-2350

Citationsformater

@inproceedings{bc189c0269ec4b0ab9dd3f60665f55d9,

title = "Pronoun Prediction with Latent Anaphora Resolution",

abstract = "This paper describes the UU-Hardmeier submissions to the WMT 2016 shared task on cross-lingual pronoun prediction. Our model is a system combination of two different approaches, one based on a neural network with latent anaphora resolution and the other one on an n-gram model with an additional dependency on the source pronoun. The combination of the two models results in an improvement over each individual system, but it appears that the contribution of the neural network is more likely due to its context modelling capacities than to the anaphora resolution subnetwork.",

author = "Christian Hardmeier",

year = "2016",

month = aug,

day = "12",

doi = "10.18653/v1/W16-2350",

language = "English",

booktitle = "Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers",

}

TY - GEN

T1 - Pronoun Prediction with Latent Anaphora Resolution

AU - Hardmeier, Christian

PY - 2016/8/12

Y1 - 2016/8/12

N2 - This paper describes the UU-Hardmeier submissions to the WMT 2016 shared task on cross-lingual pronoun prediction. Our model is a system combination of two different approaches, one based on a neural network with latent anaphora resolution and the other one on an n-gram model with an additional dependency on the source pronoun. The combination of the two models results in an improvement over each individual system, but it appears that the contribution of the neural network is more likely due to its context modelling capacities than to the anaphora resolution subnetwork.

AB - This paper describes the UU-Hardmeier submissions to the WMT 2016 shared task on cross-lingual pronoun prediction. Our model is a system combination of two different approaches, one based on a neural network with latent anaphora resolution and the other one on an n-gram model with an additional dependency on the source pronoun. The combination of the two models results in an improvement over each individual system, but it appears that the contribution of the neural network is more likely due to its context modelling capacities than to the anaphora resolution subnetwork.

U2 - 10.18653/v1/W16-2350

DO - 10.18653/v1/W16-2350

M3 - Article in proceedings

BT - Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

ER -

Pronoun Prediction with Latent Anaphora Resolution

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater