{"type":"ScholarlyArticle","title":"Discriminative Reordering Model Adaptation via Structural Learning","authors":[{"name":"Biao Zhang","slug":"biao-zhang","given":"Biao","family":"Zhang","affiliation":""},{"name":"Jinsong Su","slug":"jinsong-su","given":"Jinsong","family":"Su","affiliation":""},{"name":"Deyi Xiong","slug":"deyi-xiong","given":"Deyi","family":"Xiong","affiliation":""},{"name":"Hong Duan","slug":"hong-duan","given":"Hong","family":"Duan","affiliation":""},{"name":"Junfeng Yao","slug":"junfeng-yao","given":"Junfeng","family":"Yao","affiliation":""}],"abstract":"Reordering model adaptation remains a big challenge in statistical machine translation because reordering patterns of translation units often vary dramatically from one domain to another. In this paper, we propose a novel adaptive discriminative reordering model (DRM) based on structural learning, which can capture correspondences among reordering features from two different domains. Exploiting both in-domain and out-of-domain monolingual corpora, our model learns a shared feature representation for cross-domain phrase reordering. Incorporating features of this representation, the DRM trained on out-of-domain corpus generalizes better to in-domain data. Experiment results on the NIST Chinese-English translation task show that our approach significantly outperforms a variety of baselines.","doi":null,"url":"https://ijcai.org/proceedings/2015/151","pdf":"https://ijcai.org/proceedings/2015/0151.pdf","markdown":"https://ijcai.org/proceedings/2015/151.md","bibtex":"https://ijcai.org/proceedings/2015/bibtex/151","volume":{"slug":"2015","title":"Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2015","url":"https://ijcai.org/proceedings/2015/","year":2015,"location":"Buenos Aires, Argentina","dates":"25–31 July 2015","editors":"Qiang Yang and Michael Wooldridge","isbn":"978-1-57735-738-4","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Machine Learning","track":"Main Track","number":151,"pages":{"first":1040,"last":1045},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}