2015 AJointDependencyModelofMorpholo

(Sennrich & Haddow, 2015) ⇒ Rico Sennrich, and Barry Haddow. (2015). “A Joint Dependency Model of Morphological and Syntactic Structure for Statistical Machine Translation.” In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015). DOI:10.18653/v1/D15-1248.

Subject Headings: Sennrich-Haddow Syntax-Based SMT System; Statistical Machine Translation System; Morphological Analysis, WMT English‐to-German Translation Task.

Notes

Link(s):
- ACL Anthology: https://www.aclweb.org/anthology/D15-1248/
- DBLP: https://dblp.org/rec/html/conf/emnlp/SennrichH15

Cited By

Google Scholar: ~ 12 Citations, Retrieved: 2020-06-14.
Semantic Scholar: ~ 13 Citations, Retrieved: 2020-06-14.
MS Academic: ~ 12 Citations, Retrieved: 2020-06-14.

Quotes

Abstract

When translating between two languages that differ in their degree of morphological synthesis, syntactic structures in one language may be realized as morphological structures in the other, and SMT models need a mechanism to learn such translations. Prior work has used morpheme splitting with flat representations that do not encode the hierarchical structure between morphemes, but this structure is relevant for learning morphosyntactic constraints and selectional preferences. We propose to model syntactic and morphological structure jointly in a dependency translation model, allowing the system to generalize to the level of morphemes. We present a dependency representation of German compounds and particle verbs that results in improvements in translation quality of 1.4-1.8 BLEU in the WMT English-German translation task

References

BibTeX

@inproceedings{2015_AJointDependencyModelofMorpholo,
  author    = {Rico Sennrich and
               Barry Haddow},
  editor    = {Lluis Marquez and
               Chris Callison-Burch and
               Jian Su and
               Daniele Pighin and
               Yuval Marton},
  title     = {A Joint Dependency Model of Morphological and Syntactic Structure
               for Statistical Machine Translation},
  booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural
               Language Processing (EMNLP 2015)},
  pages     = {2081--2087},
  publisher = {The Association for Computational Linguistics},
  year      = {2015},
  url       = {https://www.aclweb.org/anthology/D15-1248},
  doi       = {10.18653/v1/d15-1248},
  address   = {Lisbon, Portugal},
  date      = {September 17-21},
}

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2015 AJointDependencyModelofMorpholo	Barry Haddow Rico Sennrich			A Joint Dependency Model of Morphological and Syntactic Structure for Statistical Machine Translation