H. Alshawi, S. Bangalore, and S. Douglas. 2000. Learning dependency translation models as collections of finite state head transducers. CL, 26(1):45--60.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....that annotators agree with each other more consistently when performing word level alignments on bitext with divergence handling. 2 Related Work Recently, researchers have extended traditional statistical machine translation (MT) models [4, 5] to include the syntactic structures of the languages [2, 3, 23]. These statistical transfer systems appear to be similar in nature to what we are proposing projecting from English to a foreign language tree but both the method of generation and the goal behind these approaches are different from ours. In these alternative approaches, parses are generated ....

Alshawi, H., Bangalore, S., Douglas, S.: Learning Dependency Translation Models as Collections of Finite State Head Transducers. Computational Linguistics. Vol. 26 (2000)

....VB He PRP music NN to TO VB ha no ga desu VB2 TO VB listening adores VB1 He PRP music NN to TO VB ha no ga desu VB2 TO VB PRP NN TO VB1 kare ongaku kiku daisuki wo Figure 1: Channel Operations: Reorder, Insert, and Translate nested structures. Wu (1997) and Alshawi et al. 2000) showed statistical models based on syntactic structure. The way we handle syntactic parse trees is inspired by their work, although their approach is not to model the translation process, but to formalize a model that generates two languages at the same time. Our channel operations are also ....

H. Alshawi, S. Bangalore, and S. Douglas. 2000. Learning dependency translation models as collections of finite state head transducers. Computational Linguistics, 26(1).

....seeks to show that empirically measurable properties of strings suffice to learn automatic classifiers (or, more generally, scoring functions) to support the hypothesis that translation ness is an observable property of some bi texts. Following an intuition made explicit by Alshawi et al. [ABD00], I suggest that a profitable approach may be to avoid artificial meaning representations in favor of the most natural ones the strings themselves. 4 1.1 Potential Applications I suggest four practical applications of such a scoring function. The first is in parallel corpus construction ....

Alshawi, Iliyan, Srinivas Bangalore, and Shona Douglas (2000). Learning Dependency Translation Models as Collections of Finite State Head Transducers. Computational Linguistics 26(1), January.

No context found.

H. Alshawi, S. Bangalore, and S. Douglas. 2000. Learning dependency translation models as collections of finite state head transducers. CL, 26(1):45--60.

No context found.

Alshawi, H., Douglas, S., & Bangalore, S. (2000). Learning Dependency Translation Models as Collections of Finite-State Head Transducers. Computational Linguistics, 26.

No context found.

Hiyan Alshawi, Srinivas Bangalore, and Shona Douglas. 2000. Learning dependency translation models as collections of finite state head transducers. Computational Linguistics, 26(1):45--60.

No context found.

Alshawi, H., Bangalore, S., and Douglas, S. (2000). Learning Dependency Translation Models as Collections of Finite State Head Transducers. Computational Linguistics, 26(1).

No context found.

H. Alshawi, S. Bangalore, and S. Douglas, "Learning dependency translation models as collections of finite state head transducers," Computational Linguistics, vol. 26, 2000.

No context found.

Alshawi, H., Srinivas, B., Douglas, S.: Learning dependency translation models as collections of nite state head transducers. Computational Linguistics 26 (2000)

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC