Báo cáo khoa học: "Discovering Sociolinguistic Associations with Structured Sparsity" doc

... June 19-24, 2011. c 2011 Association for Computational Linguistics Discovering Sociolinguistic Associations with Structured Sparsity Jacob Eisenstein Noah A. Smith Eric P. Xing School of Computer ... contribution are inadequate. In this paper, we explore the large space of po- tential sociolinguistic associations using structured sparsity. We treat the relationship between lang...

Ngày tải lên: 17/03/2014, 00:20

... of translation edit rate with targeted human annotation. In AMTA. Valentin I. Spitkovsky, Hiyan Alshawi, and Daniel Juraf- sky. 2011. Lateen em: Unsupervised training with multiple objectives, ... different metrics M k (h) for evaluating the quality of h. Without loss of gen- erality, we assume metric scores are bounded be- tween 0 and 1, with 1 being perfect. Each hypoth- esis h can be...

Ngày tải lên: 19/02/2014, 19:20

... experimented on a document clustering task. 1 Introduction In natural language processing (NLP) and text min- ing, clustering methods are crucial for various tasks such as document clustering. ... authors also justified their method by showing that with feature hashing, dot- product is unbiased, and the length of each vector is well-preserved with high probability under some conditions. Pl...

Ngày tải lên: 20/02/2014, 05:20

... scenarios, there were sig- nificant numbers of ESDs both with the minimum length of 5 and the maximum length of 16 and ev- erything in between. Combined with the fact that 93% of all individual event descriptions ... two phrases if they are semantically similar, i.e. it should cost more to align ‘exit’ with ‘eat’ than ‘exit’ with ‘leave’. Thus we take a measure of se- mantic (dis)simil...

Ngày tải lên: 07/03/2014, 22:20

... report L2P performance without any syllabification infor- mation, with perfect dictionary syllabification, and with our small learned models of syllabification. L2P performance with dictionary syllabification ... explained in far more detail in (Tsochantaridis et al., 2004). 4 Syllabification with Structured SVMs In this paper we apply structured SVMs to the syl- labification problem. S...

Ngày tải lên: 17/03/2014, 02:20

... allows a subject NP to com- bine with a transitive verb before the verb has com- bined with its object. In (3b), a sentence em- bedding verb is composed with a raised subject NP. Note that ... anything that can be proven with x can equivalently be proven with y. (16) x y X 0 Z Normalisation and the Dependency Calculus These efficiency problems for parsing with the DC ca...

Ngày tải lên: 17/03/2014, 08:20

... develop a novel structured label propagation method for structured learning problems, such as machine translation. Note that, the structured label propagation can be applied to other structured ... training. The entire process starts with a decoder without consensus features. Then a graph is constructed out of all training, dev, and test data. The subsequent structured label...

Ngày tải lên: 23/03/2014, 14:20

... the “music” sense. Document theme: Sometimes, the same pattern can express different relations in different docu- ments, depending on the document’s theme. For instance, in a document about politics, ... argument are added with prefix “lc:”. Similarly the two words to the right of the destination arguments are added with prefix “rc:”. Each document in the NYT corpus is associated with man...

Ngày tải lên: 23/03/2014, 14:20

... jointly with it, not added in afterwards. Moreover, we expect empty-element recovery to improve as the parsing quality improves. Our method makes use of a strong syntactic model, the PCFGs with ... VBZ. is . WHNP. WP. who (a) (b) Figure 2: English parse tree with empty elements marked. (a) As annotated in the Penn Treebank. (b) With empty elements reconfigured and slash categories...

Ngày tải lên: 23/03/2014, 16:20

... We show empirically that the structured preferences are crucial to the suc- cess of our task. Our model, trained with- out annotated data and with a small number of structured preferences, yields ... D. Roth. 2010b. Structured output learning with indirect super- vision. In Proc. ICML’10. K. Ganchev, J. Grac¸a, J. Gillenwater, and B. Taskar. 2010. Posterior regularization for str...

Ngày tải lên: 30/03/2014, 17:20