Bridge the gap between statistical and hand-crafted grammars

Basirat, Ali; Faili, Heshaam

doi:10.1016/j.csl.2013.02.001

Cited by 2 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results are related to the output of the HMM-based LTAG-mapping phase, before applying the errorcorrection phase. In comparison with the values reported in Basirat and Faili (2013), the table shows a somewhat smaller value for POS agreement for the DTS-CSL, 92.50% as against 94.84%. This does not however convincingly demonstrate the superiority of the LTAG-mapping model proposed in Basirat and Faili (2013) over this other work.…”

Section: Part-of-speech Agreementmentioning

confidence: 48%

“…In comparison with the values reported in Basirat and Faili (2013), the table shows a somewhat smaller value for POS agreement for the DTS-CSL, 92.50% as against 94.84%. This does not however convincingly demonstrate the superiority of the LTAG-mapping model proposed in Basirat and Faili (2013) over this other work. This is mainly due to the fact that the POS agreement provides only an estimation of the true quality of the system, and the higher values for this criterion do not necessarily confirm the high quality of the sequences.…”

Section: Part-of-speech Agreementmentioning

confidence: 48%

“…Applying these methods depends on the availability of a probability distribution that associates probabilities to the pairs of elementary structures with respect to their syntactic environment. The mapping approaches proposed by Chiang and Rambow (2006), Basirat and Faili (2011), and Basirat and Faili (2013) belong to this category. Chen (2001) proposed a conversion method to map an individual XTAG elementary tree onto an automatically extracted elementary tree using a heuristic rule-based classification procedure.…”

Section: Related Workmentioning

confidence: 96%

“…The most important improvements of this method in relation to the previous work (Basirat and Faili 2013) are as follows:…”

Section: Introductionmentioning

confidence: 98%

“…These difficulties led us to closely follow the approach proposed by Basirat and Faili (2013). In this work, the problem of finding corresponding elementary trees is formulated as a sequence tagging problem in which a sequence of elementary trees of the MICA grammar (instead of a single elementary tree) is mapped onto a proper sequence of elementary trees of the XTAG grammar, given the structural and contextual information of the MICA elementary trees.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A statistical model for grammar mapping

2015

View full text Add to dashboard Cite

The two main classes of grammars are (a) hand-crafted grammars, which are developed by language experts, and (b) data-driven grammars, which are extracted from annotated corpora. This paper introduces a statistical method for mapping the elementary structures of a datadriven grammar onto the elementary structures of a hand-crafted grammar in order to combine their advantages. The idea is employed in the context of Lexicalized Tree-Adjoining Grammars (LTAG) and tested on two LTAGs of English: the hand-crafted LTAG developed in the XTAG project, and the data-driven LTAG, which is automatically extracted from the Penn Treebank and used by the MICA parser. We propose a statistical model for mapping any elementary tree sequence of the MICA grammar onto a proper elementary tree sequence of the XTAG grammar. The model has been tested on three subsets of the WSJ corpus that have average lengths of 10, 16, and 18 words, respectively. The experimental results show that full-parse trees with average F 1 -scores of 72.49, 64.80, and 62.30 points could be built from 94.97%, 96.01%, and 90.25% of the XTAG elementary tree sequences assigned to the subsets, respectively. Moreover, by reducing the amount of syntactic lexical ambiguity of sentences, the proposed model significantly improves the efficiency of parsing in the XTAG system.

show abstract

Section: Part-of-speech Agreementmentioning

confidence: 48%

Section: Part-of-speech Agreementmentioning

confidence: 48%

Section: Related Workmentioning

confidence: 96%

“…The most important improvements of this method in relation to the previous work (Basirat and Faili 2013) are as follows:…”

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%