An annotation scheme for free word order languages

Skut, Wojciech; Krenn, Brigitte; Brants, Thorsten; Uszkoreit, Hans

doi:10.3115/974557.974571

Cited by 146 publications

(113 citation statements)

References 9 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…A related experiment is reported by Keller (2000b), who uses ditransitive verbs (i.e., complement orders including an indirect object) instead of transitive ones. Keller (2003) conducts a modeling study using the materials of Keller (2000a) and Keller (2000b), based on the syntactically annotated Negra corpus (Skut et al, 1997). He trains a probabilistic context-free grammar on Negra and demonstrates that the sentence probabilities predicted by this model correlate significantly with acceptability scores measured experimentally.…”

Section: Probabilistic Grammars and Gradient Acceptability Datamentioning

confidence: 99%

Probabilistic Grammars as Models of Gradience in Language Processing

Crocker¹,

Keller²

2006

Gradience in Grammar

View full text Add to dashboard Cite

This article deals with gradience in human sentence processing. We review the experimental evidence for the role of experience in guiding the decisions of the sentence processor. Based on this evidence, we argue that the gradient behavior observed in the processing of certain syntactic constructions can be traced back to the amount of past experience that the processor has had with these constructions. In modeling terms, linguistic experience can be approximated using large, balanced corpora. We give an overview of corpus-based and probabilistic models in the literature that have exploited this fact, and hence are well placed to make gradient predictions about processing behavior. Finally, we discuss a number of questions regarding the relationship between gradience in sentence processing and gradient grammaticality, and come to the conclusion that these two phenomena should be treated separately in conceptual and modeling terms.

show abstract

Section: Probabilistic Grammars and Gradient Acceptability Datamentioning

confidence: 99%

Probabilistic Grammars as Models of Gradience in Language Processing

Crocker¹,

Keller²

2006

Gradience in Grammar

View full text Add to dashboard Cite

show abstract

“…(Skut et al, 1997)). The Brill tagger comes with an English default version also trained on general-purpose language corpora like the PENN TREEBANK (Marcus et al, 1993).…”

Section: Experiments 1: Medical Tagging Withmentioning

confidence: 99%

High-performance tagging on medical texts

Hahn

Wermter

2004

Proceedings of the 20th International Conference on Computational Linguistics - COLING '04

View full text Add to dashboard Cite

We ran both Brill's rule-based tagger and TNT, a statistical tagger, with a default German newspaper-language model on a medical text corpus. Supplied with limited lexicon resources, TNT outperforms the Brill tagger with state-of-the-art performance figures (close to 97% accuracy). We then trained TNT on a large annotated medical text corpus, with a slightly extended tagset that captures certain medical language particularities, and achieved 98% tagging accuracy. Hence, statistical off-the-shelf POS taggers cannot only be immediately reused for medical NLP, but they also -when trained on medical corpora -achieve a higher performance level than for the newspaper genre.

show abstract

“…We utilize the version 2.0 of Negra corpus [5] for German parsing, which consists of 355,096 tokens and 20,602 sentences German newspaper text with completely annotated syntactic structures. We use 80 percent (16,482 sentences) of corpus for training, 10 percent (2,060 sentences) for developing and 10 percent (2,060 sentences) for testing.…”

Section: Parsing Of Germanmentioning

confidence: 99%

“…In the past twenty years, many treebanks were developed, such as the Chinese treebank [1][2], English treebank [3][4], German treebank [5], French treebank [6], and Portuguese treebank [7][8], etc. There are mainly two types of parsing structure, dependency structure and phrase structure.…”

Section: Introductionmentioning

confidence: 99%