LingPars, a Linguistically Inspired, Language-Independent Machine Learner for Dependency Treebanks

Proceedings of the 10th Conference on Computational Natural Language Learning (CoNLL-X), pages 171–175, New York City, June 2006. c⃝2006 Association for Computational Linguistics LingPars, a Linguistically Inspired, Language-Independent Machine Learner for Dependency Treebanks Eckhard Bick Institute of Language and Communication University of Southern Denmark 5230 Odense M, Denmark eckhard.bick@mail.dk Abstract This paper presents a Constraint Grammar- inspired machine learner and parser, Ling­ Pars, that assigns dependencies to morpho­ logically annotated treebanks in a function- centred way. The system not only bases at­ tachment probabilities for PoS, case, mood, lemma on those features' function probabili­ ties, but also uses topological features like function/PoS n-grams, barrier tags and daughter-sequences. In the CoNLL shared task, performance was below average on at­ tachment scores, but a relatively higher score for function tags/deprels in isolation suggests that the system's strengths were not fully exploited in the current architecture. 1 Introduction This paper describes LingPars, a Constraint Gram­ mar-inspired language-independent treebank-learn­ er developed from scratch between January 9th and March 9th 2006 in the context of the CoNLL-X 2006 shared task (http://nextens.uvt.nl/~conll/), or­ ganized by Sabine Buchholz, Erwin Marsi, Yval Krymolowski and Amit Dubey. Training treebanks and test data were provided for 13 different lan­ guages: Arabic (Smrž et al. 2002), Chinese (Chen et al. 2003), Czech (Hajič et al. 2001), Danish (Kromann 2003), Dutch (van der Beek et al. 2002), German (Brants et.al 2002), Japanese (Kawata and Bartels), Portuguese (Afonso et al. 2002), Slovene (Džerosky et al. 2006), Spanish (Palomar et al. 2004), Swedish (Nilsson et al. 2005), Turkish (Oflazer et al. 2003 and Nart et.al 2003), Bulgarian (Simov et al. 2005). A number of these treebanks were not originally annotated in dependency style, but transformed from constituent tree style for the task, and all differ widely in terms of tag granulari­ ty (21-302 part-of-speech tags, 7-82 function la­ bels). Also, not all treebanks included morphologi­ cal information, and only half offered a lemma field. Such descriptive variation proved to be a considerable constraint for our parser design, as will be explained in chapter 2. No external re­ sources and no structural preprocessing were used1. 2 Language independence versus theory independence While manual annotation and/or linguistic, rule- based parsers are necessary for the creation of its training data, only a machine learning based parser (as targeted in the CoNNL shared task) can hope to be truly language independent in its design. The question is, however, if this necessarily implies in­ dependence of linguistic/descriptive theory. In our own approach, LingPars, we thus depart­ ed from the Constraint Grammar descriptive model (Karlsson et al. 2005), where syntactic function tags (called DEPREL or dependency relations in the shared task) rank higher than dependency/con­ stituency and are established before head attach­ ments, rather than vice versa (as would be the case for many probabilistic, chunker based systems, or 1The only exception is what we consider a problem in the dependency-version of the German TIGER treebank, where postnominal attributes of nouns appear as dependents of that noun's head if the …

Content truncated to 500 words