Abstract | We show relative error reductions of 7.0% over the second-order dependency parser of McDonald and Pereira (2006), 9.2% over the constituent parser of Petrov et al. |
Analysis | Results are for dependency parsing on the dev set for iters:5,training-k:1. |
Introduction | For dependency parsing , we augment the features in the second-order parser of McDonald and Pereira (2006). |
Introduction | (2008) smooth the sparseness of lexical features in a discriminative dependency parser by using cluster-based word-senses as intermediate abstractions in |
Introduction | For the dependency case, we can integrate them into the dynamic programming of a base parser; we use the discriminatively-trained MST dependency parser (McDonald et al., 2005; McDonald and Pereira, 2006). |
Parsing Experiments | We first integrate our features into a dependency parser , where the integration is more natural and pushes all the way into the underlying dynamic program. |
Parsing Experiments | 4.1 Dependency Parsing |
Parsing Experiments | For dependency parsing , we use the discriminatively-trained MSTParser4, an implementation of first and second order MST parsing models of McDonald et a1. |
Web-count Features | pairs, as is standard in the dependency parsing literature (see Figure 3). |
Abstract | Most previous studies of morphological disambiguation and dependency parsing have been pursued independently. |
Baselines | For dependency parsing , our baseline is a “pipeline” parser (§4.2) that infers syntax upon the output of the baseline tagger. |
Baselines | 4.2 Baseline Dependency Parser |
Experimental Results | We compare the performance of the pipeline model (§4) and the joint model (§3) on morphological disambiguation and unlabeled dependency parsing . |
Experimental Results | 6.2 Dependency Parsing |
Introduction | To date, studies of morphological analysis and dependency parsing have been pursued more or less independently. |
Introduction | Morphological taggers disambiguate morphological attributes such as part-of-speech (POS) or case, without taking syntax nfioaummn(Hflimme7azd,2mm;Ihficet al., 2001); dependency parsers commonly assume the “pipeline” approach, relying on morphological information as part of the input (Buchholz and Marsi, 2006; Nivre et al., 2007). |
Introduction | 97% (Toutanova et al., 2003), and that of dependency parsing has reached the low nineties (Nivre et al., 2007). |
Previous Work | We know of only one previous attempt in data-driven dependency parsing for Latin (Bamman and Crane, 2008), with the goal of constructing a dynamic lexicon for a digital library. |
Previous Work | Parsing is performed using the usual pipeline approach, first with the TreeTagger analyzer (Schmid, 1994) and then with a state-of-the-art dependency parser (McDonald et al., 2005). |
Abstract | In this paper, we present a novel approach which incorporates the web-derived selectional preferences to improve statistical dependency parsing . |
Abstract | Experiments show that web-scale data improves statistical dependency parsing , particularly for long dependency relationships. |
Introduction | Dependency parsing is the task of building dependency links between words in a sentence, which has recently gained a wide interest in the natural language processing community. |
Introduction | With the availability of large-scale annotated corpora such as Penn Treebank (Marcus et al., 1993), it is easy to train a high-performance dependency parser using supervised learning methods. |
Introduction | However, current state-of—the-art statistical dependency parsers (McDonald et al., 2005; McDonald and Pereira, 2006; Hall et al., 2006) tend to have |
Abstract | In order to constrain the exhaustive attachments of function words, we limit to bind them to the nearby syntactic chunks yielded by a target dependency parser . |
Composed Rule Extraction | In the English-to-Japanese translation test case of the present study, the target chunk set is yielded by a state-of-the-art Japanese dependency parser , Cabocha v0.535 (Kudo and Matsumoto, 2002). |
Conclusion | In order to avoid generating too large a derivation forest for a packed forest, we further used chunk-level information yielded by a target dependency parser . |
Introduction | In order to constrain the exhaustive attachments of function words, we further limit the function words to bind to their surrounding chunks yielded by a dependency parser . |
Related Research | Thus, we focus on the realignment of target function words to source tree fragments and use a dependency parser to limit the attachments of unaligned target words. |
Adding Linguistic Knowledge to the Monte-Carlo Framework | Given sentence 3/, and its dependency parse qi, we model the distribution over predicate labels (5;- as: |
Adding Linguistic Knowledge to the Monte-Carlo Framework | The feature function 2; used for predicate labeling on the other hand operates only on a given sentence and its dependency parse . |
Adding Linguistic Knowledge to the Monte-Carlo Framework | It computes features which are the Cartesian product of the candidate predicate label with word attributes such as type, part-of—speech tag, and dependency parse information. |
Experimental Setup | In addition to gold standard dependency parses , the dataset also contains automatic parses obtained from the MaltParser (Nivre et al., 2007). |
Learning Setting | Given a dependency parse of a sentence, our system identifies argument instances and assigns them to clusters. |
Split-Merge Role Induction | Figure l: A sample dependency parse with dependency labels SBJ (subject), OBJ (object), NMOD (nominal modifier), OPRD (object predicative complement), PRD (predicative complement), and IM (infinitive marker). |
Experiments | Preprocessing of the ACE documents: We used the Stanford parser6 for syntactic and dependency parsing . |
Experiments | (2008) for dependency parsing . |
Introduction | Given an entity pair and a sentence containing the pair, both approaches usually start with multiple level analyses of the sentence such as tokenization, partial or full syntactic parsing, and dependency parsing . |
Experiments | The default parser in the experiments is a shift-reduce dependency parser (Nivre and Scholz, 2004). |
Experiments | We convert dependency parses to constituent trees by propagating the part-of-speech tags of the head words to the corresponding phrase structures. |
Experiments | Our fast deterministic dependency parser does not generate a packed forest. |