We present a knowledge and context-based system for parsing natural language and evaluate it on sentences from the Wall Street Journal. Applying machine learning techniques, the system uses parse action examples acquired under supervision to generate a deterministic shift-reduce parser in the form of a decision structure. It relies heavily on context, as encoded in features which describe the m...

Résumé. Nous présentons DYALOG-SR, un analyseur syntaxique statistique par dépendances développé dans le cadre de la tâche SPRML 2013 portant sur un jeu de 9 langues très différentes. L’analyseur DYALOG-SR implémente un algorithme d’analyse par transition (à la MALT), étendu par utilisation de faisceaux et de techniques de programmation dynamique. Une des particularité de DYALOG-SR provient de ...

We present an efficient multi-level chart parser that was designed for syntactic analysis of closed captions (subtitles) in a real-time Machine Translation (MT) system. In order to achieve high parsing speed, we divided an existing English grammar into multiple levels. The parser proceeds in stages. At each stage, rules corresponding to only one level are used. A constituent pruning step is add...

This paper presents recent work using the Chill parser acquisition system to automate the construction of a natural-language interface for database queries. Chill treats parser acquisition as the learning of search-control rules within a logic program representing a shift-reduce parser and uses techniques from Inductive Logic Programming to learn relational control knowledge. Starting with a ge...

Philologists assure us that it’s worth learning ancient Greek just to read Homer. For any linguist, it’s definitely worth learning French, just to read Lucien Tesnière’s Elements de Syntaxe Structurale (Tesnière 1959). For any serious dependency parsing student or professional, it would have been worth learning Swedish, just to read Joakim Nivre’s Inductive Dependency Parsing if Nivre had not d...

Data-driven learning based on shift reduce parsing algorithms has emerged dependency parsing and shown excellent performance to many Treebanks. In this paper, we investigate the extension of those methods while considerably improved the runtime and training time efficiency via L2SVMs. We also present several properties and constraints to enhance the parser completeness in runtime. We further in...

It is shown that for a large class of non-holonomic quantum mechanical systems one can make the computation of BRST charge fully algorithmic. Two computer algebra programs written in the language of REDUCE are described. They are able to realize the complex calculations needed to determine the charge for general nonlinear algebras. Some interesting specific solutions are discussed.

This paper proposes a discriminative forest reranking algorithm for dependency parsing that can be seen as a form of efficient stacked parsing. A dynamic programming shift-reduce parser produces a packed derivation forest which is then scored by a discriminative reranker, using the 1-best tree output by the shift-reduce parser as guide features in addition to third-order graph-based features. T...

Transition-based approaches have shown competitive performance on constituent and dependency parsing of Chinese. Stateof-the-art accuracies have been achieved by a deterministic shift-reduce parsing model on parsing the Chinese Treebank 2 data (Wang et al., 2006). In this paper, we propose a global discriminative model based on the shift-reduce parsing process, combined with a beam-search decod...

We present an extension to incremental shift-reduce parsing that handles discontinuous constituents, using a linear classifier and beam search. We achieve very high parsing speeds (up to 640 sent./sec.) and accurate results (up to 79.52 F1 on TiGer).