In applying word-based dependency parsing such as Universal Dependencies (UD) to Japanese, the uncertainty of word segmentation emerges for defining a word unit of the dependencies. We introduce the following hierarchical word structures to dependency parsing in Japanese: morphological units (a short unit word, SUW) and syntactic units (a long unit word, LUW). This paper describes the results o...

To investigate the contributions of taggers or chunkers to the performance of a deep syntactic parser, Weighted Constraint Dependency Grammars have been extended to also take into consideration information from external sources. Using a weak information fusion scheme based on constraint optimization techniques, a parsing accuracy has been achieved which is comparable to other (stochastic) parsers.

Query segmentation, like text chunking, is the first step towards query understanding. In this study, we explore the effectiveness of crowdsourcing for this task. Through carefully designed control experiments and Inter Annotator Agreement metrics for analysis of experimental data, we show that crowdsourcing may not be a suitable approach for query segmentation because the crowd seems to have a...

This paper describes LINGUA an architecture for text processing in Bulgarian. First, the pre-processing modules for tokenisation, sentence splitting, paragraph segmentation, partof-speech tagging, clause chunking and noun phrase extraction are outlined. Next, the paper proceeds to describe in more detail the anaphora resolution module. Evaluation results are reported for each processing task.

Finite-state chunking and tagging methods are very fast for annotating nonhierarchical syntactic information, and are often applied in applications that do not require full syntactic analyses. Scenarios such as incremental machine translation may benefit from some degree of hierarchical syntactic analysis without requiring fully connected parses. We introduce hedge parsing as an approach to rec...

A Segmenter-POS Labeller and a Chunker for French We propose a demo of two softwares : a Segmenter-POS Labeller for French and a Chunker for texts treated by the first program. Both have been learned from the French Tree Bank. MOTS-CLÉS : étiquetage POS, chunking, apprentissage automatique, French Tree Bank, CRF.

1.1 Motivation There are two chief motivations for chunking: to locate information, or to ignore information. In the former case, we may want to extract all noun phrases so that they can be indexed. A text retrieval system could the use the index to support e cient retrieval for queries involving terminological expressions. A message understanding system will extract salient chunks of text from...

Water wheels used for power generation are applied to tailwater and ultra-low head sites. In this research, the VOF method standard k-ε turbulence model utilized predict performance transient flow fields of water wheels. The numerical results show a reasonable agreement with experimental data. This work aims at improving increasing internal fluid stability wheel, based on entropy production app...

Low-head dams can be dangerous to recreational river users when a submerged hydraulic jump forms downstream, with recirculating surface flows that repeatedly carry trapped recreationists upstream into the high-velocity jet plunging over dam crest. The flow endangers those who pass from and also entrap approach too closely downstream. A national task force is using range of methods identify pote...

Central Mexico is the site of an enigmatic zone of flat subduction. The general geometry of the subducting slab has been known for some time and is characterized by a horizontal zone bounded on either side by two moderately dipping sections. We systematically evaluate proposed hypotheses for shallow subduction in Mexico based on the spatial and temporal evidence, and we find no simple or obviou...