... 505–512, Sydney, July 2006. c 2006 Association for Computational Linguistics Creating a CCGbank and a wide-coverage CCG lexicon for German Julia Hockenmaier Institute for Research in Cognitive Science University ... sentences. Lexicons extracted from this corpus contain the correct en- tries for 86.7% of all and 94.2% of all seen to- kens. Good lexical coverage is essential for the performance of statistical CCG ... challenges for syntactic theories (Rambow, 1994), and the richer inflectional morphology of these languages creates additional problems both for the coverage of lexicalized formalisms such as CCG or...
Ngày tải lên: 08/03/2014, 02:21
... cartoon human avatars. In to- tal we had 36 colors for hair/eyebrows, 18 for eyes, 27 for lips, 26 for eye shadows, 27 for fa- cial mask and 18 for skin. These data is necessary to achieve our ... colors: yellow, white, brown. concept association lexicon, CLEX. This lexicon links concepts, color terms and emotions to spe- cific RGB values. This lexicon may help to dis- ambiguate objects when ... Languages and the Implementation of Com- munication and Information Technologies (Elicit). M. Bradley and P. Lang. 1999. Affective forms for english words (anew): Instruction manual and af- fective...
Ngày tải lên: 22/02/2014, 02:20
Banks’ regulatory capital buffer and the business cycle: evidence for German savings and cooperative banks pot
... dyMERGER is unity for an acquiring bank in the year before the merger and zero otherwise. In order to account for the unit root of RISK, all variables are first differenced, before applying the ... index for owner-occupied Claudia Kurz housing in West Germany 1985 to 1998 Johannes Hoffmann 9 2004 The Inventory Cycle of the German Economy Thomas A. Knetsch 10 2004 Evaluating the German ... dyMERGER is unity for an acquiring bank in the year before the merger and zero otherwise. In order to account for the unit root of RISK, all variables are first first-differenced, before applying...
Ngày tải lên: 15/03/2014, 09:20
Báo cáo khoa học: "A Graphical Tool for GermaNet Development" ppt
... Nahrung (German noun for: food). The Para- phrase column contains a description of a synset, e.g., for the selected synset the paraphrase is: der essbare Kern einer Nuss (German phrase for: the ... Tübingen, Germany. erhard.hinrichs@uni- tuebingen.de Abstract GernEdiT (short for: GermaNet Editing Tool) offers a graphical interface for the lexicogra- phers and developers of GermaNet ... the main orthographic form prior to the Neue Deutsche Recht- schreibung. This means that Nuß was the correct spelling instead of Nuss before the German spell- ing reform. Old Orth Var contains...
Ngày tải lên: 17/03/2014, 00:20
Báo cáo khoa học: "Web-based LRT services for German" ppt
... WebLicht's own data exchange format TCF. 5 The TCF Format The D-SPIN Text Corpus Format TCF (Heid et al, 2010) is used by WebLicht as an internal data exchange format. The TCF format allows the combination ... based data formats were developed beside the TCF format (for example, an encoding for lexi- con based data). In order to avoid any confusion of element names between these different for- mats, ... exchange format, which is preferably based on widely accepted formats already in use (UTF-8, XML). WebLicht uses the RESTstyle API and its own XML-based data exchange for- mat (Text Corpus Format,...
Ngày tải lên: 17/03/2014, 00:20
Báo cáo khoa học: "Automatic Induction of a CCG Grammar for Turkish" pptx
... as constituents in other theories. 1.2 Relevant Work Julia Hockenmaier’s robust CCG parser builds a CCG lexicon for English that is then used by a statis- tical model using the Penn Treebank as ... application rules, which are presented below: (2) Forward Application ( ): Backward Application ( ): In addition to functional application rules, CCG has combinatory operators for composition (B), type raising ... computational interface for syn- tax and morphemic lexicons. Master’s thesis, Middle East Technical University. Michael Collins. 1999. Head-driven Statistical Models for Natural Language Parsing....
Ngày tải lên: 17/03/2014, 06:20
Báo cáo khoa học: "Probabilistic Parsing for German using Sister-Head Dependencies" docx
... dependen- cies improve parsing performance not only for NPs (which is well-known for English), but also for PPs, VPs, Ss, and coordinate categories. The best perfor- mance was obtained for a model that uses ... improves parsing performance for these languages. As Experiment 1 showed, this cannot be taken for granted. 7 Conclusions We presented the first probabilistic full parsing model for German trained ... Results for Experiment 2: performance for models using split phrases and sister-head dependencies CNP, etc.), a drop in performance of around 1% each is observed. A slight drop is observed also for...
Ngày tải lên: 17/03/2014, 06:20
Báo cáo khoa học: "Separable Verbs in a Reusable Morphological Dictionary for German" pdf
... emphasized. First, the entire WM-formalism for separable verbs has been implemented as described here. The rules for German have been formulated and a large dictionary for German (100'000 entries) ... word formation rule the lexicographer chooses for the definition of an individual entry. In the IRules, detachable prefixes are referred to as formatives in the formulae generating the word forms. ... and the same form functioning as part of a separable verb such as auflzOren. Redundancies emerge between the two different entries for aufhOren, one for the continuous and one for the discontinuous...
Ngày tải lên: 17/03/2014, 07:20
Báo cáo khoa học: "A Freely Available Morphological Analyzer, Disambiguator and Context Sensitive Lemmatizer for German" pdf
... The lexicon of Morphy is very compact as it only stores the base form for each word together with its inflection class. Therefore, the complete morphological information for 324,000 word forms ... algorithm for the lookup of word forms in a full form lexicon. It results in an analysis speed of about 300 word forms per second on a fast PC, compared to many thousands using a full form lexicon. ... lemmata for each word form. Secondly, the tagger determines the grammatical categories of the word forms. If, for any of the lemmata, the inflected form corre- sponding to the word form in...
Ngày tải lên: 17/03/2014, 07:20
Báo cáo khoa học: "A GRAMMAR AND A LEXICON FOR A TEXT-PRODUCTION SYSTEM" pptx
... Conse(luently, the information about the poasibilib/ of having a LOCATION constituent is not the type of information that has to be stated for specific lsxical items. The information given for them concerns ... ~ ~ ~ g/~ ~ tO¢l~vO ~ in ~ IcC0urd for nocnm4UIT~ClonL 54 A GRAMMAR AND A LEXICON FOR A TEXT-PRODUCTION SYSTEM Christian M.I.M. Matthiessen USC/Information Sciences Institute ABSTRACT ... be a word for it, in which case the concept is part of a laxical entry. If there is no word for the concept, we will have to consider the various options the grammar gives us for forming an...
Ngày tải lên: 17/03/2014, 19:20
Báo cáo khoa học: "APPLICATIONS OF ALEXICO GRAPHICAL DATABASE FOR GERMAN" doc
... features the - The lexicographer can search for a word form, for word forms beginning or ending with a specified string of graphemes or for word forms containing a specified string of graphemes ... source for each information item has to be retrievable to assist the lexicographer in the evulation. The dictionary bank will be a valuable tool not only for the lexicographer but also for ... For all word forms, REFER will provide information on the relative and absolute frequency and the distribution over the texts of the corpus. - The lexicographer hat a choice of options for...
Ngày tải lên: 17/03/2014, 19:21
Báo cáo khoa học: "A Cascaded Finite-State Parser for German" pot
... representations by distinguishing lower bound performance (random choice of a parse) ADJ 165 A Cascaded Finite-State Parser for German Michael Schiehlen Institute for Computational Linguistics, University ... upper 88.9 77.7 90.9 79.5 93.6 81.8 31.0 Figure 2: Results for Finite-State Parser on Ideal, Lexicon and Tagger tags. The last col- umn of the table shows the percentage of com- pletely correct analyses of sentences. For the lower bound, ... Clark and Julia Hockenmaier. 2002. Evaluating a Wide-Coverage CCG Parser. In Beyond PARSE VAL - Tivoards Improved Evaluation Measures for Parsign Sys- tems (LREC Workshop). Jochen DOrre. 1997....
Ngày tải lên: 17/03/2014, 22:20
The Privatization of Italian Savings Banks – A Role Model for Germany?* doc
... of central institutes. Finally, before the reforms, Italy had a much higher share of public banks than Germany now does. Therefore, the scope for reform in Germany is smaller than it was in Italy ... discussion in Germany and discuss whether the Italian case can be used as a role model for the reform of the German banking sector. 2 Two Stylized Facts The comparison between the Italian and the German ... H. Schmidt (eds.): The German Financial System. Oxford, Oxford University Press, 71–105. 44 DIW Berlin Elena Carletti, Hendrik Hakenes and Isabel Schnabel 5 Lessons for Germany In this section...
Ngày tải lên: 22/03/2014, 21:20
Báo cáo khoa học: "Combining Multiple, Large-Scale Resources in a Reusable Lexicon for Natural Language Generation" pptx
Ngày tải lên: 31/03/2014, 04:20
Graphically Speaking: A Visual Lexicon for Achieving Better Designer-P1 doc
Ngày tải lên: 01/07/2014, 15:20
Graphically Speaking: A Visual Lexicon for Achieving Better Designer-P2 pot
Ngày tải lên: 01/07/2014, 15:20
Graphically Speaking: A Visual Lexicon for Achieving Better Designer-P3 potx
Ngày tải lên: 01/07/2014, 15:20
Graphically Speaking: A Visual Lexicon for Achieving Better Designer-P4 pptx
Ngày tải lên: 01/07/2014, 15:20
Bạn có muốn tìm thêm với từ khóa: