making tree kernels practical for natural language learning

... a cat PP IN A subtree Figure 1: A syntactic parse tree. We define as a subtree (ST) any node of a tree along with all its descendants. For example, the line in Figure 1 circles the subtree rooted in ... different information level between the two tree- based representations. 2.2 The Tree Kernel Functions The main idea of tree kernels is to compute the number of the common substructures between two trees ... that the above tree kernels are not convolution kernels as those proposed in this article. In (Shen et al., 2003), a tree- kernel based on Lexicalized Tree Adjoining Grammar (LTAG) for the parse-reranking...

Ngày tải lên: 08/03/2014, 21:20

Ngày tải lên: 08/03/2014, 01:20

Ngày tải lên: 08/03/2014, 01:20

Ngày tải lên: 23/03/2014, 14:20

Ngày tải lên: 23/03/2014, 19:20

... system, we currently use exact solution for input size of 7 propositions or less and switch to greedy for any larger input size to ensure sub-second performance for the NLG component. 0 20 40 60 80 100 120 140 160 180 200 24689101214161820 # ... 565–572, Ann Arbor, June 2005. c 2005 Association for Computational Linguistics Instance-based Sentence Boundary Determination by Optimization for Natural Language Generation Shimei Pan and James C. ... boundary determination in natural language generation exists when more than one sentence is needed to convey multiple concepts and propositions. In the classic natural language generation (NLG)...

Ngày tải lên: 20/02/2014, 15:20

... Domain A class is defined for each constant of PAL. A class object for a lexical item contains linguistic knowledge in a procedural form. In other words, a class contains information as to how a ... Portable Natural Language Query System. Artificial Intelligence 19(1982) :165-187, 1982. Montague, R. Proper Treatment of Quantification in Ordinary English. In Thompson (editor), Formal ... to share methods for these cases. Any exceptional method can be attached to lower level items. For example, we can define a class "action verb" which has methods for instrumental...

Ngày tải lên: 21/02/2014, 20:20

... Simplification Transformation for Natural Language Question-Answering Systems David G. Stallard BBN Laboratories Inc. I0 Moulton St. Cambridge, MA. 02238 Abstract A new method is presented for simplifying ... issues for natural- language systems which serve as interfaces to a database: the problems that arise in a module which maps the meaning representation to a second logical language for expressing ... exists for physician SPECIALTIES, we can nonetheless give a rule for this predicate in way that is uniform with the rule given for the predicate PATIENTS. 2This term, while a standard one in formal...

Ngày tải lên: 21/02/2014, 20:20

... application to Natural Language Database Interfacing. Ph.D. Thesis, Royal Institute of Technology, Stockholm, Sweden. 316 Semantic Information Preprocessing for Natural Language Interfaces ... LDT was introduced for a sys- tem, where input is a logical formula, whose predi- cates approximately correspond to the content words of the input utterance in natural language (lexical predicates). ... predicates). Output is a logical formula, consist- ing of predicates meaningful to the database engine (database predicates). AET provides a formalism for describing how a formula consisting of lexical...

Ngày tải lên: 08/03/2014, 07:20

... motive for doing ~ dictated by the planner. 189 A Computational Theory of Prose Style for Natural Language Generation David D. McDonald and James D. Pnstejovsky Department of Computer and Information ... (1984) "Another Representation Language Offer", PhJ3. Thesis, M1T. McDonald,D. (1984) "[kscription Directed Control: Its implications for natural language generation", International ... & Pustejovsky J. (1985a) WAGs as a Grammatical Formalism for Generation", pr~eedings of the 23rd Annual Meeting of the Association for Computational Linguistics, University of Chicago....

Ngày tải lên: 09/03/2014, 01:20

... we present Tree- Node-Fix, an efficient approximation algorithm for Max-Trans-Forest, as well as Graph-Node-Fix, an approximation for Max- Trans-Graph. 4.1 Tree- Node-Fix The scheme of Tree- Node-Fix ... curve. Maximal F 1 on the curve is .43 for Exact-graph, .41 for TNF, and .34 for No-trans. AUC in the recall range 0-0.5 is .32 for Exact-graph, .31 for TNF, and .26 for No-trans. Run-time of LP-relax ... Etzioni. 2011. Identifying relations for open information ex- traction. In Proceedings of Empirical Methods in Nat- ural Language Processing. J. R. Finkel and C. D. Manning. 2008. Enforcing transi- tivity...

Ngày tải lên: 16/03/2014, 19:20

... the system's performance on that application. The Parseval effort (Black (1991)) attempted to compare parsing performance across systems using the Treebank as a basis for comparison. Although ... have been used in natural language processing for a number of years (ATIS-3 (1991), MUC-6 (1995), Harman and Voorhees (1996)). Although these tests were originally designed for comparing different ... data based on the diagnostic information. Compared with Tgrep (1992) which works only on Treebank trees, ETE provides a more general and powerful search mechanism for a complex database. •...

Ngày tải lên: 17/03/2014, 07:20

... used for TEXT i. 2. 3. 4. identification -requests for definitions attributive -requests for available information constituency -requests for definitions -requests for available information ... detailed attributive information is included. For entities that are very different, only generic class information is included. A combination of this information is included for entities falling ... two generalizations. (See [MCCOY 82] for discussion of information associated with sub-types of database entity classes). 114 THE TEXT SYSTEM FO ~NATURAL LANGUAGE GENERATION: AN OVERVIEW* Kathleen...

Ngày tải lên: 17/03/2014, 19:21

... descriptive information for the sub-classes involves combinatoric problems which depend on the number of records for each entity in the database and the number of sub-classes formed for these ... and descriptive information is generated for each sub-class involved. This process is overseen by the general axioms which may throw out breakdowns for which descriptive information can not ... of independent modules; each is responsible for generating some piece of descriptive information for the sub-classes. When the system is invoked for a particular entity class, it first generates...

Ngày tải lên: 17/03/2014, 19:21

... Web Text Corpus for Natural Language Processing Vinci Liu and James R. Curran School of Information Technologies University of Sydney NSW 2006, Australia {vinci,james}@it.usyd.edu.au Abstract Web ... gathers information from the hit counts but does not require the com- putationally expensive downloading of actual text for analysis. Unfortunately search engines were not designed for NLP research ... Nat- ural Language Processing (NLP) tasks. There are many advantages to creating a corpus from web data rather than printed text. All web data is already in electronic form and therefore readable...

Ngày tải lên: 17/03/2014, 22:20

... OF DISCOURSE REPRESENTATIONS FOR NATURAL LANGUAGE INTERFACES Ntis Dahlb~ick Ame JOnsson Natural Language Processing Laboratory Department of Computer and Information Science LinkOping University, ... INTRODUCTION Natural Language interfaces will in the fore- seeable future only be able to handle a subset of natural language. The usability of this type of in- terfaces is therefore dependent ... empirical methodology for writing User-Friendly Natural Language computer applications, Proc. CHI "83 Kittredge, R. & Lehrberger, J. (1982) Sub- language. Studies of Language in Restricted...

Ngày tải lên: 18/03/2014, 02:20

Ngày tải lên: 23/03/2014, 19:20

Ngày tải lên: 31/03/2014, 04:20

Ngày tải lên: 31/03/2014, 17:20

Ngày tải lên: 31/03/2014, 17:20