General features

Xem 1-20 trên 224 kết quả General features
  • We develop a general feature space for automatic classification of verbs into lexical semantic classes. Previous work was limited in scope by the need for manual selection of discriminating features, through a linguistic analysis of the target verb classes (Merlo and Stevenson, 2001). We instead analyze the classification structure at a higher level, using the possible defining characteristics of classes as the basis for our feature space.

    pdf8p bunthai_1 06-05-2013 16 2   Download

  • Rationale: ICTs have changed the way information is created and distributed. They have also changed the way libraries select, acquire, organize and deliver information. Library automation has. By the end of the lesson you should be able to: Define library automation Define an automated/Integrated Library System and identify as general features. Be aware of standards. Define an online public access catalog/web catalog Indentify the binifit of Library automation Identify potentail difficult in imple menting library automation ...

    ppt32p hoangyen999 04-05-2013 14 2   Download

  • If we take an existing supervised NLP system, a simple and general way to improve accuracy is to use unsupervised word representations as extra word features. We evaluate Brown clusters, Collobert and Weston (2008) embeddings, and HLBL (Mnih & Hinton, 2009) embeddings of words on both NER and chunking. We use near state-of-the-art supervised baselines, and find that each of the three word representations improves the accuracy of these baselines.

    pdf11p hongdo_1 12-04-2013 19 2   Download

  • Transition-based dependency parsers generally use heuristic decoding algorithms but can accommodate arbitrarily rich feature representations. In this paper, we show that we can improve the accuracy of such parsers by considering even richer feature sets than those employed in previous systems. In the standard Penn Treebank setup, our novel features improve attachment score form 91.4% to 92.9%, giving the best results so far for transitionbased parsing and rivaling the best results overall. For the Chinese Treebank, they give a signficant improvement of the state of the art. ...

    pdf6p hongdo_1 12-04-2013 8 2   Download

  • This paper explores methods to alleviate the effect of lexical sparseness in the classification of verbal arguments. We show how automatically generated selectional preferences are able to generalize and perform better than lexical features in a large dataset for semantic role classification. The best results are obtained with a novel second-order distributional similarity measure, and the positive effect is specially relevant for out-of-domain data. Our findings suggest that selectional preferences have potential for improving a full system for Semantic Role Labeling. ...

    pdf4p hongphan_1 15-04-2013 19 2   Download

  • In this paper we present word sense disambiguation (WSD) experiments on ten highly polysemous verbs in Chinese, where significant performance improvements are achieved using rich linguistic features. Our system performs significantly better, and in some cases substantially better, than the baseline on all ten verbs. Our results also demonstrate that features extracted from the output of an automatic Chinese semantic role labeling system in general benefited the WSD system, even though the amount of improvement was not consistent across the verbs. ...

    pdf8p hongvang_1 16-04-2013 18 2   Download

  • We present an efficient procedure for cost-based abduction, which is based on the idea of using chart parsers as proof procedures. We discuss in detail three features of our algorithm - - goal-driven bottom-up derivation, tabulation of the partial results, and agenda control mechanism - - and report the results of the preliminary experiments, which show how these features improve the computational efficiency of cost-based abduction.

    pdf8p bunmoc_1 20-04-2013 19 2   Download

  • Ristad (1986a) examines the computational complexity of two components of the G P S G formal system (metarules and the feature system) and shows how each of these systems can lead to computational intractability. Rlstad also proves that the universal recognition problem for G P S G s is E X P - P O L Y hard, and intractable.2 In another words, the fastest recognition algorithm for G P S G s can take more than exponential time. These results m a y appear surprising, given GPSG's weak context-fres generative power. ...

    pdf8p bungio_1 03-05-2013 22 2   Download

  • This paper presents an algorithm for the compilation of regular formalisms with rule features into finite-state automata. Rule features are incorporated into the right context of rules. This general notion can also be applied to other algorithms which compile regular rewrite rules into automata.

    pdf8p bunthai_1 06-05-2013 15 2   Download

  • The notion of a Horn extended feature structure (HoXF) is introduced, which is a feature structure constrained so that its only allowable extensions are those satisfying some set of llorn clauses in featureterm logic, l l o X F ' s greatly generalize ordinary feature structures in admitting explicit representation of negative and implicational constraints. In contradistinction to the general case in which arbitrary logical constraints are allowed (for which the best known algorithms are exponential), there is a highly tractable algorithm for the unification of HoXF's. ...

    pdf6p buncha_1 08-05-2013 22 2   Download

  • To address semantic ambiguities in coreference resolution, we use Web n-gram features that capture a range of world knowledge in a diffuse but robust way. Specifically, we exploit short-distance cues to hypernymy, semantic compatibility, and semantic context, as well as general lexical co-occurrence. When added to a state-of-the-art coreference baseline, our Web features give significant gains on multiple datasets (ACE 2004 and ACE 2005) and metrics (MUC and B3 ), resulting in the best results reported to date for the end-to-end task of coreference resolution....

    pdf10p nghetay_1 07-04-2013 20 1   Download

  • We investigate the tasks of general morphological tagging, diacritization, and lemmatization for Arabic. We show that for all tasks we consider, both modeling the lexeme explicitly, and retuning the weights of individual classifiers for the specific task, improve the performance.

    pdf4p hongphan_1 15-04-2013 13 1   Download

  • We present a novel hierarchical prior structure for supervised transfer learning in named entity recognition, motivated by the common structure of feature spaces for this task across natural language data sets. The problem of transfer learning, where information gained in one learning task is used to improve performance in another related task, is an important new area of research.

    pdf9p hongphan_1 15-04-2013 21 1   Download

  • This paper presents a semi-supervised training method for linear-chain conditional random fields that makes use of labeled features rather than labeled instances. This is accomplished by using generalized expectation criteria to express a preference for parameter settings in which the model’s distribution on unlabeled data matches a target distribution. We induce target conditional probability distributions of labels given features from both annotated feature occurrences in context and adhoc feature majority label assignment. ...

    pdf9p hongphan_1 15-04-2013 20 1   Download

  • Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sentences, we present the first general, featurerich discriminative parser, based on a conditional random field model, which has been successfully scaled to the full WSJ parsing data.

    pdf9p hongphan_1 15-04-2013 19 1   Download

  • Machine learning methods have been extensively employed in developing MT evaluation metrics and several studies show that it can help to achieve a better correlation with human assessments. Adopting the regression SVM framework, this paper discusses the linguistic motivated feature formulation strategy. We argue that “blind” combination of available features does not yield a general metrics with high correlation rate with human assessments.

    pdf6p hongphan_1 15-04-2013 15 1   Download

  • We explore how features based on syntactic dependency relations can be utilized to improve performance on opinion mining. Using a transformation of dependency relation triples, we convert them into “composite back-off features” that generalize better than the regular lexicalized dependency relation features. Experiments comparing our approach with several other approaches that generalize dependency features or ngrams demonstrate the utility of composite back-off features.

    pdf4p hongphan_1 15-04-2013 16 1   Download

  • This paper describes a parser which generates parse trees with empty elements in which traces and fillers are co-indexed. The parser is an unlexicalized PCFG parser which is guaranteed to return the most probable parse. The grammar is extracted from a version of the PENN treebank which was automatically annotated with features in the style of Klein and Manning (2003). The annotation includes GPSG-style slash features which link traces and fillers, and other features which improve the general parsing accuracy. ...

    pdf8p hongvang_1 16-04-2013 25 1   Download

  • We investigate different feature sets for performing automatic sentence-level discourse segmentation within a general machine learning approach, including features derived from either finite-state or contextfree annotations. We achieve the best reported performance on this task, and demonstrate that our SPADE-inspired context-free features are critical to achieving this level of accuracy. This counters recent results suggesting that purely finite-state approaches can perform competitively. Nucleus....

    pdf8p hongvang_1 16-04-2013 21 1   Download

  • This paper presents the results of experiments in which we tested different kinds of features for retrieval of Chinese opinionated texts. We assume that the task of retrieval of opinionated texts (OIR) can be regarded as a subtask of general IR, but with some distinct features. The experiments showed that the best results were obtained from the combination of character-based processing, dictionary look up (maximum matching) and a negation check.

    pdf6p hongvang_1 16-04-2013 19 1   Download


Đồng bộ tài khoản