We consider the problem of correcting errors made by English as a Second Language (ESL) writers and address two issues that are essential to making progress in ESL error correction - algorithm selection and model adaptation to the ﬁrst language of the ESL learner. A variety of learning algorithms have been applied to correct ESL mistakes, but often comparisons were made between incomparable data sets. We conduct an extensive, fair comparison of four popular learning methods for the task, reversing conclusions from earlier evaluations. ...
A comprehensive treatment focusing on the creation of efficient data structures and algorithms, this text explains how to select or design the data structure best suited to specific problems. It uses C++ as the programming language and is suitable for second-year data structure courses and computer science courses in algorithmic analysis.
Data Structures and Algorithm Analysis Edition 3.2 (Java Version) a comprehensive treatment focusing on the creation of efficient data structures and algorithms, this text explains how to select or design the data structure best suited to specific problems. It uses Java as the programming language and is suitable for second-year data structure courses and computer science courses in algorithmic analysis.
When we agreed to edit this book for a second edition, we looked forward to
a bit of updating and including some of our latest research results. However,
the effort grew rapidly beyond our original vision. The use of genetic algorithms
(GAs) is a quickly evolving field of research, and there is much new to
recommend. Practitioners are constantly dreaming up new ways to improve
and use GAs. Therefore this book differs greatly from the first edition.
This paper proposes a novel method for learning probability models of subcategorization preference of verbs. We consider the issues of case dependencies and noun class generalization in a uniform way by employing the maximum entropy modeling method. We also propose a new model selection algorithm which starts from the most general model and gradually examines more specific models.
This paper discusses a decision-tree approach to the problem of assigning probabilities to words following a given text. In contrast with previous decision-tree language model attempts, an algorithm for selecting nearly optimal questions is considered. The model is to be tested on a standard task, The Wall Street Journal, allowing a fair comparison with the well-known trigram model.
In bootstrapping (seed set expansion), selecting good seeds and creating stop lists are two effective ways to reduce semantic drift, but these methods generally need human supervision. In this paper, we propose a graphbased approach to helping editors choose effective seeds and stop list instances, applicable to Pantel and Pennacchiotti’s Espresso bootstrapping algorithm. The idea is to select seeds and create a stop list using the rankings of instances and patterns computed by Kleinberg’s HITS algorithm. ...
In this paper we investigate how much data is required to train an algorithm for attribute selection, a subtask of Referring Expressions Generation (REG). To enable comparison between different-sized training sets, a systematic training method was developed. The results show that depending on the complexity of the domain, training on 10 to 20 items may already lead to a good performance.
This paper presents an innovative, complex approach to semantic verb classiﬁcation that relies on selectional preferences as verb properties. The probabilistic verb class model underlying the semantic classes is trained by a combination of the EM algorithm and the MDL principle, providing soft clusters with two dimensions (verb senses and subcategorisation frames with selectional preferences) as a result. A language-model-based evaluation shows that after 10 training iterations the verb class model results are above the baseline results.
While the average performance of statistical parsers gradually improves, they still attach to many sentences annotations of rather low quality. The number of such sentences grows when the training and test data are taken from different domains, which is the case for major web applications such as information retrieval and question answering. In this paper we present a Sample Ensemble Parse Assessment (SEPA) algorithm for detecting parse quality.
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a method based on conditional random ﬁelds (CRFs). The models are encoded as deterministic weighted ﬁnite state automata, and are applied by intersecting the automata with word-lattices that are the output from a baseline recognizer. The perceptron algorithm has the beneﬁt of automatically selecting a relatively small feature set in just a couple of passes over the training data. ...
Previous algorithms for the generation of referring expressions have been developed specifically for this purpose. Here we introduce an alternative approach based on a fully generic aggregation method also motivated for other generation tasks. We argue that the alternative contributes to a more integrated and uniform approach to content determination in the context of complete noun phrase generation.
In this paper we compare two grammar-based generation algorithms: the Semantic-Head-Driven Generation Algorithm (SHDGA), and the Essential Arguments Algorithm (EAA). Both algorithms have successfully addressed several outstanding problems in grammarbased generation, including dealing with non-monotonic compositionality of representation, left-recursion, deadlock-prone rules, and nondeterminism. We concentrate here on the comparison of selected properties: generality, efficiency, and determinism.
Robust natural language interpretation requires strong semantic domain models, "fall-soff" recovery heuristics, and very flexible control structures. Although single-strategy parsers have met with a measure of success, a multi.strategy approach is shown to provide a much higher degree of flexibility, redundancy, and ability to bring task-specific domain knowledge (in addition to general linguistic knowledge) to bear on both grammatical and ungrammatical input. A parsing algorithm is presented that integrates several different parsing strategies, with case-frame instantiation dominating. ...
Most algorithms dedicated to the generation of referential descriptions widely suffer from a fundamental problem: they make too strong assumptions about adjacent processing components, resulting in a limited coordination with their perceptive and linguistics data, that is, the provider for object descriptors and the lexical expression by which the chosen descriptors is ultimately realized.
We present a novel algorithm for multilingual dependency parsing that uses annotations from a diverse set of source languages to parse a new unannotated language. Our motivation is to broaden the advantages of multilingual learning to languages that exhibit significant differences from existing resource-rich languages.
We propose a novel approach for improving Feature Selection for Word Sense Disambiguation by incorporating a feature relevance prior for each word indicating which features are more likely to be selected. We use transfer of knowledge from similar words to learn this prior over the features, which permits us to learn higher accuracy models, particularly for the rarer word senses. Results on the O NTO N OTES verb data show signiﬁcant improvement over the baseline feature selection algorithm and results that are comparable to or better than other state-of-the-art methods. in this case). ...
The algorithm is implemented on top of the Selective Gain Computation (SGC) algorithm (Zhou et al., 2003), which offers fast training and high quality models. Theoretically, the new algorithm is able to explore an unlimited amount of features. Because of the improved capability of the CME algorithm, we are able to consider many new features and feature combinations during model construction.
Convolution kernels, such as sequence and tree kernels, are advantageous for both the concept and accuracy of many natural language processing (NLP) tasks. Experiments have, however, shown that the over-ﬁtting problem often arises when these kernels are used in NLP tasks. This paper discusses this issue of convolution kernels, and then proposes a new approach based on statistical feature selection that avoids this issue. To enable the proposed method to be executed efﬁciently, it is embedded into an original kernel calculation process by using sub-structure mining algorithms. ...