Downloads & Free Reading Options - Results

The popularity of applying machine learning methods to computational linguistics problems has produced a large supply of trainable natural language processing systems. Most problems of interest have an array of off-the-shelf products or downloadable code implementing solutions using various techniques. Where these solutions are developed independently, it is observed that their errors tend to be independently distributed. This thesis is concerned with approaches for capitalizing on this situation in a sample problem domain, Penn Treebank-style parsing. The machine learning community provides techniques for combining outputs of classifiers, but parser output is more structured and interdependent than classifications. To address this discrepancy, two novel strategies for combining parsers are used: learning to control a switch between parsers and constructing a hybrid parse from multiple parsers' outputs. Off-the-shelf parsers are not developed with an intention to perform well in a collaborative ensemble. Two techniques are presented for producing an ensemble of parsers that collaborate. All of the ensemble members are created using the same underlying parser induction algorithm, and the method for producing complementary parsers is only loosely constrained by that chosen algorithm.

The popularity of applying machine learning methods to computational linguistics problems has produced a large supply of trainable natural language processing systems. Most problems of interest have an array of off-the-shelf products or downloadable code implementing solutions using various techniques. Where these solutions are developed independently, it is observed that their errors tend to be independently distributed. This thesis is concerned with approaches for capitalizing on this situation in a sample problem domain, Penn Treebank-style parsing. The machine learning community provides techniques for combining outputs of classifiers, but parser output is more structured and interdependent than classifications. To address this discrepancy, two novel strategies for combining parsers are used: learning to control a switch between parsers and constructing a hybrid parse from multiple parsers' outputs. Off-the-shelf parsers are not developed with an intention to perform well in a collaborative ensemble. Two techniques are presented for producing an ensemble of parsers that collaborate. All of the ensemble members are created using the same underlying parser induction algorithm, and the method for producing complementary parsers is only loosely constrained by that chosen algorithm.

This paper presents a new context-free parsing algorithm based on a bidirectional strictly horizontal strategy which incorporates strong top-down predictions (derivations and adjacencies). From a functional point of view, the parser is able to propagate syntactic constraints reducing parsing ambiguity. From a computational perspective, the algorithm includes different techniques aimed at the improvement of the manipulation and representation of the structures used.

We present our work on semi-supervised parsing of natural language sentences, focusing on multi-source crosslingual transfer of delexicalized dependency parsers. We first evaluate the influence of treebank annotation styles on parsing performance, focusing on adposition attachment style. Then, we present KLcpos3, an empirical language similarity measure, designed and tuned for source parser weighting in multi-source delexicalized parser transfer. And finally, we introduce a novel resource combination method, based on interpolation of trained parser models.

266 p. ; 28 cm

266 p. ; 28 cm

This article introduces the idea that "information compression by multiple alignment, unification and search" (ICMAUS) provides a framework within which natural language syntax may be represented in a simple format and the parsing and production of natural language may be performed in a transparent manner. The ICMAUS concepts are embodied in a software model, SP61. The organisation and operation of the model are described and a simple example is presented showing how the model can achieve parsing of natural language. Notwithstanding the apparent paradox of 'decompression by compression', the ICMAUS framework, without any modification, can produce a sentence by decoding a compressed code for the sentence. This is illustrated with output from the SP61 model. The article includes four other examples - one of the parsing of a sentence in French and three from the domain of English auxiliary verbs. These examples show how the ICMAUS framework and the SP61 model can accommodate 'context sensitive' features of syntax in a relatively simple and direct manner.

This article introduces the idea that "information compression by multiple alignment, unification and search" (ICMAUS) provides a framework within which natural language syntax may be represented in a simple format and the parsing and production of natural language may be performed in a transparent manner. The ICMAUS concepts are embodied in a software model, SP61. The organisation and operation of the model are described and a simple example is presented showing how the model can achieve parsing of natural language. Notwithstanding the apparent paradox of 'decompression by compression', the ICMAUS framework, without any modification, can produce a sentence by decoding a compressed code for the sentence. This is illustrated with output from the SP61 model. The article includes four other examples - one of the parsing of a sentence in French and three from the domain of English auxiliary verbs. These examples show how the ICMAUS framework and the SP61 model can accommodate 'context sensitive' features of syntax in a relatively simple and direct manner.

This article introduces the idea that "information compression by multiple alignment, unification and search" (ICMAUS) provides a framework within which natural language syntax may be represented in a simple format and the parsing and production of natural language may be performed in a transparent manner. The ICMAUS concepts are embodied in a software model, SP61. The organisation and operation of the model are described and a simple example is presented showing how the model can achieve parsing of natural language. Notwithstanding the apparent paradox of 'decompression by compression', the ICMAUS framework, without any modification, can produce a sentence by decoding a compressed code for the sentence. This is illustrated with output from the SP61 model. The article includes four other examples - one of the parsing of a sentence in French and three from the domain of English auxiliary verbs. These examples show how the ICMAUS framework and the SP61 model can accommodate 'context sensitive' features of syntax in a relatively simple and direct manner.

We describe an approach to create a diverse set of predictions with spectral learning of latent-variable PCFGs (L-PCFGs). Our approach works by creating multiple spectral models where noise is added to the underlying features in the training set before the estimation of each model. We describe three ways to decode with multiple models. In addition, we describe a simple variant of the spectral algorithm for L-PCFGs that is fast and leads to compact models. Our experiments for natural language parsing, for English and German, show that we get a significant improvement over baselines comparable to state of the art. For English, we achieve the $F_1$ score of 90.18, and for German we achieve the $F_1$ score of 83.38.

Traditional natural language parsers are based on rewrite rule systems developed in an arduous, time-consuming manner by grammarians. A majority of the grammarian's efforts are devoted to the disambiguation process, first hypothesizing rules which dictate constituent categories and relationships among words in ambiguous sentences, and then seeking exceptions and corrections to these rules. In this work, I propose an automatic method for acquiring a statistical parser from a set of parsed sentences which takes advantage of some initial linguistic input, but avoids the pitfalls of the iterative and seemingly endless grammar development process. Based on distributionally-derived and linguistically-based features of language, this parser acquires a set of statistical decision trees which assign a probability distribution on the space of parse trees given the input sentence. These decision trees take advantage of significant amount of contextual information, potentially including all of the lexical information in the sentence, to produce highly accurate statistical models of the disambiguation process. By basing the disambiguation criteria selection on entropy reduction rather than human intuition, this parser development method is able to consider more sentences than a human grammarian can when making individual disambiguation rules. In experiments between a parser, acquired using this statistical framework, and a grammarian's rule-based parser, developed over a ten-year period, both using the same training material and test sentences, the decision tree parser significantly outperformed the grammar-based parser on the accuracy measure which the grammarian was trying to maximize, achieving an accuracy of 78% compared to the grammar-based parser's 69%.

We propose a formalism for representation of finite languages, referred to as the class of IDL-expressions, which combines concepts that were only considered in isolation in existing formalisms. The suggested applications are in natural language processing, more specifically in surface natural language generation and in machine translation, where a sentence is obtained by first generating a large set of candidate sentences, represented in a compact way, and then by filtering such a set through a parser. We study several formal properties of IDL-expressions and compare this new formalism with more standard ones. We also present a novel parsing algorithm for IDL-expressions and prove a non-trivial upper bound on its time complexity.

This paper describes how robust parsing techniques can be fruitful applied for building a query generation module which is part of a pipelined NLP architecture aimed at process natural language queries in a restricted domain. We want to show that semantic robustness represents a key issue in those NLP systems where it is more likely to have partial and ill-formed utterances due to various factors (e.g. noisy environments, low quality of speech recognition modules, etc...) and where it is necessary to succeed, even if partially, in extracting some meaningful information.

This paper describes how robust parsing techniques can be fruitful applied for building a query generation module which is part of a pipelined NLP architecture aimed at process natural language queries in a restricted domain. We want to show that semantic robustness represents a key issue in those NLP systems where it is more likely to have partial and ill-formed utterances due to various factors (e.g. noisy environments, low quality of speech recognition modules, etc...) and where it is necessary to succeed, even if partially, in extracting some meaningful information.

With the development of Natural Language Processing (NLP), more and more systems want to adopt NLP in User Interface Module to process user input, in order to communicate with user in a natural way. However, this raises a speed problem. That is, if NLP module can not process sentences in durable time delay, users will never use the system. As a result, systems which are strict with processing time, such as dialogue systems, web search systems, automatic customer service systems, especially real-time systems, have to abandon NLP module in order to get a faster system response. This paper aims to solve the speed problem. In this paper, at first, the construction of a syntactic parser which is based on corpus machine learning and statistics model is introduced, and then a speed problem analysis is performed on the parser and its algorithms. Based on the analysis, two accelerating methods, Compressed POS Set and Syntactic Patterns Pruning, are proposed, which can effectively improve the time efficiency of parsing in NLP module. To evaluate different parameters in the accelerating algorithms, two new factors, PT and RT, are introduced and explained in detail. Experiments are also completed to prove and test these methods, which will surely contribute to the application of NLP.

One of the main goals of natural language processing (NLP) is to build automated systems that can understand and generate human languages. This goal has so far remained elusive. Existing hand-crafted systems can provide in-depth analysis of domain sub-languages, but are often notoriously fragile and costly to build. Existing machine-learned systems are considerably more robust, but are limited to relatively shallow NLP tasks. In this thesis, we present novel statistical methods for robust natural language understanding and generation. We focus on two important sub-tasks, semantic parsing and tactical generation. The key idea is that both tasks can be treated as the translation between natural languages and formal meaning representation languages, and therefore, can be performed using state-of-the-art statistical machine translation techniques. Specifically, we use a technique called synchronous parsing, which has been extensively used in syntax-based machine translation, as the unifying framework for semantic parsing and tactical generation. The parsing and generation algorithms learn all of their linguistic knowledge from annotated corpora, and can handle natural-language sentences that are conceptually complex.