Results 1  10
of
17
Computational Complexity of Probabilistic Disambiguation by means of TreeGrammars
, 1996
"... This paper studies the compntational complexity of dlsambiguation under probabilistic treegrammars as in (Bod, 1992; Schabes and Waters, 1993). It presents a proof that the following problems are NPhard: computing the Most Probable Parse frmn a sentence or from a wordgraph, and computing t ..."
Abstract

Cited by 100 (7 self)
 Add to MetaCart
This paper studies the compntational complexity of dlsambiguation under probabilistic treegrammars as in (Bod, 1992; Schabes and Waters, 1993). It presents a proof that the following problems are NPhard: computing the Most Probable Parse frmn a sentence or from a wordgraph, and computing the Most Pro'oable Sentence (MPS) from a word graph. The NPhardness of computing the MPS from a wordgraph also holds for Stochastic ContextFree Gram mars (SCFGs).
Parsing InsideOut
, 1998
"... Probabilistic ContextFree Grammars (PCFGs) and variations on them have recently become some of the most common formalisms for parsing. It is common with PCFGs to compute the inside and outside probabilities. When these probabilities are multiplied together and normalized, they produce the probabili ..."
Abstract

Cited by 83 (2 self)
 Add to MetaCart
Probabilistic ContextFree Grammars (PCFGs) and variations on them have recently become some of the most common formalisms for parsing. It is common with PCFGs to compute the inside and outside probabilities. When these probabilities are multiplied together and normalized, they produce the probability that any given nonterminal covers any piece of the input sentence. The traditional use of these probabilities is to improve the probabilities of grammar rules. In this thesis we show that these values are useful for solving many other problems in Statistical Natural Language Processing. We give a framework for describing parsers. The framework generalizes the inside and outside values to semirings. It makes it easy to describe parsers that compute a wide variety of interesting quantities, including the inside and outside probabilities, as well as related quantities such as Viterbi probabilities and nbest lists. We also present three novel uses for the inside and outside probabilities. T...
Efficient Algorithms for Parsing the DOP Model
, 1996
"... Excellent results have been reported for DataOriented Parsing (DOP) of natural language texts (Bod, 1993c). Unfortunately, existing algorithms are both computationally intensive and difficult to implement. Previous algorithms are expensive due to two factors: the exponential number of rules that mus ..."
Abstract

Cited by 58 (4 self)
 Add to MetaCart
Excellent results have been reported for DataOriented Parsing (DOP) of natural language texts (Bod, 1993c). Unfortunately, existing algorithms are both computationally intensive and difficult to implement. Previous algorithms are expensive due to two factors: the exponential number of rules that must be generated and the use of a Monte Carlo p arsing algorithm. In this paper we solve the first problem by a novel reduction of the DOP model toga small, equivalent probabilistic contextfree grammar. We solve the second problem by a novel deterministic parsing strategy that maximizes the expected number of correct con stituents, rather than the probability of a correct parse tree. Using ithe optimizations, experiments yield a 97% crossing brackets rate and 88% zero crossing brackets rate. This differs significantly from the results reported by Bod, and is compara ble to results from a duplication of Pereira and Schabes's (1992) experiment on the same data. We show that Bod's results are at least partially due to an extremely fortuitous choice of test data, and partially due to using cleaner data than other researchers.
A DOP Model for Semantic Interpretation
 Proceedings ACL/EACL97
, 1997
"... In dataoriented language processing, an annotated language corpus is used as a stochastic grammar. The most probable analysis of a new sentence is constructed by combining fragments from the corpus in the most probable way. This approach has been successfully used for syntactic analysis, usi ..."
Abstract

Cited by 37 (14 self)
 Add to MetaCart
In dataoriented language processing, an annotated language corpus is used as a stochastic grammar. The most probable analysis of a new sentence is constructed by combining fragments from the corpus in the most probable way. This approach has been successfully used for syntactic analysis, using corpora with syntactic annota tions such as the Penn Treebank. If a cor pus with semantically annotated sentences is used, the same approach can also gen erate the most probable semantic interpretation of an input sentence. The present paper explains this semantic interpretation method. A dataoriented semantic inter pretation algorithm was tested on two semantically annotated corpora: the English ATIS corpus and the Dutch OVIS corpus.
An optimized algorithm for Data Oriented Parsing
, 1996
"... This paper presents an optimization of a syntactic disambiguation algorithm for Data Oriented Parsing (DOP) (Bod 93) in particular, and for Stochastic TreeSubstitution Grammars (STSGs) in general. The main advantage of this algorithm on existing alternatives ((Bod 93), (Schabes & Waters 93), (Sima' ..."
Abstract

Cited by 32 (5 self)
 Add to MetaCart
This paper presents an optimization of a syntactic disambiguation algorithm for Data Oriented Parsing (DOP) (Bod 93) in particular, and for Stochastic TreeSubstitution Grammars (STSGs) in general. The main advantage of this algorithm on existing alternatives ((Bod 93), (Schabes & Waters 93), (Sima'an et al. 94)) is that its timecomplexity is linear, instead of square, in grammarsize (and cubic in sentence length). It is particularly suitable for natural language STSGs which have many deep elementarytrees and a small underlying ContextFree Grammar (CFG). A first implementation of this algorithm is operational and is exhibiting substantial speed up in comparison to the unoptimized version. In addition to presenting the optimized algorithm, the paper reports experiments for measuring the disambiguationaccuracy, the expected sizes and the executiontimes of various DOP models, which are projected from the ATIS domain. Keywords: Corpusbased statistical NLP, syntactic disambiguation...
A CorpusBased Approach to Semantic Interpretation
 Proceedings Ninth Amsterdam Colloquium
, 1994
"... ..."
Efficient Disambiguation by means of Stochastic Tree Substitution Grammars
, 1994
"... In Stochastic Tree Substitution Grammars (STSGs), a parse(tree) of an input sentence can be generated by (exponentially) many derivations. Each of these derivations is the result of a different combination of STSG elementarytrees and therefore receives a distinct probability; the probability of the ..."
Abstract

Cited by 21 (9 self)
 Add to MetaCart
In Stochastic Tree Substitution Grammars (STSGs), a parse(tree) of an input sentence can be generated by (exponentially) many derivations. Each of these derivations is the result of a different combination of STSG elementarytrees and therefore receives a distinct probability; the probability of the parse is defined as the sum of the probabilities of all derivations which generate that parse. Therefore, some methods of Stochastic ContextsFree Grammars (SCFGs), e.g. the Viterbi algorithm for finding the most probable parse (MPP) of an input sentence, are not applicable to STSGs. In this paper we study the problem of efficient disambiguation by means of STSGs under the Data Oriented Parsing model (DOP) [Bod, 1993c]. We present polynomial algorithms for computing the probability of a parse and the probability of an input sentence and its most probable derivation (MPD). In addition, we present a Viterbilike optimization technique for search algorithms for the MPP. A major concern in desi...
A MemoryBased Model of Syntactic Analysis: DataOriented Parsing
 Journal of Experimental and Theoretical Artificial Intelligence
, 1999
"... This paper presents a memorybased model of human syntactic processing: DataOriented Parsing. After a brief introduction (section 1), it argues that any account of disambiguation and many other performance phenomena inevitably has an important memorybased component (section 2). It discusses the li ..."
Abstract

Cited by 20 (6 self)
 Add to MetaCart
This paper presents a memorybased model of human syntactic processing: DataOriented Parsing. After a brief introduction (section 1), it argues that any account of disambiguation and many other performance phenomena inevitably has an important memorybased component (section 2). It discusses the limitations of probabilistically enhanced competencegrammars, and argues for a more principled memorybased approach (section 3). In sections 4 and 5, one particular memorybased model is described in some detail: a simple instantiation of the "DataOriented Parsing" approach ("DOP1"). Section 6 reports on experimentally established properties of this model, and section 7 compares it with other memorybased techniques. Section 8 concludes and points to future work. 1.
DataOriented Language Processing  An Overview
 CORPUSBASED METHODS IN LANGUAGE AND SPEECH PROCESSING
, 1997
"... Dataoriented models of language processing embody the assumption that human language perception and production works with representations of concrete past language experiences, rather than with abstract grammar rules. Such models therefore maintain large corpora of linguistic representations of pre ..."
Abstract

Cited by 15 (2 self)
 Add to MetaCart
Dataoriented models of language processing embody the assumption that human language perception and production works with representations of concrete past language experiences, rather than with abstract grammar rules. Such models therefore maintain large corpora of linguistic representations of previously occurring utterances. When processing a new input utterance, analyses of this utterance are constructed by combining fragments from the corpus; the occurrencefrequencies of the fragments are used to estimate which analysis is the most probable one. This paper motivates the idea of dataoriented language processing by considering the problem of syntactic disambiguation. One relatively simple parsing/disambiguation model that implements this idea is described in some detail. This model assumes a corpus of utterances annotated with labelled phrasestructure trees, and parses new input by combining subtrees from the corpus; it selects the most probable parse of an input utterance by considering the sum of the probabilities of all its derivations. The paper discusses some experiments carried out with this model. Finally, it reviews some other models that instantiate the dataoriented processing approach. Many of these models also employ labelled phrasestructure trees, but use different criteria for extracting subtrees from the corpus or employ different disambiguation strategies; other models use richer formalisms for their corpus annotations.
Automatic Acquisition of Language Models for Speech Recognition
, 1994
"... This thesis focuses on the automatic acquisition of language structure and the subsequent use of the learned language structure to improve the performance of a speech recognition system. First, we develop a grammar inference process which is able to learn a grammar describing a large set of training ..."
Abstract

Cited by 14 (3 self)
 Add to MetaCart
This thesis focuses on the automatic acquisition of language structure and the subsequent use of the learned language structure to improve the performance of a speech recognition system. First, we develop a grammar inference process which is able to learn a grammar describing a large set of training sentences. The process of acquiring this grammar is one of generalization so that the resulting grammar predicts likely sentences beyond those contained in the training set. From the grammar we construct a novel probabilistic language model called the phrase class ngram model (pcng), which is a natural generalization of the word class ngram model [11] to phrase classes. This model utilizes the grammar in such a way that it maintains full coverage of any test set while at the same time reducing the complexity, or number of parameters, of the resulting predictive model. Positive results are shown in terms of perplexity of the acquired phrase class ngram models and in terms of reduction of ...