Thesis (Ph. D.)--Brown University, 1988. / Includes bibliographical references.

Given a natural language sentence, parsing is the task of assigning it a grammatical structure, according to the rules within a particular grammar formalism. Different grammar formalisms like Dependency Grammar, Phrase Structure Grammar, Combinatory Categorial Grammar, Tree Adjoining Grammar are explored in the literature for parsing. For example, given a sentence like “John ate an apple”, parsers based on the widely used dependency grammars find grammatical relations, such as that ‘John’ is the subject and ‘apple’ is the object of the action ‘ate’. We mainly focus on Combinatory Categorial Grammar (CCG) in this thesis. In this thesis, we present an incremental algorithm for parsing CCG for two diverse languages: English and Hindi. English is a fixed word order, SVO (Subject-Verb- Object), and morphologically simple language, whereas, Hindi, though predominantly a SOV (Subject-Object-Verb) language, is a free word order and morphologically rich language. Developing an incremental parser for Hindi is really challenging since the predicate needed to resolve dependencies comes at the end. As previously available shift-reduce CCG parsers use English CCGbank derivations which are mostly right branching and non-incremental, we design our algorithm based on the dependencies resolved rather than the derivation. Our novel algorithm builds a dependency graph in parallel to the CCG derivation which is used for revealing the unbuilt structure without backtracking. Though we use dependencies for meaning representation and CCG for parsing, our revealing technique can be applied to other meaning representations like lambda expressions and for non-CCG parsing like phrase structure parsing. Any statistical parser requires three major modules: data, parsing algorithm and learning algorithm. This thesis is broadly divided into three parts each dealing with one major module of the statistical parser. In Part I, we design a novel algorithm for converting dependency treebank to CCGbank. We create Hindi CCGbank with a decent coverage of 96% using this algorithm. We also do a cross-formalism experiment where we show that CCG supertags can improve widely used dependency parsers. We experiment with two popular dependency parsers (Malt and MST) for two diverse languages: English and Hindi. For both languages, CCG categories improve the overall accuracy of both parsers by around 0.3-0.5% in all experiments. For both parsers, we see larger improvements specifically on dependencies at which they are known to be weak: long distance dependencies for Malt, and verbal arguments for MST. The result is particularly interesting in the case of the fast greedy parser (Malt), since improving its accuracy without significantly compromising speed is relevant for large scale applications such as parsing the web. We present a novel algorithm for incremental transition-based CCG parsing for English and Hindi, in Part II. Incremental parsers have potential advantages for applications like language modeling for machine translation and speech recognition. We introduce two new actions in the shift-reduce paradigm for revealing the required information during parsing. We also analyze the impact of a beam and look-ahead for parsing. In general, using a beam and/or look-ahead gives better results than not using them. We also show that the incremental CCG parser is more useful than a non-incremental version for predicting relative sentence complexity. Given a pair of sentences from wikipedia and simple wikipedia, we build a classifier which predicts if one sentence is simpler/complex than the other. We show that features from a CCG parser in general and incremental CCG parser in particular are more useful than a chart-based phrase structure parser both in terms of speed and accuracy. In Part III, we develop the first neural network based training algorithm for parsing CCG. We also study the impact of neural network based tagging models, and greedy versus beam-search parsing, by using a structured neural network model. In greedy settings, neural network models give significantly better results than the perceptron models and are also over three times faster. Using a narrow beam, structured neural network model gives consistently better results than the basic neural network model. For English, structured neural network gives similar performance to structured perceptron parser. But for Hindi, structured perceptron is still the winner.

No description available.

No description available.

Wide-coverage parsing is an area that attracts much attention in natural language processing research. This is due to the fact that it is the first step tomany other applications in natural language understanding, such as question answering. Supervised learning using human-labelled data is currently the best performing method. Therefore, there is great demand for annotated data. However, human annotation is very expensive and always, the amount of annotated data is much less than is needed to train well-performing parsers. This is the motivation behind making the best use of data available. Turkish presents a challenge both because syntactically annotated Turkish data is relatively small and Turkish is highly agglutinative, hence unusually sparse at the whole word level. METU-Sabancı Treebank is a dependency treebank of 5620 sentences with surface dependency relations and morphological analyses for words. We show that including even the crudest forms of morphological information extracted from the data boosts the performance of both generative and discriminative parsers, contrary to received opinion concerning English. We induce word-based and morpheme-based CCG grammars from Turkish dependency treebank. We use these grammars to train a state-of-the-art CCG parser that predicts long-distance dependencies in addition to the ones that other parsers are capable of predicting. We also use the correct CCG categories as simple features in a graph-based dependency parser and show that this improves the parsing results. We show that a morpheme-based CCG lexicon for Turkish is able to solve many problems such as conflicts of semantic scope, recovering long-range dependencies, and obtaining smoother statistics from the models. CCG handles linguistic phenomena i.e. local and long-range dependencies more naturally and effectively than other linguistic theories while potentially supporting semantic interpretation in parallel. Using morphological information and a morpheme-cluster based lexicon improve the performance both quantitatively and qualitatively for Turkish. We also provide an improved version of the treebank which will be released by kind permission of METU and Sabancı.

This study investigates the problem of quantifier scope ambiguity in natural languages and the various ways with which it has been accounted for, some of which are problematic for monotonic theories of grammar like Combinatory Categorial Grammar (CCG) which strive for solutions that avoid non-monotonic functional application, and assume complete transparency between the syntax and the semantics interface of a language. Another purpose of this thesis is to explore these proposals on examples from Turkish and to try to account for the meaning differences that may be caused by word order and see how the observations from Turkish fit within the framework of CCG.

This thesis investigates fundamental questions surrounding the phenomenon of control, with an emphasis on control in Turkish, as well as the behaviour of control verbs in non-infinitival environments, which have received little attention previously. I focus solely on the cases of obligatory control (OC) which constitute the only kind of control that is conditioned by the matrix verb alone. This approach is couched in Combinatory Categorial Grammar (CCG) where the control verb projects the necessary syntactic and semantic information. In particular, I argue that the control behaviour is an entailment associated with the verb itself, and that variable, split and partial control are instances of OC. Hence, no special mechanism/structure is needed to account for their interpretation. As to the syntactic and semantic status of the complement, I maintain that the complement is a bare VP in syntax and denotes a property in semantics. Building upon the conclusions reached about OC, I attempt to account for additional complementation patterns of OC verbs. I argue that here too the matrix verb has a crucial role in ruling in and out possible complement types. Finally, I note that control involves much more than just figuring out the reference of the &ldquo / unexpressed&rdquo / subject of the complement, and I furthermore propose that the additional frames of an OC verb provide important clues as to its lexical meaning, which are argued to be relevant for the acquisition of control.

A large proportion of computationally-oriented theories of grammar operate within the confines of monostratality (i.e. there is only one level of syntactic analysis), compositionality (i.e. the meaning of an expression is determined by the meanings of its syntactic parts, plus their manner of combination), and adjacency (i.e. the only operation on terminal strings is concatenation). This thesis looks at two major approaches falling within these bounds: that based on phrase structure grammar (e.g. Gazdar), and that based on categorial grammar (e.g. Steedman). The theories are examined with reference to extraction and coordination constructions; crucially a range of 'compound' extraction and coordination phenomena are brought to bear. It is argued that the early phrase structure grammar metarules can characterise operations generating compound phenomena, but in so doing require a categorial-like category system. It is also argued that while categorial grammar contains an adequate category apparatus, Steedman's primitives such as composition do not extend to cover the full range of data. A theory is therefore presented integrating the approaches of Gazdar and Steedman. The central issue as regards processing is derivational equivalence: the grammars under consideration typically generate many semantically equivalent derivations of an expression. This problem is addressed by showing how to axiomatise derivational equivalence, and a parser is presented which employs the axiomatisation to avoid following equivalent paths.

Research into parsing sign language corpora is ongoing. Corpora for German Sign Language and Italian Sign Language have been parsed (Bungeroth et al., 2006; Mazzei, 2011, 2012, respectively). However, research into parsing a corpus of American Sign Language is non-existent. Examples of parsed ASL sentences in literature are typically isolated examples used to show a particular type of construction. Apparently no attempt has been made to parse an entire corpus of American Sign Language utterances. This thesis presents a method for constructing a grammar so that a parser implementing Combinatory Categorial Grammar can parse a corpus of American Sign Language. The results are evaluated and presented.

No description available.