The subject matter of this thesis is the problem of learning to discover grammatical structure from raw text alone, without access to explicit instruction or annotation -- in particular, by a computer or computational process -- in other words, unsupervised parser induction, or simply, unsupervised parsing. This work presents a method for raw text unsupervised parsing that is simple, but nevertheless achieves state-of-the-art results on treebank-based direct evaluation. The approach to unsupervised parsing presented in this dissertation adopts a different way to constrain learned models than has been deployed in previous work. Specifically, I focus on a sub-task of full unsupervised partial parsing called unsupervised partial parsing. In essence, the strategy is to learn to segment a string of tokens into a set of non-overlapping constituents or chunks which may be one or more tokens in length. This strategy has a number of advantages: it is fast and scalable, based on well-understood and extensible natural language processing techniques, and it produces predictions about human language structure which are useful for human language technologies. The models developed for unsupervised partial parsing recover base noun phrases and local constituent structure with high accuracy compared to strong baselines. Finally, these models may be applied in a cascaded fashion for the prediction of full constituent trees: first segmenting a string of tokens into local phrases, then re-segmenting to predict higher-level constituent structure. This simple strategy leads to an unsupervised parsing model which produces state-of-the-art results for constituent parsing of English, German and Chinese. This thesis presents, evaluates and explores these models and strategies. / text

Parts of the thesis were published in: 1. Khoo, C., Myaeng, S.H., & Oddy, R. (2001). Using cause-effect relations in text to improve information retrieval precision. Information Processing and Management, 37(1), 119-145. 2. Khoo, C., Kornfilt, J., Oddy, R., & Myaeng, S.H. (1998). Automatic extraction of cause-effect information from newspaper text without knowledge-based inferencing. Literary & Linguistic Computing, 13(4), 177-186. 3. Khoo, C. (1997). The use of relation matching in information retrieval. LIBRES: Library and Information Science Research Electronic Journal [Online], 7(2). Available at: http://aztec.lib.utk.edu/libres/libre7n2/. An update of the literature review on causal relations in text was published in: Khoo, C., Chan, S., & Niu, Y. (2002). The many facets of the cause-effect relation. In R.Green, C.A. Bean & S.H. Myaeng (Eds.), The semantics of relationships: An interdisciplinary perspective (pp. 51-70). Dordrecht: Kluwer / This study represents one attempt to make use of relations expressed in text to improve information retrieval effectiveness. In particular, the study investigated whether the information obtained by matching causal relations expressed in documents with the causal relations expressed in users' queries could be used to improve document retrieval results in comparison to using just term matching without considering relations. An automatic method for identifying and extracting cause-effect information in Wall Street Journal text was developed. The method uses linguistic clues to identify causal relations without recourse to knowledge-based inferencing. The method was successful in identifying and extracting about 68% of the causal relations that were clearly expressed within a sentence or between adjacent sentences in Wall Street Journal text. Of the instances that the computer program identified as causal relations, 72% can be considered to be correct. The automatic method was used in an experimental information retrieval system to identify causal relations in a database of full-text Wall Street Journal documents. Causal relation matching was found to yield a small but significant improvement in retrieval results when the weights used for combining the scores from different types of matching were customized for each query -- as in an SDI or routing queries situation. The best results were obtained when causal relation matching was combined with word proximity matching (matching pairs of causally related words in the query with pairs of words that co-occur within document sentences). An analysis using manually identified causal relations indicate that bigger retrieval improvements can be expected with more accurate identification of causal relations. The best kind of causal relation matching was found to be one in which one member of the causal relation (either the cause or the effect) was represented as a wildcard that could match with any term. The study also investigated whether using Roget's International Thesaurus (3rd ed.) to expand query terms with synonymous and related terms would improve retrieval effectiveness. Using Roget category codes in addition to keywords did give better retrieval results. However, the Roget codes were better at identifying the non-relevant documents than the relevant ones. Parts of the thesis were published in: 1. Khoo, C., Myaeng, S.H., & Oddy, R. (2001). Using cause-effect relations in text to improve information retrieval precision. Information Processing and Management, 37(1), 119-145. 2. Khoo, C., Kornfilt, J., Oddy, R., & Myaeng, S.H. (1998). Automatic extraction of cause-effect information from newspaper text without knowledge-based inferencing. Literary & Linguistic Computing, 13(4), 177-186. 3. Khoo, C. (1997). The use of relation matching in information retrieval. LIBRES: Library and Information Science Research Electronic Journal [Online], 7(2). Available at: http://aztec.lib.utk.edu/libres/libre7n2/. An update of the literature review on causal relations in text was published in: Khoo, C., Chan, S., & Niu, Y. (2002). The many facets of the cause-effect relation. In R.Green, C.A. Bean & S.H. Myaeng (Eds.), The semantics of relationships: An interdisciplinary perspective (pp. 51-70). Dordrecht: Kluwer

This study is in the area of sentiment classification: classifying online review documents according to the overall sentiment expressed in them. This paper presents a prototype sentiment-based meta search engine that has been developed to perform sentiment categorization of Web search results. It assists users to quickly focus on recommended or non-recommended information by classifying Web search results into four categories: positive, negative, neutral, and non-review documents. It does this by using an automatic classifier based on a supervised machine learning algorithm, Support Vector Machine (SVM). This paper also discusses various issues we have encountered during the prototype development, and presents our approaches for resolving them. A user evaluation of the prototype was carried out with positive responses from users.

Humans are not often very skilled in asking good questions because of their inconsistent mind in certain situations. Thus, Question Generation (QG) and Question Answering (QA) became the two major challenges for the Natural Language Processing (NLP), Natural Language Generation (NLG), Intelligent Tutoring System, and Information Retrieval (IR) communities, recently. In this thesis, we consider a form of Sentence-to-Question generation task where given a sentence as input, the QG system would generate a set of questions for which the sentence contains, implies, or needs answers. Since the given sentence may be a complex sentence, our system generates elementary sentences from the input complex sentences using a syntactic parser. A Part of Speech (POS) tagger and a Named Entity Recognizer (NER) are used to encode necessary information. Based on the subject, verb, object and preposition information, sentences are classified in order to determine the type of questions to be generated. We conduct extensive experiments on the TREC-2007 (Question Answering Track) dataset. The scenario for the main task in the TREC-2007 QA track was that an adult, native speaker of English is looking for information about a target of interest. Using the given target, we filter out the important sentences from the large sentence pool and generate possible questions from them. Once we generate all the questions from the sentences, we perform a recall-based evaluation. That is, we count the overlap of our system generated questions with the given questions in the TREC dataset. For a topic, we get a recall 1.0 if all the given TREC questions are generated by our QG system and 0.0 if opposite. To validate the performance of our QG system, we took part in the First Question Generation Shared Task Evaluation Challenge, QGSTEC in 2010. Experimental analysis and evaluation results along with a comparison of different participants of QGSTEC'2010 show potential significance of our QG system. / x, 125 leaves : ill. ; 29 cm

No description available.

No description available.

No description available.

Parsing is the task of assigning syntactic or semantic structure to a natural language sentence. This thesis focuses on syntactic parsing with Combinatory Categorial Grammar (CCG; Steedman 2000). CCG allows incremental processing, which is essential for speech recognition and some machine translation models, and it can build semantic structure in tandem with syntactic parsing. Supertagging solves a subset of the parsing task by assigning lexical types to words in a sentence using a sequence model. It has emerged as a way to improve the efficiency of full CCG parsing (Clark and Curran, 2007) by reducing the parser’s search space. This has been very successful and it is the central theme of this thesis. We begin by an analysis of how efficiency is being traded for accuracy in supertagging. Pruning the search space by supertagging is inherently approximate and to contrast this we include A* in our analysis, a classic exact search technique. Interestingly, we find that combining the two methods improves efficiency but we also demonstrate that excessive pruning by a supertagger significantly lowers the upper bound on accuracy of a CCG parser. Inspired by this analysis, we design a single integrated model with both supertagging and parsing features, rather than separating them into distinct models chained together in a pipeline. To overcome the resulting complexity, we experiment with both loopy belief propagation and dual decomposition approaches to inference, the first empirical comparison of these algorithms that we are aware of on a structured natural language processing problem. Finally, we address training the integrated model. We adopt the idea of optimising directly for a task-specific metric such as is common in other areas like statistical machine translation. We demonstrate how a novel dynamic programming algorithm enables us to optimise for F-measure, our task-specific evaluation metric, and experiment with approximations, which prove to be excellent substitutions. Each of the presented methods improves over the state-of-the-art in CCG parsing. Moreover, the improvements are additive, achieving a labelled/unlabelled dependency F-measure on CCGbank of 89.3%/94.0% with gold part-of-speech tags, and 87.2%/92.8% with automatic part-of-speech tags, the best reported results for this task to date. Our techniques are general and we expect them to apply to other parsing problems, including lexicalised tree adjoining grammar and context-free grammar parsing.

Word-Sense Disambiguation (WSD), holds promise for many NLP applications requiring broad-coverage language understanding, such as summarization (Barzilay and Elhadad, 1997) and question answering (Ramakrishnan et al., 2003). Recent studies have also shown that WSD can benefit machine translation (Vickrey et al., 2005) and information retrieval (Stokoe, 2005). Much work has focused on the computational treatment of sense ambiguity, primarily using data-driven methods. The most accurate WSD systems to date are supervised and rely on the availability of sense-labeled training data. This restriction poses a significant barrier to widespread use of WSD in practice, since such data is extremely expensive to acquire for new languages and domains. Unsupervised WSD holds the key to enable such application, as it does not require sense-labeled data. However, unsupervised methods fall far behind supervised ones in terms of accuracy and ease of use. In this thesis we explore the reasons for this, and present solutions to remedy this situation. We hypothesize that one of the main problems with unsupervised WSD is its lack of a standard formulation and general purpose tools common to supervised methods. As a first step, we examine existing approaches to unsupervised WSD, with the aim of detecting independent principles that can be utilized in a general framework. We investigate ways of leveraging the diversity of existing methods, using ensembles, a common tool in the supervised learning framework. This approach allows us to achieve accuracy beyond that of the individual methods, without need for extensive modification of the underlying systems. Our examination of existing unsupervised approaches highlights the importance of using the predominant sense in case of uncertainty, and the effectiveness of statistical similarity methods as a tool for WSD. However, it also serves to emphasize the need for a way to merge and combine learning elements, and the potential of a supervised-style approach to the problem. Relying on existing methods does not take full advantage of the insights gained from the supervised framework. We therefore present an unsupervised WSD system which circumvents the question of actual disambiguation method, which is the main source of discrepancy in unsupervised WSD, and deals directly with the data. Our method uses statistical and semantic similarity measures to produce labeled training data in a completely unsupervised fashion. This allows the training and use of any standard supervised classifier for the actual disambiguation. Classifiers trained with our method significantly outperform those using other methods of data generation, and represent a big step in bridging the accuracy gap between supervised and unsupervised methods. Finally, we address a major drawback of classical unsupervised systems – their reliance on a fixed sense inventory and lexical resources. This dependence represents a substantial setback for unsupervised methods in cases where such resources are unavailable. Unfortunately, these are exactly the areas in which unsupervised methods are most needed. Unsupervised sense-discrimination, which does not share those restrictions, presents a promising solution to the problem. We therefore develop an unsupervised sense discrimination system. We base our system on a well-studied probabilistic generative model, Latent Dirichlet Allocation (Blei et al., 2003), which has many of the advantages of supervised frameworks. The model’s probabilistic nature lends itself to easy combination and extension, and its generative aspect is well suited to linguistic tasks. Our model achieves state-of-the-art performance on the unsupervised sense induction task, while remaining independent of any fixed sense inventory, and thus represents a fully unsupervised, general purpose, WSD tool.

The amount of information available on the web is growing constantly. As a result, theproblem of retrieving any desired information is getting more difficult by the day. Toalleviate this problem, several techniques are currently being used, both for locatingpages of interest and for extracting meaningful information from the retrieved pages.Information extraction (IE) is one such technology that is used for summarizingunrestricted natural language text into a structured set of facts. IE is already being appliedwithin several domains such as news transcripts, insurance information, and weatherreports. Various approaches to IE have been taken and a number of significant resultshave been reported.In this thesis, we describe the application of IE techniques to the domain of universityweb pages. This domain is broader than previously evaluated domains and has a varietyof idiosyncratic problems to address. We present an analysis of the domain of universityweb pages and the consequences of having them input to IE systems. We then presentUniversityIE, a system that can search a web site, extract relevant pages, and processthem for information such as admission requirements or general information. TheUniversityIE system, developed as part of this research, contributes three IE methods anda web-crawling heuristic that worked relatively well and predictably over a test set ofuniversity web sites.We designed UniversityIE as a generic framework for plugging in and executing IEmethods over pages acquired from the web. We also integrated in the system a genericweb crawler (built at the University of Kentucky) and ported to Java and integrated anexternal word lexicon (WordNet) and a syntax parser (Link Grammar Parser).