The aim of this thesis is to improve coreference resolution in Swedish by providing a hybrid approach based on combining data-driven methods and linguistic knowledge. Coreference resolution here consists in identifying all expressions in a text that have the same referent, for example, a person or an object. The linguistic knowledge is based on Accessibility Theory (Ariel 1990). This is used for guiding the  selection of likely anaphor-antecedent pairs from the set of all possible such pairs in a text. The data-driven method adopted is Memory-Based Learning (MBL), a supervised method based on the idea that learning means storing experiences in memory, and that new problems are solved by reusing solutions from similar experiences (Daelemans and Van den Bosch 2005). The referring expressions covered by the system are names, definite descriptions, and pronouns. In order to maximize performance, we use different classifiers with a specific set of linguistically motivated features for each type of expression. The great majority of features used for classification are domain- and language-independent. We demonstrate two ways of using this method of linguistically motivated selection of anaphor-antecedent pairs. First, the amount of training examples stored in memory  is reduced. We find that for coreference resolution of definite descriptions and names, the amount of training data can thereby be reduced with only a minor loss in performance, but for pronoun resolution there is a negative effect. Second, selection can be used for improving on coreference resolution results. This is the first step in our hybrid approach to coreference resolution, where the second step is the application of an MBL classifier for determining coreference between the selected pairs. Results indicate that this hybrid approach is advantageous for coreference resolution of definite descriptions and names. For pronoun resolution, there is a negative effect on recall along with a positive effect on precision. / För att köpa boken skicka en beställning till exp@ling.su.se/ To order the book send an e-mail to exp@ling.su.se

No description available.

The theme of this thesis writen in french is one of the ways of referring in the text called cataphora. Firstly, the work deals begin with the theoretical part, which contains the theory of text linguistics because of a close connection with the analyzed phenomenon. Then, the cataphora term is defined on the basis of literature and later analyzed in the selected corpus of journalistic texts.

The aim of this work is to describe and to analyse one type of anaphoric nominal syntagma found in the articles of French sports newspapers. The work is divided in two parts theoretical and practical. The theoretical part describes the basic concepts of text linguistics. Then it focuses on the concept of anaphora and nominal syntagma with brief reference to journalistic-style writing. In the practical part, an analysis of anaphoric nominal syntagmas and the description of their semantico-pragmatic relations is carried out.

No description available.

The notion of salience in the discourse analysis models how the activation of referred objects evolves in the flow of text. The salience algorithm was already defined and tested briefly in an earlier research, we present a reproduction of its results in a larger scale using data from the Prague Discourse Treebank 1.0. The results are then collected into an accessible shape and analyzed both in their visual and quantitative form in the context of the two main resources of the salience - coreference relations and topic-focus articulation. Finally, attempts are made with using the salience information in the machine learning NLP tasks of document clustering and topic modeling. Powered by TCPDF (www.tcpdf.org)

Coreference from the Cross-lingual Perspective Michal Nov'ak The subject of this thesis is to study properties of coreference using cross- lingual approaches. The work is motivated by the research on coreference-related linguistic typology. Another motivation is to explore whether differences in the ways how languages express coreference can be exploited to build better models for coreference resolution. We design two cross-lingual methods: the bilingually informed coreference resolution and the coreference projection. The results of our experiments with the methods carried out on Czech-English data suggest that with respect to coreference English is more informative for Czech than vice versa. Furthermore, the bilingually informed resolution applied on parallel texts has managed to outperform the monolingual resolver on both languages. In the experiments, we employ the monolingual coreference resolver and an improved method for alignment of coreferential expressions, both of which we also designed within the thesis. 1

The notion of salience in the discourse analysis models how the activation of referred objects evolves in the flow of text. The salience algorithm was already defined and tested briefly in an earlier research, we present a reproduction of its results in a larger scale using data from the Prague Dependency Treebank 3.0. The results are then collected into an accessible shape and analyzed both in their visual and quantitative form in the context of the two main resources of the salience - coreference relations and topic-focus articulation. Furthermore, a possibility of modeling the salience degree by a machine learning algorithm (decision trees and random forest) is examined. Finally, attempts are made with using the salience information in the machine learning NLP task of document clustering visualization. Powered by TCPDF (www.tcpdf.org)

It is often supposed that we can make progress understanding singular thought about objects by claiming that thinkers use ‘mental files’. However, the proposal is rarely subject to sustained critical evaluation. This thesis aims to clarify and critique the claim that thinkers use mental files. In my introductory first chapter, I motivate my subsequent discussion by introducing the claim that thinkers deploy modes of presentation in their thought about objects, and lay out some of my assumptions and terminology. In the second chapter, I introduce mental files, responding to the somewhat fragmented files literature by setting out a core account of files, and outlining different ways of implementing the claim that thinkers use mental files. I highlight pressing questions about the synchronic and diachronic individuation conditions for files. In chapters three and four, I explore whether ‘de jure coreference’ can be used to give synchronic individuation conditions on mental files. I explore existing characterisations of de jure coreference before presenting my own, but conclude that de jure coreference does not give a useful account of the synchronic individuation conditions on files. In chapter five, I consider the proposal that thinkers must sometimes trade on the coreference of their mental representations, and argue that we can give synchronic individuation conditions on files in terms of trading on coreference. In chapter six, I bring together the account of files developed so far, compare it to the most developed theory of mental files published to date, and defend my account from the objection that it is circular. In chapter seven, I explore routes for giving diachronic individuation conditions on mental files. In my concluding chapter, I distinguish the core account of files from the idea that the file metaphor should be taken seriously. I suggest that my investigation of the consequences of the core account has shown that the file metaphor is unhelpful, and I outline reasons to exercise caution when using ‘files’ terminology.

Submitted by PPG Ci?ncia da Computa??o (ppgcc@pucrs.br) on 2018-06-19T11:37:24Z No. of bitstreams: 1 EVANDRO BRASIL FONSECA_TES.pdf: 1972824 bytes, checksum: 9fca0c499753cd9d2822c59040e826bf (MD5) / Approved for entry into archive by Sheila Dias (sheila.dias@pucrs.br) on 2018-06-26T14:40:39Z (GMT) No. of bitstreams: 1 EVANDRO BRASIL FONSECA_TES.pdf: 1972824 bytes, checksum: 9fca0c499753cd9d2822c59040e826bf (MD5) / Made available in DSpace on 2018-06-26T14:48:46Z (GMT). No. of bitstreams: 1 EVANDRO BRASIL FONSECA_TES.pdf: 1972824 bytes, checksum: 9fca0c499753cd9d2822c59040e826bf (MD5) Previous issue date: 2018-03-19 / Coreference Resolution task is challenging for Natural Language Processing, considering the required linguistic knowledge and the sophistication of language processing techniques involved. Even though it is a demanding task, a motivating factor in the study of this phenomenon is its usefulness. Basically, several Natural Language Processing tasks may benefit from their results, such as named entities recognition, relation extraction between named entities, summarization, sentiment analysis, among others. Coreference Resolution is a process that consists on identifying certain terms and expressions that refer to the same entity. For example, in the sentence ? France is refusing. The country is one of the first in the ranking... ? we can say that [the country] is a coreference of [France]. By grouping these referential terms, we form coreference groups, more commonly known as coreference chains. This thesis proposes a process for coreference resolution between noun phrases for Portuguese, focusing on the use of semantic knowledge. Our proposed approach is based on syntactic-semantic linguistic rules. That is, we combine different levels of linguistic processing, using semantic relations as support, in order to infer referential relations between mentions. Models based on linguistic rules have been efficiently applied in other languages, such as: English, Spanish and Galician. In few words, these models are more efficient than machine learning approaches when we deal with less resourceful languages, since the lack of sample-rich corpora may produce a poor training. The proposed approach is the first model for Portuguese coreference resolution which uses semantic knowledge. Thus, we consider it as the main contribution of this thesis. / A tarefa de Resolu??o de Correfer?ncia ? um grande desafio para a ?rea de Processamento da Linguagem Natural, tendo em vista o conhecimento lingu?stico exigido e a sofistica??o das t?cnicas de processamento da l?ngua empregados. Mesmo sendo uma tarefa desafiadora, um fator motivador do estudo deste fen?meno se d? pela sua utilidade. Basicamente, v?rias tarefas de Processamento da Linguagem Natural podem se beneficiar de seus resultados, como, por exemplo, o reconhecimento de entidades nomeadas, extra??o de rela??o entre entidades nomeadas, sumariza??o, an?lise de sentimentos, entre outras. A Resolu??o de Correfer?ncia ? um processo que consiste em identificar determinados termos e express?es que remetem a uma mesma entidade. Por exemplo, na senten?a ?A Fran?a est? resistindo. O pa?s ? um dos primeiros no ranking...? podemos dizer que [o pa?s] ? uma correfer?ncia de [A Fran?a]. Realizando o agrupamento desses termos referenciais, formamos grupos de men??es correferentes, mais conhecidos como cadeias de correfer?ncia. Esta tese prop?e um processo para a resolu??o de correfer?ncia entre sintagmas nominais para a l?ngua portuguesa, tendo como foco a utiliza??o do conhecimento sem?ntico. Nossa abordagem proposta ? baseada em regras lingu?sticas sint?tico-sem?nticas. Ou seja, combinamos diferentes n?veis de processamento lingu?stico utilizando rela??es sem?nticas como apoio, de forma a inferir rela??es referenciais entre men??es. Modelos baseados em regras lingu?sticas t?m sido aplicados eficientemente em outros idiomas como o ingl?s, o espanhol e o galego. Esses modelos mostram-se mais eficientes que os baseados em aprendizado de m?quina quando lidamos com idiomas menos providos de recursos, dado que a aus?ncia de corpora ricos em amostras pode prejudicar o treino desses modelos. O modelo proposto nesta tese ? o primeiro voltado para a resolu??o de correfer?ncia em portugu?s que faz uso de conhecimento sem?ntico. Dessa forma, tomamos este fator como a principal contribui??o deste trabalho.