Semantic role labeling has become a popular natural language processing task in recent years. A number of conferences have addressed this task for the English language and many different approaches have been applied to the task. In particular, some have used a memory-based learning approach. This thesis further develops the memory-based learning approach to semantic role labeling through the use of analogical modeling of language. Data for this task were taken from a previous conference (CoNLL-2005) so that a direct comparison could be made with other algorithms that attempted to solve this task. It will be shown here that the current approach is able to closely compare to other memory-based learning systems on the same task. Future work is also addressed.

No description available.

Contexto: A Anotação de Papéis Semânticos (APS) é uma tarefa da área de Processamento de Línguas Naturais (PLN) que permite detectar os eventos descritos nas sentenças e os participantes destes eventos (Palmer et al., 2010). A APS responde perguntas como Quem?, Quando?, Onde?, O quê?, e Por quê?, dentre outras e, sendo assim, é importante para várias aplicações de PLN. Para anotar automaticamente um texto com papéis semânticos, a maioria dos sistemas atuais emprega técnicas de Aprendizagem de Máquina (AM). Porém, alguns papéis semânticos são previsíveis e, portanto, não necessitam ser tratados via AM. Além disso, a grande maioria das pesquisas desenvolvidas em APS tem dado foco ao inglês, considerando as particularidades gramaticais e semânticas dessa língua, o que impede que essas ferramentas e resultados sejam diretamente transportados para outras línguas. Revisão da Literatura: Para o português do Brasil, há três trabalhos finalizados recentemente que lidam com textos jornalísticos, porém com performance inferior ao estado da arte para o inglês. O primeiro (Alva- Manchego, 2013) obteve 79,6 de F1 na APS sobre o córpus PropBank.Br; o segundo (Fonseca, 2013), sem fazer uso de um treebank para treinamento, obteve 68,0 de F1 sobre o córpus PropBank.Br; o terceiro (Sequeira et al., 2012) realizou anotação apenas dos papéis Arg0 (sujeito prototípico) e Arg1 (paciente prototípico) no córpus CETEMPúblico, com performance de 31,3 pontos de F1 para o primeiro papel e de 19,0 de F1 para o segundo. Objetivos: O objetivo desse trabalho de mestrado é avançar o estado da arte na APS do português brasileiro no gênero jornalístico, avaliando o desempenho de um sistema de APS treinado com árvores sintáticas geradas por um parser automático (Bick, 2000), sem revisão humana, usando uma amostragem do córpus PLN-Br. Como objetivo adicional, foi avaliada a robustez da tarefa de APS frente a gêneros diferentes, testando o sistema de APS, treinado no gênero jornalístico, em uma amostra de revisões de produtos da web. Esse gênero não foi explorado até então na área de APS e poucas de suas características foram formalizadas. Resultados: Foi compilado o primeiro córpus de opiniões sobre produtos da web, o córpus Buscapé (Hartmann et al., 2014). A diferença de performance entre um sistema treinado sobre árvores revisadas e outro sobre árvores não revisadas ambos no gênero jornalístico foi de 10,48 pontos de F1. A troca de gênero entre as fases de treinamento e teste, em APS, é possível, com perda de performance de 3,78 pontos de F1 (córpus PLN-Br e Buscapé, respectivamente). Foi desenvolvido um sistema de inserção de sujeitos não expressos no texto, com precisão de 87,8% no córpus PLN-Br e de 94,5% no córpus Buscapé. Foi desenvolvido um sistema, baseado em regras, para anotar verbos auxiliares com papéis semânticos modificadores, com confiança de 96,76% no córpus PLN-Br. Conclusões: Foi mostrado que o sistema de Alva-Manchego (2013), baseado em árvores sintáticas, desempenha melhor APS do que o sistema de Fonseca (2013), independente de árvores sintáticas. Foi mostrado que sistemas de APS treinados sobre árvores sintáticas não revisadas desempenham melhor APS sobre árvores não revisadas do que um sistema treinado sobre dados gold-standard. Mostramos que a explicitação de sujeitos não expressos nos textos do Buscapé, um córpus do gênero de opinião de produtos na web, melhora a performance da sua APS. Também mostramos que é possível anotar verbos auxiliares com papéis semânticos modificadores, utilizando um sistema baseado em regras, com alta confiança. Por fim, mostramos que o uso do sentido do verbo, como feature de AM, para APS, não melhora a perfomance dos sistemas treinados sobre o PLN-Br e o Buscapé, por serem córpus pequenos. / Background: Semantic Role Labeling (SRL) is a Natural Language Processing (NLP) task that enables the detection of events described in sentences and the participants of these events (Palmer et al., 2010). SRL answers questions such as Who?, When?, Where?, What? and Why? (and others), that are important for several NLP applications. In order to automatically annotate a text with semantic roles, most current systems use Machine Learning (ML) techniques. However, some semantic roles are predictable, and therefore, do not need to be classified through ML. In spite of SRL being well advanced in English, there are grammatical and semantic particularities that prevents full reuse of tools and results in other languages. Related work: For Brazilian Portuguese, there are three studies recently concluded that performs SRL in journalistic texts. The first one (Alva-Manchego, 2013) obtained 79.6 of F1 on the SRL of the PropBank.Br corpus; the second one (Fonseca, 2013), without using a treebank for training, obtained 68.0 of F1 for the same corpus; and the third one (Sequeira et al., 2012) annotated only the Arg0 (prototypical agent) and Arg1 (prototypical patient) roles on the CETEMPúblico corpus, with a perfomance of 31.3 of F1 for the first semantic role and 19.0 for the second one. None of them, however, reached the state of the art of the English language. Purpose: The goal of this masters dissertation was to advance the state of the art of SRL in Brazilian Portuguese. The training corpus used is from the journalistic genre, as previous works, but the SRL annotation is performed on non-revised syntactic trees, i.e., generated by an automatic parser (Bick, 2000) without human revision, using a sampling of the corpus PLN-Br. To evaluate the resulting SRL classifier in another text genre, a sample of product reviews from web was used. Until now, product reviews was a genre not explored in SRL research, and few of its characteristics are formalized. Results: The first corpus of web product reviews, the Buscapé corpus (Hartmann et al., 2014), was compiled. It is shown that the difference in the performance of a system trained on revised syntactic trees and another trained on non-revised trees both from the journalistic genre was of 10.48 of F1. The change of genres during the training and testing steps in SRL is possible, with a performance loss of 3.78 of F1 (corpus PLN-Br and Buscapé, respectively). A system to insert unexpressed subjects reached 87.8% of precision on the PLN-Br corpus and a 94.5% of precision on the Buscapé corpus. A rule-based system was developed to annotated auxiliary verbs with semantic roles of modifiers (ArgMs), achieving 96.76% confidence on the PLN-Br corpus. Conclusions: First we have shown that Alva-Manchego (2013) SRL system, that is based on syntactic trees, performs better annotation than Fonseca (2013)s system, that is nondependent on syntactic trees. Second the SRL system trained on non-revised syntactic trees performs better over non-revised trees than a system trained on gold-standard data. Third, the explicitation of unexpressed subjects on the Buscapé texts improves their SRL performance. Additionally, we show it is possible to annotate auxiliary verbs with semantic roles of modifiers, using a rule-based system. Last, we have shown that the use of the verb sense as a feature of ML, for SRL, does not improve the performance of the systems trained over PLN-Br and Buscapé corpus, since they are small.

Semantic role labeling is an important stage in systems for Natural Language Understanding. The basic problem is one of identifying who did what to whom for each predicate in a sentence. Thus labeling is a two-step process: identify constituent phrases that are arguments to a predicate, then label those arguments with appropriate thematic roles. Existing systems for semantic role labeling use machine learning methods to assign roles one-at-a-time to candidate arguments. There are several drawbacks to this general approach. First, more than one candidate can be assigned the same role, which is undesirable. Second, the search for each candidate argument is exponential with respect to the number of words in the sentence. Third, single-role assignment cannot take advantage of dependencies known to exist between semantic roles of predicate arguments, such as their relative juxtaposition. And fourth, execution times for existing algorithm are excessive, making them unsuitable for real-time use. This thesis seeks to obviate these problems by approaching semantic role labeling as a multi-argument classification process. It observes that the only valid arguments to a predicate are unembedded constituent phrases that do not overlap that predicate. Given that semantic role labeling occurs after parsing, this thesis proposes an algorithm that systematically traverses the parse tree when looking for arguments, thereby eliminating the vast majority of impossible candidates. Moreover, instead of assigning semantic roles one at a time, an algorithm is proposed to assign all labels simultaneously; leveraging dependencies between roles and eliminating the problem of duplicate assignment. Experimental results are provided as evidence to show that a combination of the proposed argument identification and multi-argument classification algorithms outperforms all existing systems that use the same syntactic information.

Semantic role labelling (SRL) is a natural language processing (NLP) technique that maps sentences to semantic representations. This can be used in different NLP tasks. The goal of this master thesis is to investigate how to support the novel method proposed by He Tan for building corpus annotated with semantic roles. The mentioned goal provides the context for developing a general framework of the work and as a result implementing a supporting system based on the framework. Implementation is followed using Java. Defined features of the system reflect the usage of frame semantics in understanding and explaining the meaning of lexical items. This prototype system has been processed by the biomedical corpus as a dataset for the evaluation. Our supporting environment has the ability to create frames with all related associations through XML, updating frames and related information including definition, elements and example sentences and at last annotating the example sentences of the frame. The output of annotation is a semi structure schema where tokens of a sentence are labelled. We evaluated our system by means of two surveys. The evaluation results showed that our framework and system have fulfilled the expectations of users and has satisfied them in a good scale. Also feedbacks from users have defined new areas of improvement regarding this supporting environment.

In recent years, a considerable amount of work has been devoted to the task of automatic frame-semantic analysis. Given the relative maturity of syntactic parsing technology, which is an important prerequisite, frame-semantic analysis represents a realistic next step towards broad-coverage natural language understanding and has been shown to benefit a range of natural language processing applications such as information extraction and question answering. Due to the complexity which arises from variations in syntactic realization, data-driven models based on supervised learning have become the method of choice for this task. However, the reliance on large amounts of semantically labeled data which is costly to produce for every language, genre and domain, presents a major barrier to the widespread application of the supervised approach. This thesis therefore develops unsupervised machine learning methods, which automatically induce frame-semantic representations without making use of semantically labeled data. If successful, unsupervised methods would render manual data annotation unnecessary and therefore greatly benefit the applicability of automatic framesemantic analysis. We focus on the problem of semantic role induction, in which all the argument instances occurring together with a specific predicate in a corpus are grouped into clusters according to their semantic role. Our hypothesis is that semantic roles can be induced without human supervision from a corpus of syntactically parsed sentences, by leveraging the syntactic relations conveyed through parse trees with lexical-semantic information. We argue that semantic role induction can be guided by three linguistic principles. The first is the well-known constraint that semantic roles are unique within a particular frame. The second is that the arguments occurring in a specific syntactic position within a specific linking all bear the same semantic role. The third principle is that the (asymptotic) distribution over argument heads is the same for two clusters which represent the same semantic role. We consider two approaches to semantic role induction based on two fundamentally different perspectives on the problem. Firstly, we develop feature-based probabilistic latent structure models which capture the statistical relationships that hold between the semantic role and other features of an argument instance. Secondly, we conceptualize role induction as the problem of partitioning a graph whose vertices represent argument instances and whose edges express similarities between these instances. The graph thus represents all the argument instances for a particular predicate occurring in the corpus. The similarities with respect to different features are represented on different edge layers and accordingly we develop algorithms for partitioning such multi-layer graphs. We empirically validate our models and the principles they are based on and show that our graph partitioning models have several advantages over the feature-based models. In a series of experiments on both English and German the graph partitioning models outperform the feature-based models and yield significantly better scores over a strong baseline which directly identifies semantic roles with syntactic positions. In sum, we demonstrate that relatively high-quality shallow semantic representations can be induced without human supervision and foreground a promising direction of future research aimed at overcoming the problem of acquiring large amounts of lexicalsemantic knowledge.

Ce travail est une étude syntaxique, sémantique et pragmatique des énoncés où le verbe voir a pour sujet un circonstant.Voix ou diathèse ? Telle est la première question qui est posée à propos de la tournure qui caractérise des phrases comme :(ex) L'année 1981 voit s'atténuer, du moins publiquement, les grandes polémiques politico-religieuses.Le sujet de la phrase peut être restitué en tant que circonstant dans un énoncé standard :(ex) Durant l’année 1981, les grandes polémiques politico-religieuses s’atténuent, du moins publiquement.Nous montrons que cette construction relève de la diathèse circonstancielle où le verbe voir doit être considéré comme un semi-auxiliaire de diathèse et non comme le verbe voir dans son sens plein.Nous menons ensuite une étude syntaxique et sémantique sur un corpus de 338 exemples extraits du Monde Diplomatique. Tous les éléments autour de voir, son sujet, le verbe ou le SNPred qui le suit, l’adjectif et enfin le participe passé passif, sont analysés des deux points de vue, syntaxique d’abord, puis sémantique.Du point de vue syntaxique, grâce à des tests auxquels nous soumettons ces éléments, nous montrons que voir forme un tout avec les éléments qui l’entourent, ce qui empêche de considérer que la proposition infinitive ou le SN prédicatif complexe qui le suivent immédiatement soit COD de voir. Par ailleurs, il ressort que les prédicats intransitifs et pronominaux dominent quantitativement.L’étude sémantique montre que la syntaxe propre à cette construction se traduit par une perte de la signification de voir en proportion du degré de grammaticalisation de ce verbe : son sujet devenant progressivement /-animé/. Le rôle d’expérient attribué par voir au sujet reste mais s’affaiblit. Nous l’avons appelé expérient "métaphorique". Par ailleurs, nous montrons que dans notre corpus les prédicats associés à voir sont tous de type dynamique.L’étude des contextes dans lesquels les constructions à diathèse circonstancielle montrent que leur choix par le journaliste peut être libre ou contraint. / This work is a syntactic, semantic and pragmatic study of the sentences of French in which the subject of the verb voir is a noun phrase with an adverbial (time or place).Is it an instance of voice or of diathesis? Such is the first question concerning such sentences as:L'année 1981 voit s'atténuer, du moins publiquement, les grandes polémiques politico-religieuses.In a standard sentence, the subject would appear as an adverbial complement referring to time or place:Durant l’année 1981, les grandes polémiques politico-religieuses s’atténuent, du moins publiquement.The voir structure is analysed as a case of adverbial diathesis, in which voir is considered as a semi-auxiliary of diathesis, not as the verb voir with its original meaning.The syntactic and semantic study is based on a corpus of 338 examples from Le Monde Diplomatique. All the terms around voir (its subject, the infinitive verb or the nominalised verb or the passive past participle that follow) have been analysed from both the syntactic and the semantic point of view.From the syntactic point of view, thanks to a number of tests, it can be shown that voir and the terms around it make up a whole, so that is impossible to consider the infinitive clause or the complex verb-derived NP as objects of voir. Moreover, the quantitative study shows that intransitive and pronominal (se) verbs are a majority.The semantic study shows that the syntax that is typical of the structure is related to a loss of meaning of voir in proportion to its degree of grammaticalization as its subject progressively becomes /-animate/. The role of experiencer of the subject of voir remains only in a weakened form. I have called this role metaphorical experiencer. Moreover, all the verbs or nominalizations after voir that occur in the corpus are shown to be of the dynamic type.Finally, the study of the contexts where the adverbial diathesis structure occurs shows that the choice of the structure by the journalist can be either free or constrained

Esta tese propõe um recurso léxico de verbos com anotação de papéis semânticos, denominado VerbLexPor, baseado em recursos como VerbNet, PropBank e FrameNet. As bases teóricas da proposta são interdisciplinares e retiradas da Linguística de Corpus e do Processamento de Linguagem Natural (PLN), visando-se a contribuir para a Linguística e para a Computação. As hipóteses de pesquisa são: a) um mesmo conjunto de papéis semânticos pode ser aplicado a diferentes gêneros textuais; e b) as diferenças entre esses gêneros se destacam no ranqueamento dos papéis semânticos. O desenvolvimento do VerbLexPor se apoia em dois corpora: um especializado, com mais de 1,6 milhão de palavras, composto por artigos científicos de Cardiologia de três periódicos brasileiros; e um não especializado, com mais de 1 milhão de palavras composto por artigos do jornal popular Diário Gaúcho. Os corpora foram anotados com o parser PALAVRAS, e as informações de sentenças, verbos e argumentos foram extraídas e armazenadas em um banco de dados. O VerbLexPor tem 192 verbos e mais de 15 mil argumentos anotados distribuídos em mais de 6 mil sentenças. Observou-se que o corpus do Diário Gaúcho privilegia uma sintaxe direta e pouco uso de voz passiva e adjuntos, enquanto o corpus de Cardiologia apresenta mais voz passiva e um maior uso de INSTRUMENTOS na posição de sujeito, além de uma menor incidência de AGENTES. Foram realizados também alguns experimentos paralelos, como a anotação de papéis semânticos por vários anotadores e o agrupamento automático de verbos. Na tarefa de múltiplos anotadores, cada um anotou exatamente as mesmas 25 orações. Os anotadores receberam um manual de anotação e um treinamento básico (explicação sobre a tarefa e dois exemplos de anotação). Usou-se o cálculo de multi-π para avaliar a concordância entre os anotadores, e o resultado foi de π = 0,25. Os motivos para essa concordância baixa podem estar na falta de um treinamento mais completo. A tarefa de agrupamento de verbos mostrou que a sintaxe e a semântica são igualmente importantes para o agrupamento. Este estudo contribui para a área de Linguística, com um léxico de verbos anotados semanticamente, e também para a Computação, com dados que podem ser consultados e processados para diversas aplicações do PLN, principalmente por estarem disponíveis nos formatos XML e SQL. / This dissertation aims at developing a lexical resource of verbs annotated with semantic roles, called VerbLexPor, and based on other resources, such as VerbNet, PropBank, and FrameNet. The theoretical bases of this study lies in Corpus Linguistics and Natural Language Processing (NLP), so that it aims at contributing to both Linguistics and Computer Science. The hypotheses are: a) one set of semantic roles can be applied to different genres; and b) the differences among genres are shown by the ranking of semantic roles. The development of VerbLexPor has two corpora at the basis: a specialized one, with more than 1.6 million words, composed by scientific papers in the field of Cardiology from three Brazilian journals; and a non-specialized one, with more than 1 million words, composed by newspaper articles from Diário Gaúcho. The corpora were analyzed with the parser PALAVRAS, and sentence, verb and argument information was extracted and stored in a database. VerbLexPor has 192 verbs and more than 15 thousand arguments annotated with semantic roles, distributed among more than 6 thousand sentences. We observed that Diário Gaúcho has a more direct syntax, with less passive voice and adjuncts, while Cardiology has more passive voice and more INSTRUMENTS for subjects, and fewer AGENTS. We also conducted some parallel experiments, such as semantic role labeling with multiple annotators and automatic verbal clustering. In the multiple annotators task, each of them annotated exactly the same 25 sentences. They received an annotation manual and basic training (explanation on the task and two annotation examples). We used multi-π to evaluate agreement among annotators, and results were π = 0,25. Reasons for this low agreement may be a lack of a thoroughly developed training. The verbal clustering task showed that syntax and semantics are equally important for verbal clustering. This study contributes to Linguistics, with a verbal lexicon annotated with semantic roles, and also to Computer Science, with data that can be assessed and processed for various NLP applications, especially because the data are available in both XML and SQL formats.

Esta tese propõe um recurso léxico de verbos com anotação de papéis semânticos, denominado VerbLexPor, baseado em recursos como VerbNet, PropBank e FrameNet. As bases teóricas da proposta são interdisciplinares e retiradas da Linguística de Corpus e do Processamento de Linguagem Natural (PLN), visando-se a contribuir para a Linguística e para a Computação. As hipóteses de pesquisa são: a) um mesmo conjunto de papéis semânticos pode ser aplicado a diferentes gêneros textuais; e b) as diferenças entre esses gêneros se destacam no ranqueamento dos papéis semânticos. O desenvolvimento do VerbLexPor se apoia em dois corpora: um especializado, com mais de 1,6 milhão de palavras, composto por artigos científicos de Cardiologia de três periódicos brasileiros; e um não especializado, com mais de 1 milhão de palavras composto por artigos do jornal popular Diário Gaúcho. Os corpora foram anotados com o parser PALAVRAS, e as informações de sentenças, verbos e argumentos foram extraídas e armazenadas em um banco de dados. O VerbLexPor tem 192 verbos e mais de 15 mil argumentos anotados distribuídos em mais de 6 mil sentenças. Observou-se que o corpus do Diário Gaúcho privilegia uma sintaxe direta e pouco uso de voz passiva e adjuntos, enquanto o corpus de Cardiologia apresenta mais voz passiva e um maior uso de INSTRUMENTOS na posição de sujeito, além de uma menor incidência de AGENTES. Foram realizados também alguns experimentos paralelos, como a anotação de papéis semânticos por vários anotadores e o agrupamento automático de verbos. Na tarefa de múltiplos anotadores, cada um anotou exatamente as mesmas 25 orações. Os anotadores receberam um manual de anotação e um treinamento básico (explicação sobre a tarefa e dois exemplos de anotação). Usou-se o cálculo de multi-π para avaliar a concordância entre os anotadores, e o resultado foi de π = 0,25. Os motivos para essa concordância baixa podem estar na falta de um treinamento mais completo. A tarefa de agrupamento de verbos mostrou que a sintaxe e a semântica são igualmente importantes para o agrupamento. Este estudo contribui para a área de Linguística, com um léxico de verbos anotados semanticamente, e também para a Computação, com dados que podem ser consultados e processados para diversas aplicações do PLN, principalmente por estarem disponíveis nos formatos XML e SQL. / This dissertation aims at developing a lexical resource of verbs annotated with semantic roles, called VerbLexPor, and based on other resources, such as VerbNet, PropBank, and FrameNet. The theoretical bases of this study lies in Corpus Linguistics and Natural Language Processing (NLP), so that it aims at contributing to both Linguistics and Computer Science. The hypotheses are: a) one set of semantic roles can be applied to different genres; and b) the differences among genres are shown by the ranking of semantic roles. The development of VerbLexPor has two corpora at the basis: a specialized one, with more than 1.6 million words, composed by scientific papers in the field of Cardiology from three Brazilian journals; and a non-specialized one, with more than 1 million words, composed by newspaper articles from Diário Gaúcho. The corpora were analyzed with the parser PALAVRAS, and sentence, verb and argument information was extracted and stored in a database. VerbLexPor has 192 verbs and more than 15 thousand arguments annotated with semantic roles, distributed among more than 6 thousand sentences. We observed that Diário Gaúcho has a more direct syntax, with less passive voice and adjuncts, while Cardiology has more passive voice and more INSTRUMENTS for subjects, and fewer AGENTS. We also conducted some parallel experiments, such as semantic role labeling with multiple annotators and automatic verbal clustering. In the multiple annotators task, each of them annotated exactly the same 25 sentences. They received an annotation manual and basic training (explanation on the task and two annotation examples). We used multi-π to evaluate agreement among annotators, and results were π = 0,25. Reasons for this low agreement may be a lack of a thoroughly developed training. The verbal clustering task showed that syntax and semantics are equally important for verbal clustering. This study contributes to Linguistics, with a verbal lexicon annotated with semantic roles, and also to Computer Science, with data that can be assessed and processed for various NLP applications, especially because the data are available in both XML and SQL formats.

Programming and the possibility to express one’s intent to a machine is becoming a very important skill in our digitalizing society. Today, instructing a machine, such as a computer to perform actions is done through programming. What if this could be done with human language? This thesis examines how new technologies and methods in the form of Natural Language Processing can be used to make programming more accessible by translating intent expressed in natural language into code that a computer can execute. Related research has studied using natural language as a programming language and using natural language to instruct robots. These studies have shown promising results but are hindered by strict syntaxes, limited domains and inability to handle ambiguity. Studies have also been made using Natural Language Processing to analyse source code, turning code into natural language. This thesis has the reversed approach. By utilizing Natural Language Processing techniques, an intent can be translated into code containing concepts such as sequential execution, loops and conditional statements. In this study, a system for converting intent, expressed in English sentences, into code is developed. To analyse this approach to programming, an evaluation framework is developed, evaluating the system during the development process as well as usage of the final system. The results show that this way of programming might have potential but conclude that the Natural Language Processing models still have too low accuracy. Further research is required to increase this accuracy to further assess the potential of this way of programming.