No description available.

A anotação de papéis semânticos (APS) é uma subárea do Processamento de Línguas Naturais (PLN) que começou a ser explorada para a língua inglesa a partir de 2002. Seu objetivo é detectar estruturas de predicador e argumentos em sentenças escritas, que correspondem a descrições de eventos (normalmente feitas por verbos); seus participantes, como agente e paciente; e circunstâncias, como tempo, local, etc. Diversas aplicações de PLN, como tradução automática e recuperação de informação, têm obtido melhorias em seu desempenho ao empregar a APS como uma etapa de pré-processamento. Para a língua portuguesa, os avanços na pesquisa de APS são ainda muito incipientes. Dado que a grande maioria dos trabalhos encontrados na literatura desta área emprega aprendizado de máquina supervisionado, um fator limitante tem sido a ausência de dados rotulados em português, problema que apenas recentemente foi parcialmente resolvido com a criação do PropBank-Br. Este recurso segue o modelo de anotação usado no Prop- Bank, o principal conjunto de dados rotulados empregado na tarefa de APS para a língua inglesa. Ainda assim, o PropBank-Br contém menos de um décimo do total de instâncias de dados presentes no PropBank original. Outro ponto a ser observado é que a abordagem mais comum para a APS baseia-se na extração de uma grande quantidade de informação linguística das sentenças de entrada para ser usada por classificadores automáticos. Tal abordagem mostra-se extremamente dependente de outras ferramentas de PLN, característica particularmente indesejável no caso da língua portuguesa, que não possui muitos recursos livremente disponíveis. Em contrapartida, uma outra abordagem bem sucedida encontrada na literatura abre mão do uso de conhecimento linguístico explícito e associa palavras a sequências numéricas, cujos valores são ajustados durante o treinamento de uma rede neural artificial. Estas sequências são então empregadas pela rede para realizar a APS, e podem servir também para outras tarefas de PLN. O presente trabalho seguiu o segundo método descrito acima. Foram implementadas alterações nesse método que permitiram um ganho de desempenho em comparação com sua versão original quando testada no PropBank-Br. A versão final do sistema desenvolvido está pronta para uso e poderá auxiliar pesquisas de PLN em português / Semantic Role Labeling (SRL) is a subfield of Natural Language Processing (NLP) which began to be explored for English in 2002. Its goal is to detect structures of predicate and arguments in written sentences, which correspond to descriptions of events (usually made by verbs); its participants, such as agents and patients; and circumstances, such as time, place, etc. Many NLP applications, as machine translation and information retrieval, have achieved performance gains by applying SRL as a pre-processing step. For Portuguese, advances in SRL research are still in very early stages. Given that the majority of works found in the literature of this area employ supervised machine learning, a limiting factor has been the absence of labeled data in Portuguese, a problem that only recently was partially solved with the creation of PropBank-Br. This resource follows the annotation model used in PropBank, the main labeled data set employed in the SRL task for English. Even then, PropBank-Br contains less than one tenth of the data instances present in the original PropBank. Another point to be observed is that the most common approach to SRL is based on the extraction of a great amount of information from the input sentences to be used by automatic classifiers. Such approach is extremely dependent on other NLP tools, a particularly undesirable feature in the case of Portuguese, which does not have many freely available resources. On the other hand, another succesful approach found in the literature forgoes the use of explicit linguistic knowledge and associates words to numeric sequences, whose values are adjusted during the training of an artificial neural network. These sequences are then employed by the network in order to perform SRL, and can also be useful for other NLP tasks. This work followed the second method described above. Modifications on this method were implemented and allowed for a performance gain in comparison with its original version when tested on PropBank-Br. The final version of the developed system is ready for use and will be able to help NLP research in Portuguese

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.

The aim of this paper is to investigate the semantic and syntactic properties of the -­ee suffix in English. The -­ee suffix was borrowed from the French ‑­é suffix during the late Middle Ages, when French started to exert its linguistic influence on English. Previous research suggests that the -­ee suffix in English exhibits the semantic properties of sentience, episodicity and passivity. Syntactically, the function of the ­-ee suffix in English may suggest ergativity. Furthermore, it has been suggested that contextual anchoring is involved in the use of the -­ee suffix. I explored these characteristics of the ­-ee suffix by testing non‑­standardised ­-ee suffixed nouns with the mentioned semantic and syntactic properties. The process of differentiating non‑­standardised from standardised -­ee suffixed nouns was done with the help of a well­-established dictionary and the Internet. The results showed that sentience and episodicity applied to most -­ee suffixed nouns. In addition, passivity was an important feature in the -­ee nominalisation of transitive stem verbs. When the meaning of ­-ee suffixed nouns was complex, contextual anchoring served to facilitate the understanding of the meaning of the noun. Syntactically, the relationship between the ‑ee suffix and ergativity was weak. Thus, it can be concluded that the use of the ‑ee suffix is controlled by several semantic properties simultaneously, whereas the syntactic properties are relatively unimportant. / Den här uppsatsen undersöker -ee-suffixets semantiska och syntaktiska egenskaper i engelska. Suffixet lånades från det franska suffixet -é under senmedeltiden, när det franska språket började påverka engelska. Tidigare forskning hävdar att det engelska -ee-suffixet påvisar semantiska egenskaper såsom animacitet, episodicitet och passivitet. Syntaktiskt sett kan suffixet även tyda på ergativitet. Användning av suffixet är i viss mån förknippad med förankringen i kontexten. Ickestandardiserade -ee -avledda substantiv identifierades och deras semantiska och syntaktiska egenskaper undersöktes. Urvalet av icke-standardiserade och standiserade substantiv utfördes med hjälp av ett väletablerat lexikon och Internet. Resultatet visade att de flesta -ee-avledda substantiven uppvisar episodicitet och majoriteten även animacitet. Passivitet är ett viktigt kännetecken av suffixet när det gäller substantiveringen av transitiva verb. Betydelserna av vissa mer svårtydda eeavledda substantiv förankras ibland i kontexten med exempelvis förekomsten av er-/-or-avledda motsvarigheter. Syntaktiskt sett är ergativitet inte ett tydligt särdrag av -ee-suffixet. Sammanfattningsvis kan det hävdas att -ee-suffixets användning styrs framför allt av samverkan mellan flera olika semantiska aspekter, medan den syntaktiska egenskapen, ergativitet, är relativt oväsentlig.

A anotação de papéis semânticos (APS) é uma subárea do Processamento de Línguas Naturais (PLN) que começou a ser explorada para a língua inglesa a partir de 2002. Seu objetivo é detectar estruturas de predicador e argumentos em sentenças escritas, que correspondem a descrições de eventos (normalmente feitas por verbos); seus participantes, como agente e paciente; e circunstâncias, como tempo, local, etc. Diversas aplicações de PLN, como tradução automática e recuperação de informação, têm obtido melhorias em seu desempenho ao empregar a APS como uma etapa de pré-processamento. Para a língua portuguesa, os avanços na pesquisa de APS são ainda muito incipientes. Dado que a grande maioria dos trabalhos encontrados na literatura desta área emprega aprendizado de máquina supervisionado, um fator limitante tem sido a ausência de dados rotulados em português, problema que apenas recentemente foi parcialmente resolvido com a criação do PropBank-Br. Este recurso segue o modelo de anotação usado no Prop- Bank, o principal conjunto de dados rotulados empregado na tarefa de APS para a língua inglesa. Ainda assim, o PropBank-Br contém menos de um décimo do total de instâncias de dados presentes no PropBank original. Outro ponto a ser observado é que a abordagem mais comum para a APS baseia-se na extração de uma grande quantidade de informação linguística das sentenças de entrada para ser usada por classificadores automáticos. Tal abordagem mostra-se extremamente dependente de outras ferramentas de PLN, característica particularmente indesejável no caso da língua portuguesa, que não possui muitos recursos livremente disponíveis. Em contrapartida, uma outra abordagem bem sucedida encontrada na literatura abre mão do uso de conhecimento linguístico explícito e associa palavras a sequências numéricas, cujos valores são ajustados durante o treinamento de uma rede neural artificial. Estas sequências são então empregadas pela rede para realizar a APS, e podem servir também para outras tarefas de PLN. O presente trabalho seguiu o segundo método descrito acima. Foram implementadas alterações nesse método que permitiram um ganho de desempenho em comparação com sua versão original quando testada no PropBank-Br. A versão final do sistema desenvolvido está pronta para uso e poderá auxiliar pesquisas de PLN em português / Semantic Role Labeling (SRL) is a subfield of Natural Language Processing (NLP) which began to be explored for English in 2002. Its goal is to detect structures of predicate and arguments in written sentences, which correspond to descriptions of events (usually made by verbs); its participants, such as agents and patients; and circumstances, such as time, place, etc. Many NLP applications, as machine translation and information retrieval, have achieved performance gains by applying SRL as a pre-processing step. For Portuguese, advances in SRL research are still in very early stages. Given that the majority of works found in the literature of this area employ supervised machine learning, a limiting factor has been the absence of labeled data in Portuguese, a problem that only recently was partially solved with the creation of PropBank-Br. This resource follows the annotation model used in PropBank, the main labeled data set employed in the SRL task for English. Even then, PropBank-Br contains less than one tenth of the data instances present in the original PropBank. Another point to be observed is that the most common approach to SRL is based on the extraction of a great amount of information from the input sentences to be used by automatic classifiers. Such approach is extremely dependent on other NLP tools, a particularly undesirable feature in the case of Portuguese, which does not have many freely available resources. On the other hand, another succesful approach found in the literature forgoes the use of explicit linguistic knowledge and associates words to numeric sequences, whose values are adjusted during the training of an artificial neural network. These sequences are then employed by the network in order to perform SRL, and can also be useful for other NLP tasks. This work followed the second method described above. Modifications on this method were implemented and allowed for a performance gain in comparison with its original version when tested on PropBank-Br. The final version of the developed system is ready for use and will be able to help NLP research in Portuguese

The purpose of this essay is to examine metaphors in cancer contexts, and in particular war and military metaphors. A four step approach was performed for the examination. The use over time has been studied for metaphorical linguistic expressions including the words fight and battle in the Corpus of Contemporary American English in the categories Academic Journals, Magazines and Newspapers. A general corpus search for the word cancer in the same categories has been made to investigate what kinds of metaphorical linguistic expressions could be found. The goal was to examine possible development of the use of other expressions than the dominant martial ones for the period 2005 - 2011. The findings were also investigated to see which thematic role for the word cancer was the most frequent in the categories. To complement the corpus findings, an inquiry was sent out to explore how writers of research articles reason when they use expressions such as fight against cancer or battle with cancer in their texts. The corpus findings show that the martial metaphorical linguistic expressions are more often used within the categories Newspapers and Magazines. In the category Academic journals the occurrences are fewer. The most common metaphor alternatives were within the area of sports. The study of semantic roles shows that the word cancer appears most often in the role of patient. The agent role occurred slightly more often in the newspaper category than in the other text categories investigated. The result of the inquiry suggests that some researchers use martial metaphors out of routine. The four step approach of the study reveals a complex image of the use of metaphors in cancer contexts. Detection of trends for the use of metaphorical linguistic expressions possibly demands a longer time interval than the studied period.

Inspired by an ongoing debate in the clinical sciences concerning the value of evil as a label for human behavior (Mowrer 1960, Staub 1999, Wellman 2000, Williams 2004 etc.), this thesis examines the semantic role of AGENT in the lexical items sick and evil. Williams makes the argument that the label evil removes responsibility from the doctor, whereas, the label sick empowers the doctor in bringing about a cure. While this view is not universally accepted in the field, it does bring to light an interesting question in applied linguistic semantics as to the assignment of agency with respect to sick and evil. Based on the close association of the meanings of sick and evil that stems from historical, psychological, and legal perspectives, this thesis assumes that the semantic feature [+/-RESPONSIBILITY] is assigned to either sick or evil at some point along a continuum. This continuum establishes EVIL at one pole and receives [+RESPONSIBILITY] while SICK is at the opposite pole and receives [-RESPONSIBILITY]. Using a variety of prompts to survey 106 respondents, the continuum model is shown to be only partially true. There is a correlation between NON-RESPONSIBILITY and SICK. Also, a continuum exists that allows the assignment of PARTIAL RESPONSIBILITY to both terms. However, there is no definitive significant correlation between RESPONSIBILITY and EVIL. Further conclusions include the indication of adherence to a legal model of guilt, innocence, and insanity in the general conceptions of SICK and EVIL. Also, demographic variation shows little predictive potential in how people perceive SICK and EVIL. This thesis concludes with a proposal for an alternative model using a Greimas Square to represent the conceptions of SICK and EVIL that more appropriately fits the trends found in the survey data.

This study explores the use of war metaphors, more specifically metaphors centred on the verb, in modern French newspaper prose from three principal angles.  The first part of the analysis shows that the verbs of war used are metaphorical rather than concrete. However, the vast majority of the metaphors stem from only five verbs, namely attaquer, affronter, combattre, défendre and lutter.  The second part of the analysis focuses on these five verbs and their metaphorical uses. It is shown that it is the semantic role of patient that separates a metaphorical use from a concrete use. A classification of the patients according to semantic fields reveals that each of the five verbs shows a distinct preference for a certain type of patient and the verbs also differ in whether their patients have negative or positive connotations. This creates an image of five verbs, each of which is conventionalised in a certain linguistic context.  The final chapter of the analysis investigates war metaphors from a textual perspective, analysing their usage according to three parameters: position, function and target domains. The position that is the most susceptible to war metaphors is the initial position. The textual functions of metaphors are divided into one semantic and three pragmatic functions. The semantic function structures the theme of an article in terms of war, construing an antagonism by means of elaborating or extending a conventional metaphor. The pragmatic functions considered are argumentative, descriptive and expressive. In the articles studied, war metaphors have mostly a descriptive or argumentative function. Finally, the target domains and their interconnections with the source domain WAR are considered, showing that the war metaphors are linked to power or the lack thereof. The metaphor often describes the person in power, but the case can be reversed with the metaphor describing the powerless resisting or fighting the person in power.

The subject of the present study is an analysis of five ditransitive verbs: give, lend, send, offer and show. The study focuses on the position of the two objects and on the factors that have an impact on the object ordering. An attempt is here made to provide a systematic overview of the position of the two objects with respect to their realization (i.e. substantival or pronominal). As regards the realization of the two objects, four types are distinguished: i. both Oi /Oprep and Od realized by nouns; ii. both Oi /Oprep and Od realized by pronouns; iii. Oi /Oprep realized by a noun and Od by a pronoun; iv. Oi /Oprep realized by a pronoun and Od by a noun. The position of the objects is assumed to be associated with the distribution of communicative dynamism or in other words with the principle of end-focus, i.e. that given information tends to precede new information. The second principle that operates in the ordering the two objects is the principle of end-weight. Of the three (or four, including intonation) factors whose interplay determines the FSP function of a clause element, in the case of ditransitive complementation the most important role is played by the contextual factor. Therefore, particular attention is paid to the context-dependence / independence of the two objects. The present...