Computational approach to anaphora resolution in Spanish dialogues

This paper presents an algorithm for identifying noun-phrase antecedents of pronouns and adjectival anaphors in Spanish dialogues. We believe that anaphora resolution requires numerous sources of information in order to find the correct antecedent of the anaphor. These sources can be of different kinds, e.g., linguistic information, discourse/dialogue structure information, or topic information. For this reason, our algorithm uses various different kinds of information (hybrid information). The algorithm is based on linguistic constraints and preferences and uses an anaphoric accessibility space within which the algorithm finds the noun phrase. We present some experiments related to this algorithm and this space using a corpus of 204 dialogues. The algorithm is implemented in Prolog. According to this study, 95.9% of antecedents were located in the proposed space, a precision of 81.3% was obtained for pronominal anaphora resolution, and 81.5% for adjectival anaphora.

Método para la Construcción Automática de Ontologías Basado en Patrones Lingüísticos

La tesis que se presenta tiene como propósito la construcción automática de ontologías a partir de textos, enmarcándose en el área denominada Ontology Learning. Esta disciplina tiene como objetivo automatizar la elaboración de modelos de dominio a partir de fuentes información estructurada o no estructurada, y tuvo su origen con el comienzo del milenio, a raíz del crecimiento exponencial del volumen de información accesible en Internet. Debido a que la mayoría de información se presenta en la web en forma de texto, el aprendizaje automático de ontologías se ha centrado en el análisis de este tipo de fuente, nutriéndose a lo largo de los años de técnicas muy diversas provenientes de áreas como la Recuperación de Información, Extracción de Información, Sumarización y, en general, de áreas relacionadas con el procesamiento del lenguaje natural. La principal contribución de esta tesis consiste en que, a diferencia de la mayoría de las técnicas actuales, el método que se propone no analiza la estructura sintáctica superficial del lenguaje, sino que estudia su nivel semántico profundo. Su objetivo, por tanto, es tratar de deducir el modelo del dominio a partir de la forma con la que se articulan los significados de las oraciones en lenguaje natural. Debido a que el nivel semántico profundo es independiente de la lengua, el método permitirá operar en escenarios multilingües, en los que es necesario combinar información proveniente de textos en diferentes idiomas. Para acceder a este nivel del lenguaje, el método utiliza el modelo de las interlinguas. Estos formalismos, provenientes del área de la traducción automática, permiten representar el significado de las oraciones de forma independiente de la lengua. Se utilizará en concreto UNL (Universal Networking Language), considerado como la única interlingua de propósito general que está normalizada. La aproximación utilizada en esta tesis supone la continuación de trabajos previos realizados tanto por su autor como por el equipo de investigación del que forma parte, en los que se estudió cómo utilizar el modelo de las interlinguas en las áreas de extracción y recuperación de información multilingüe. Básicamente, el procedimiento definido en el método trata de identificar, en la representación UNL de los textos, ciertas regularidades que permiten deducir las piezas de la ontología del dominio. Debido a que UNL es un formalismo basado en redes semánticas, estas regularidades se presentan en forma de grafos, generalizándose en estructuras denominadas patrones lingüísticos. Por otra parte, UNL aún conserva ciertos mecanismos de cohesión del discurso procedentes de los lenguajes naturales, como el fenómeno de la anáfora. Con el fin de aumentar la efectividad en la comprensión de las expresiones, el método provee, como otra contribución relevante, la definición de un algoritmo para la resolución de la anáfora pronominal circunscrita al modelo de la interlingua, limitada al caso de pronombres personales de tercera persona cuando su antecedente es un nombre propio. El método propuesto se sustenta en la definición de un marco formal, que ha debido elaborarse adaptando ciertas definiciones provenientes de la teoría de grafos e incorporando otras nuevas, con el objetivo de ubicar las nociones de expresión UNL, patrón lingüístico y las operaciones de encaje de patrones, que son la base de los procesos del método. Tanto el marco formal como todos los procesos que define el método se han implementado con el fin de realizar la experimentación, aplicándose sobre un artículo de la colección EOLSS “Encyclopedia of Life Support Systems” de la UNESCO. ABSTRACT The purpose of this thesis is the automatic construction of ontologies from texts. This thesis is set within the area of Ontology Learning. This discipline aims to automatize domain models from structured or unstructured information sources, and had its origin with the beginning of the millennium, as a result of the exponential growth in the volume of information accessible on the Internet. Since most information is presented on the web in the form of text, the automatic ontology learning is focused on the analysis of this type of source, nourished over the years by very different techniques from areas such as Information Retrieval, Information Extraction, Summarization and, in general, by areas related to natural language processing. The main contribution of this thesis consists of, in contrast with the majority of current techniques, the fact that the method proposed does not analyze the syntactic surface structure of the language, but explores his deep semantic level. Its objective, therefore, is trying to infer the domain model from the way the meanings of the sentences are articulated in natural language. Since the deep semantic level does not depend on the language, the method will allow to operate in multilingual scenarios, where it is necessary to combine information from texts in different languages. To access to this level of the language, the method uses the interlingua model. These formalisms, coming from the area of machine translation, allow to represent the meaning of the sentences independently of the language. In this particular case, UNL (Universal Networking Language) will be used, which considered to be the only interlingua of general purpose that is standardized. The approach used in this thesis corresponds to the continuation of previous works carried out both by the author of this thesis and by the research group of which he is part, in which it is studied how to use the interlingua model in the areas of multilingual information extraction and retrieval. Basically, the procedure defined in the method tries to identify certain regularities at the UNL representation of texts that allow the deduction of the parts of the ontology of the domain. Since UNL is a formalism based on semantic networks, these regularities are presented in the form of graphs, generalizing in structures called linguistic patterns. On the other hand, UNL still preserves certain mechanisms of discourse cohesion from natural languages, such as the phenomenon of the anaphora. In order to increase the effectiveness in the understanding of expressions, the method provides, as another significant contribution, the definition of an algorithm for the resolution of pronominal anaphora limited to the model of the interlingua, in the case of third person personal pronouns when its antecedent is a proper noun. The proposed method is based on the definition of a formal framework, adapting some definitions from Graph Theory and incorporating new ones, in order to locate the notions of UNL expression and linguistic pattern, as well as the operations of pattern matching, which are the basis of the method processes. Both the formal framework and all the processes that define the method have been implemented in order to carry out the experimentation, applying on an article of the "Encyclopedia of Life Support Systems" of the UNESCO-EOLSS collection.

Evaluation of pronoun resolution algorithm for Spanish dialogues

In this paper, we present an algorithm for anaphora resolution in Spanish dialogues and an evaluation of the algorithm for pronominal anaphora. The proposed algorithm uses both linguistic information and the structure of the dialogue to find the antecedent of the anaphors. The system has been evaluated on ten dialogues.

Pronoun-dropping or zero anaphora in translation from german into portuguese

In this article I will analyse anaphoric references in German texts and their transaltion into Portuguese. I will take as main corpus Heinrich Böll's novel Haus ohne Hüter and its translation into Portuguese by Jorge Rosa with the title Casa Indefesa. I will concentrate on the use of personal pronouns and possessives in references to both people and objects in source text and target text and I will present patterns of symmetries and asymmetries. I will claim that asymmetries in the translation of such anaphoric references can be accounted for mainly by differences in the pronominal systems and verbal systems of both languages and by differences in the way each language marks theme/topic continuity/discontinuity in discourse. Issues related to style and the translation of anaphors will also be addressed. I will finally raise some questions related to ambiguous references which can not be solved within the scope of syntax or semantics, thus requiring pragmatic interpretation based on cultural knowledge/world knowledge.

Pronoun processing in Broca's aphasia: discourse-syntax effects in ambiguous anaphora resolution

Background: The interpretation of ambiguous subject pronouns in a null subject language, like Greek, requires that one possesses grammatical knowledge of the two subject pronominal forms, i.e., null and overt, and that discourse constraints regulating the distribution of the two pronouns in context are respected. Aims: We investigated whether the topic-shift feature encoded in overt subject pronouns would exert similar interpretive effects in a group of seven participants with Broca’s aphasia and a group of language-unimpaired adults during online processing of null and overt subject pronouns in referentially ambiguous contexts. Method & Procedures: An offline picture–sentence matching task was initially administered to investigate whether the participants with Broca’s aphasia had access to the gender and number features of clitic pronouns. An online self-paced listening picture-verification task was subsequently administered to examine how the aphasic individuals resolve pronoun ambiguities in contexts with either null or overt subject pronouns and how their performance compares to that of language-unimpaired adults. Outcomes & Results: Results demonstrate that the Broca group, along with controls, had intact access to the morphosyntactic features of clitic pronouns. However, the aphasic individuals showed decreased preference for non-salient antecedents in object position during the online resolution of ambiguous overt subject pronouns and preferred to pick the subject antecedent instead. Conclusions: Broca’s aphasic participants’ parsing decisions in the online task reflect their difficulty with establishing topic-shifted interpretations of the ambiguous overt subject pronouns. The presence of a local topic-shift effect in the immediate temporal vicinity of the overt pronoun suggests that sensitivity to the marked informational status of overt pronouns is preserved in the aphasic individuals, yet, it is blocked under conditions of global sentential processing.

Exploring the source of differences and similarities in L1 attrition and heritage speaker competence: evidence from pronominal resolution

Several studies of different bilingual groups including L2 learners, child bilinguals, heritage speakers and L1 attriters reveal similar performance on syntax-discourse interface properties such as anaphora resolution (Sorace, 2011 and references therein). Specifically, bilinguals seem to allow more optionality in the interpretation of overt subject pronouns in null subject languages, such as Greek, Italian and Spanish while the interpretation of null subject pronouns is indistinguishable from monolingual natives. Nevertheless, there is some evidence pointing to bilingualism effects on the interpretation of null subject pronouns too in heritage speakers’ grammars (Montrul, 2004) due to some form of ‘arrested’ development in this group of bilinguals. The present study seeks to investigate similarities and differences between two Greek–Swedish bilingual groups, heritage speakers and L1 attriters, in anaphora resolution of null and overt subject pronouns in Greek using a self-paced listening with a sentence-picture matching decision task at the end of each sentence. The two groups differ in crucial ways: heritage speakers were simultaneous or early bilinguals while the L1 attriters were adult learners of the second language, Swedish. Our findings reveal differences from monolingual preferences in the interpretation of the overt pronoun for both heritage and attrited speakers while the differences attested between the two groups in the interpretation of null subject pronouns affect only response times with heritage being faster than attrited speakers. We argue that our results do not support an age of onset or differential input effects on bilingual performance in pronoun resolution.

Um estudo sócio-discursivo do sistema pronominal dos demonstrativos no português contemporâneo

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Dialogue structure as a preference in anaphora resolution systems

Comunicación presentada en ACIDCA 2000, International Conference on Artificial and Computational Intelligence For Decision, Control and Automation In Engineering and Industrial Applications, Monastir, Tunisia, 22-24 March 2000.

Australian political discourse: Pronominal choice in campaign speeches

The intention behind language used by candidates during an election campaign is to persuade voters to vote for a particular political party. Fundamental to the political arena is construction of identity, group membership and ways of talking about self, others, and the polarizing categories of 'us' and 'them'. This paper will investigate the pragmatics of pronominal choice and the way in which politicians construct and convey their own identities and those of their political opponents within political speeches. Taking six speeches by John Howard and Mark Latham across the course of the 2004 federal election campaign, I look at the ways in which pronominal choice indicates a shifting scope of reference to creat pragmatic effects and serve political functions.

Pronominal and anaphoric reference in agrammatism

Subjects with Broca's aphasia have been shown to display difficulties in on-line and off-line tasks involving personal pronouns and reflexives. Off-line tasks have indicated more errors with pronouns than with reflexives while the reverse has been found in on-line studies. In the present off-line study, the comprehension of sentences containing personal pronouns and reflexives is examined in a group of 10 agrammatic participants. Results indicate that subjects had difficulties with both pronouns and reflexives, particularly with reflexives in sentences that contained a quantificational antecedent, as well as with pronouns in exceptional case marking constructions. It is argued that the low performance that subjects exhibited as a group in pronouns and reflexives indicates two distinct impairments, one that concerns coreference and one that concerns A-dependencies, the latter being a manifestation of a general processing failure to link positions. Poor performance on exceptional case marking constructions compared to simple transitive sentences is claimed to be interpreted within theories for reference assignment that distinguish between the two sentence types. (c) 2007 Elsevier Ltd. All rights reserved.