Coreference resolution for portuguese using parallel corpora word alignment

A área de Extração da Informação tem como objetivo essencial investigar métodos e técnicas para transformar a informação não estruturada presente em textos de língua natural em dados estruturados. Um importante passo deste processo é a resolução de correferência, tarefa que identifica diferentes sintagmas nominais que se referem a mesma entidade no discurso. A área de estudos sobre resolução de correferência tem sido extensivamente pesquisada para a Língua Inglesa (Ng, 2010) lista uma série de estudos da área, entretanto tem recebido menos atenção em outras línguas. Isso se deve ao fato de que a grande maioria das abordagens utilizadas nessas pesquisas são baseadas em aprendizado de máquina e, portanto, requerem uma extensa quantidade de dados anotados.

Variable binding and coreference in sentence comprehension: evidence from eye movements

The hypothesis that pronouns can be resolved via either the syntax or the discourse representation has played an important role in linguistic accounts of pronoun interpretation (e.g. Grodzinsky & Reinhart, 1993). We report the results of an eye-movement monitoring study investigating the relative timing of syntactically-mediated variable binding and discourse-based coreference assignment during pronoun resolution. We examined whether ambiguous pronouns are preferentially resolved via either the variable binding or coreference route, and in particular tested the hypothesis that variable binding should always be computed before coreference assignment. Participants’ eye movements were monitored while they read sentences containing a pronoun and two potential antecedents, a c-commanding quantified noun phrase and a non c-commanding proper name. Gender congruence between the pronoun and either of the two potential antecedents was manipulated as an experimental diagnostic for dependency formation. In two experiments, we found that participants’ reading times were reliably longer when the linearly closest antecedent mismatched in gender with the pronoun. These findings fail to support the hypothesis that variable binding is computed before coreference assignment, and instead suggest that antecedent recency plays an important role in affecting the extent to which a variable binding antecedent is considered. We discuss these results in relation to models of memory retrieval during sentence comprehension, and interpret the antecedent recency preference as an example of forgetting over time.

Structural constraints on pronoun binding and coreference: evidence from eye movements during reading

A number of recent studies have investigated how syntactic and non-syntactic constraints combine to cue memory retrieval during anaphora resolution. In this paper we investigate how syntactic constraints and gender congruence interact to guide memory retrieval during the resolution of subject pronouns. Subject pronouns are always technically ambiguous, and the application of syntactic constraints on their interpretation depends on properties of the antecedent that is to be retrieved. While pronouns can freely corefer with non-quantified referential antecedents, linking a pronoun to a quantified antecedent is only possible in certain syntactic configurations via variable binding. We report the results from a judgment task and three online reading comprehension experiments investigating pronoun resolution with quantified and non-quantified antecedents. Results from both the judgment task and participants' eye movements during reading indicate that comprehenders freely allow pronouns to corefer with non-quantified antecedents, but that retrieval of quantified antecedents is restricted to specific syntactic environments. We interpret our findings as indicating that syntactic constraints constitute highly weighted cues to memory retrieval during anaphora resolution.

A Coreference Service for Enterprise Application Integration using Linked Data

The use of semantic and Linked Data technologies for Enterprise Application Integration (EAI) is increasing in recent years. Linked Data and Semantic Web technologies such as the Resource Description Framework (RDF) data model provide several key advantages over the current de-facto Web Service and XML based integration approaches. The flexibility provided by representing the data in a more versatile RDF model using ontologies enables avoiding complex schema transformations and makes data more accessible using Web standards, preventing the formation of data silos. These three benefits represent an edge for Linked Data-based EAI. However, work still has to be performed so that these technologies can cope with the particularities of the EAI scenarios in different terms, such as data control, ownership, consistency, or accuracy. The first part of the paper provides an introduction to Enterprise Application Integration using Linked Data and the requirements imposed by EAI to Linked Data technologies focusing on one of the problems that arise in this scenario, the coreference problem, and presents a coreference service that supports the use of Linked Data in EAI systems. The proposed solution introduces the use of a context that aggregates a set of related identities and mappings from the identities to different resources that reside in distinct applications and provide different views or aspects of the same entity. A detailed architecture of the Coreference Service is presented explaining how it can be used to manage the contexts, identities, resources, and applications which they relate to. The paper shows how the proposed service can be utilized in an EAI scenario using an example involving a dashboard that integrates data from different systems and the proposed workflow for registering and resolving identities. As most enterprise applications are driven by business processes and involve legacy data, the proposed approach can be easily incorporated into enterprise applications.

Overcoming schema heterogeneity between linked semantic repositories to improve coreference resolution

Schema heterogeneity issues often represent an obstacle for discovering coreference links between individuals in semantic data repositories. In this paper we present an approach, which performs ontology schema matching in order to improve instance coreference resolution performance. A novel feature of the approach is its use of existing instance-level coreference links defined in third-party repositories as background knowledge for schema matching techniques. In our tests of this approach we obtained encouraging results, in particular, a substantial increase in recall in comparison with existing sets of coreference links.

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.

Processing reflexives in a second language: the timing of structural and discourse-level information

We report the results from two eye-movement monitoring experiments examining the processing of reflexive pronouns by proficient German-speaking learners of second language (L2) English. Our results show that the nonnative speakers initially tried to link English argument reflexives to a discourse-prominent but structurally inaccessible antecedent, thereby violating binding condition A. Our native speaker controls, in contrast, showed evidence of applying condition A immediately during processing. Together, our findings show that L2 learners’ initial focusing on a structurally inaccessible antecedent cannot be due to first language influence and is also independent of whether the inaccessible antecedent c-commands the reflexive. This suggests that unlike native speakers, nonnative speakers of English initially attempt to interpret reflexives through discourse-based coreference assignment rather than syntactic binding.

Referenciação anafórica :as anáforas não-correfereciais no livro didático da língua portuguesa

On recent years, it has been observed an increasing interest on referentiation processes, which involves an important field of Text Linguistics and Discourse Analysis studies. The existence of a significant number of international and national publications which focus on this perspective corroborate this finding. Given the textbook importance as a teaching instrument, and the relevance of the referentiation processes to text production and comprehension, we realize that the study of these two topics articulation is taken as a relevant research theme, with consequences to the improvement of Portuguese Language teaching. Taking this into consideration, we intend to analyze the non-coreference anaphors in texts of Portuguese Language textbooks from fifth to eighth grades, adopted in many schools of Pau dos Ferros RN, considering the frequency, genre, kind of anaphor and manifestation form. This study is classified as a documental and qualitative research. We have found out that the indirect anaphor was used in more than a half of the corpus. We have found out, as well, that the literary and press genres do not favor the use of labeling and metadiscursive anaphors. On the other hand, concerning the indirect anaphor, it is clear its abundant use in the literary genre. In what concerns the manifestation forms, we have verified that on labeling and metadiscursive anaphors it is significant the predominance of demonstrative pronouns working as determiners. On the indirect anaphor, we have verified that most of the occurrences do not present a determiner, and for the ones which present it, the majority occurs under the form of definite and indefinite articles. We believe that this work can contribute to the activities which involve questions related to text production and comprehension, since the referentiation processes are intimately related to them

A proposal of algorithm for solving definite descriptions through dialogue structure

En este trabajo proponemos un algoritmo para la resolución de las descripciones definidas en español a través de la estructura del diálogo, mediante la definición de un espacio de accesibilidad anafórico. Este algoritmo está basado en la hipótesis de que la resolución de la anáfora está relacionada con la estructura del diálogo. Así, la resolución de la anáfora mejora si se especifica un espacio de accesibilidad para cada tipo descripción definida según la estructura del diálogo. La utilización de este espacio de accesibilidad anafóico reduce tanto el tiempo de procesamiento como la posibilidad de obtener un antecedente erróneo. Además, la definición de este espacio de accesibilidad depende únicamente de la propia estructura textual del diálogo.

Grammar specification for the recognition of temporal expressions

This paper tells about the recognition of temporal expressions and the resolution of their temporal reference. A proposal of the units we have used to face up this tasks over a restricted domain is shown. We work with newspapers' articles in Spanish, that is why every reference we use is in Spanish. For the identification and recognition of temporal expressions we base on a temporal expression grammar and for the resolution on a dictionary, where we have the information necessary to do the date operation based on the recognized expressions. In the evaluation of our proposal we have obtained successful results for the examples studied.

Event ordering through temporal expression resolution

In this paper a multilingual method for event ordering based on temporal expression resolution is presented. This method has been implemented through the TERSEO system which consists of three main units: temporal expression recognizing, resolution of the coreference introduced by these expressions, and event ordering. By means of this system, chronological information related to events can be extracted from documental databases. This information is automatically added to the documental database in order to allow its use by question answering systems in those cases referring to temporality. The system has been evaluated obtaining results of 91 % precision and 71 % recall. For this, a blind evaluation process has been developed guaranteing a reliable annotation process that was measured through the kappa factor.