Anaphora Resolution Module Research Articles

Detection and categorization of bacteria habitats using shallow linguistic analysis.

BackgroundInformation regarding bacteria biotopes is important for several research areas including health sciences, microbiology, and food processing and preservation. One of the challenges for scientists in these domains is the huge amount of information buried in the text of electronic resources. Developing methods to automatically extract bacteria habitat relations from the text of these electronic resources is crucial for facilitating research in these areas.MethodsWe introduce a linguistically motivated rule-based approach for recognizing and normalizing names of bacteria habitats in biomedical text by using an ontology. Our approach is based on the shallow syntactic analysis of the text that include sentence segmentation, part-of-speech (POS) tagging, partial parsing, and lemmatization. In addition, we propose two methods for identifying bacteria habitat localization relations. The underlying assumption for the first method is that discourse changes with a new paragraph. Therefore, it operates on a paragraph-basis. The second method performs a more fine-grained analysis of the text and operates on a sentence-basis. We also develop a novel anaphora resolution method for bacteria coreferences and incorporate it with the sentence-based relation extraction approach.ResultsWe participated in the Bacteria Biotope (BB) Task of the BioNLP Shared Task 2013. Our system (Boun) achieved the second best performance with 68% Slot Error Rate (SER) in Sub-task 1 (Entity Detection and Categorization), and ranked third with an F-score of 27% in Sub-task 2 (Localization Event Extraction). This paper reports the system that is implemented for the shared task, including the novel methods developed and the improvements obtained after the official evaluation. The extensions include the expansion of the OntoBiotope ontology using the training set for Sub-task 1, and the novel sentence-based relation extraction method incorporated with anaphora resolution for Sub-task 2. These extensions resulted in promising results for Sub-task 1 with a SER of 68%, and state-of-the-art performance for Sub-task 2 with an F-score of 53%.ConclusionsOur results show that a linguistically-oriented approach based on the shallow syntactic analysis of the text is as effective as machine learning approaches for the detection and ontology-based normalization of habitat entities. Furthermore, the newly developed sentence-based relation extraction system with the anaphora resolution module significantly outperforms the paragraph-based one, as well as the other systems that participated in the BB Shared Task 2013.

The role of statistical and semantic features in single-document extractive summarization

This paper reports on the further results of the ongoing research analyzing the impact of a range of commonly used statistical and semantic features in the context of extractive text summarization. The features experimented with include word frequency, inverse sentence and term frequencies, stopwords filtering, word senses, resolved anaphora and textual entailment. The obtained results demonstrate the relative importance of each feature and the limitations of the tools available. It has been shown that the inverse sentence frequency combined with the term frequency yields almost the same results as the latter combined with stopwords filtering that in its turn proved to be a highly competitive baseline. To improve the suboptimal results of anaphora resolution, the system was extended with the second anaphora resolution module. The present paper also describes the first attempts of the internal document data representation.

Use of Domain Knowledge in Resolving Pronominal Anaphora

Abstract. The research reported here has been conducted in the context of the Plinius project, which aims at semi-automatic knowledge acquisition from short natural-language texts. In this framework, a system has been developed for finding the antecedents of pronominal anaphora, in particular 'it'- and 'its'- anaphora. The anaphora resolution module operates on parser output and can make use of information generated by the parser; the lexicon gives the conceptual representations corresponding to the words. The algorithm for anaphora resolution involves three steps: (i) Assemble: construct a list of discourse entities (DEs); (ii) Identify: identify anaphoric DEs; (iii) Select: select, for each anaphoric DE, another DE from the list of DEs as its antecedent. The third step applies four constraints, i.e. rules to which a DE must conform in order to be a valid candidate: (a) semantic type agreement; (b) number agreement; (c) projection constraint; (d) conceptual compatibility. Constraints (a, b, c) are linguistic, while (d) is domain-related. The algorithm has been tested on three texts. It turns out that applying (d) before (a, b, c) considerably improves efficiency.