No abstract

Informative aspects represent the basic units of information in texts. For example, in news texts they could represent the following information: what happened, when it happened and where it happened. With the identification of these aspects, it is possible to automate some NLP tasks such as Summarization, Question Answering and Information Extraction. Microaspects --a type of informative aspects--represent local segments of the sentence. In this paper, we automatically identify microaspects using Semantic Role Labeling, Named-Entity Recognition, Handcrafted Rules and Machine Learning techniques. We evaluate our proposal using the CSTNews journalistic corpus, which has manually annotated aspects. The results are satisfactory, and prove that microaspects can be automatically identified in news texts with acceptable performance.

Aspect-based opinion summarization is the task of automatically generating a summary for some aspects of a specific topic from a set of opinions. In most cases, to evaluate the quality of the automatic summaries, it is necessary to have a reference corpus of human summaries to analyze how similar they are. The scarcity of corpora in that task has been a limiting factor for many research works. In this paper, we introduce OpiSums-PT, a corpus of extractive and abstractive summaries of opinions written in Brazilian Portuguese. We use this corpus to analyze how similar human summaries are and how people take into account the issues of aspect coverage and sentiment orientation to generate manual summaries. The results of these analyses show that human summaries are diversified and people generate summaries only for some aspects, keeping the overall sentiment orientation with little variation.