Open-Domain Question–Answering

Abstract

An important part of our information-gathering behavior has always been to find out what other people think. With the growing availability and popularity of opinion-rich resources such as online review sites and personal blogs, new opportunities and challenges arise as people now can, and do, actively use information technologies to seek out and understand the opinions of others. The sudden eruption of activity in the area of opinion mining and sentiment analysis, which deals with the computational treatment of opinion, sentiment, and subjectivity in text, has thus occurred at least in part as a direct response to the surge of interest in new systems that deal directly with opinions as a first-class object. This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems. Our focus is on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis. We include material on summarization of evaluative text and on broader issues regarding privacy, manipulation, and economic impact that the development of opinion-oriented information-access services gives rise to. To facilitate future work, a discussion of available resources, benchmark datasets, and evaluation campaigns is also provided.

Question Focus Recognition in Question Answering Systems

“…The user use an explicit set of answer types emphasize the importance of summarizing the given natural language question into a single word which clarifies the type of the expected answer: according to [4] the question focus is defined as "a noun phrase composed of several words and in some Natural Language Question In question Q6, the word company emphasizes the type of the answer. In question Q7 and the noun phrase "the largest city in Germany" specifies the focus of the question, while at the same time its head noun city specifies a type/class of the answer.…”

Using Bio-inspired intelligence for Web opinion Mining

“…Opinion mining (ΟΜ) has lately become a topic of interest trying to combine statistics, Artificial Intelligence and Data Mining technologies in a unified framework [24]. It is a recent subdiscipline at the crossroads of information retrieval and computational linguistics which is concerned not with the topic a document is about, but with the opinion it expresses.…”

Toward automatic facet analysis and need negotiation

“…One effective strategy has been to provide users with explicit control over query terms (Koenemann and Belkin, 1996), but it would be preferable to operate at the level of concepts, in conjunction with the related work discussed above. The integration of named-entity detection with information retrieval in the context of factoid question answering (Prager, 2007) provides a successful example of managing concept-term mappings. Factoid question answering systems primarily deal with the subcase where concepts are represented by entities such as people, organizations, dates, etc.…”