Identifying Semantic Relations in Text for Information Retrieval and Information Extraction

Automatic identification of semantic relations in text is a difficult problem, but is important for many applications. It has been used for relation matching in information retrieval to retrieve documents that contain not only the concepts but also the relations between concepts specified in the user’s query. It is an integral part of information extraction—extracting from natural language text, facts or pieces of information related to a particular event or topic. Other potential applications are in the construction of relational thesauri (semantic networks of related concepts) and other kinds of knowledge bases, and in natural language processing applications such as machine translation and computer comprehension of text. This chapter examines the main methods used for identifying semantic relations automatically and their application in information retrieval and information extraction.