Concept Mining, AI

In this paper a methodology to mine the concepts from documents and use these concepts to generate an objective summary of the claims section of the patent documents is proposed. Conceptual Graph (CG) formalism as proposed by Sowa (Sowa 1984) is used in this work for representing the concepts and their relationships. Automatic identification of concepts and conceptual relations from text documents is a challenging task. In this work the focus is on the analysis of the patent documents, mainly on the claim's section (Claim) of the documents. There are several complexities in the writing style of these documents as they are technical as well as legal. It is observed that the general in-depth parsers available in the open domain fail to parse the 'claims section' sentences in patent documents. The failure of in-depth parsers has motivated us, to develop methodology to extract CGs using other resources. Thus in the present work shallow parsing, NER and machine learning technique for extracting concepts and conceptual relationships from sentences in the claim section of patent documents is used. Thus, this paper discusses i) Generation of CG, a semantic network and ii) Generation of abstractive summary of the claims section of the patent. The aim is to generate a summary which is 30% of the whole claim section. Here we use Restricted Boltzmann Machines (RBMs), a deep learning technique for automatically extracting CGs. We have tested our methodology using a corpus of 5000 patent documents from electronics domain. The results obtained are encouraging and is comparable with the state of the art systems.

The gigantic growth of information on the Internet makes discovery information challenging and time consuming. We are encircled by a plethora of data in the form of blogs, papers, reviews, and comments on different websites. Recommender systems endow a solution to this situation by automatically capturing user interests and recommending respective information the user may also find relevant. The purpose of developing recommender systems is to detract information overload by retrieving the most pertinent knowledge and services from an enormous amount of data, thereby providing personalized services. The most vital feature of a recommender system is its proficiency to "supposition" a user's preferences and interests by examining the behavior of this user and/or the behavior of other users to originate personalized recommendations. So several research works have been done in this area, but nothing consolidated has been appraised. In this paper, we are going to discuss a brief summary of imperfection in the available recommender system. We are also trying to figure out these shortcomings of the available recommender system to generate a new method that improves these shortcomings.

While conceptual analysis can be facilitated by computer assistance, the absence of proper models for concepts in text has curtailed the development of such tools. The most common heuristic, which consists in identifying keywords as canonical expression of a concept, poses problems of ambiguity and fails to retrieve most of the relevant textual data. In this paper, we present CoFiH, an algorithm that exploits topics in order to retrieve segments relevant to a given concept. It is then applied to C.S. Peirce's Collected Papers to facilitate the analysis of Peirce's concept of LAW. Compared to the baseline, CoFiH produces better recall and enables a meaningful analysis along several topics.