Abstract. An object model of a text is de ned, and structural and manipulative aspects of the model are presented. The model proposed supports text in its general sence (as a natural language document), which comprises structural, syntactic, semantic, orthographic, stylistic properties of both

Natural Language Processing (NLP) techniques to the problem of accurately classifying the sentiment a document contains relating to a certain subject. Common NLP methods that are implemented in pursuit this goal include part of speech tagging, grammatical structure parsing, and coreference resolution

the facts corresponding to the design being documented. Our approach is to translate the Statechart into a propositional formula, then translate this formula into a natural language report. In the later translation, pragmatic e ects arise due to the way the information is presented. Whereas such e ects can

This paper attempts to systematize natural language analysis process by (1) use of a partitioned semantic network formalism as the meaning representation and (2) stepwise translation based on Montague Grammar. The meaning representation is obtained in two steps. The first step translates natural

, in practice, ACPs are commonly written in Natural Language (NL) and buried in large documents such as requirements documents, not directly checkable for correctness. It is very tedious and error-prone to manually identify and extract ACPs from these NL documents, and validate NL functional requirements

Abstract not found

We propose a method to compare semantically two natural language texts. The process is realized in two steps, the first translates the texts into description logics terminologies. The second computes the difference between the terminologies obtained. We show how the best covering problem can

Most of the existing plagiarism detection systems compare a text to a database of other texts. These external approaches, however, are vulnerable because texts not contained in the database cannot be detected as source texts. This paper examines an internal plagiarism detection method that uses style markers from authorship attribution studies in order to find stylistic changes in a text. These changes might pinpoint plagiarized passages. Additionally, a new style marker called "specific words" is introduced. A pre-study tests if the style markers can "fingerprint" an author's style and if they are constant with sample size. It is shown that vocabulary richness measures do not fulfil these prerequisites. The other style markers - simple ratio measures, readability scores, frequency lists, and entropy measures - have these characteristics and are, together with the new specific words measure, used in a main study with an unsupervised approach for detecting stylistic changes in plagiarized texts at sentence and paragraph levels. It is shown that at these small levels the style markers generally cannot detect plagiarized sections because of intra-authorial stylistic variations (i.e. noise), and that at bigger levels the results are strongly a#ected by the sliding window approach. The specific words measure, however, can pinpoint single sentences written by another author.

The Internet and even our personal computers are full of unlabeled text content and we could benefit from tools that automatically organize and tag this text content so that we can quickly access the appropriate content when needed. Supervised learning algorithms for text classification that learn from labeled training examples are already available, however they rely on future data being classified to bear similarity to the training data for good performance and they often require a large amount of labeled training data. One major problem with supervised learning approaches is that they cannot easily generalize to terms that they have not seen before. So over time as new terms (like person names) enter the public lexicon, approaches trained on older data may have trouble generalizing to these new terms, which often bear a lot of informational content for purposes of text classification. However, there are rich knowledge sources like Wikipedia that are frequently updated and which carry rich category information about text terms like person names, organizations, and geographical locations, collectively termed named entities. This report investigates whether a knowledge-based approach to text classification that leverages Wikipedia's knowledge of named entities can outperform various supervised learning algorithms. The results show that the algorithm has some advantages to the current supervised learning algorithms, especially when little training data is available, but also a few weaknesses that need further improvement

A great part of the product knowledge in manufacturing enterprises is only available in the form of natural language documents. The know-how recorded in these documents is an essential resource for successful competition in the market. From the viewpoint of knowledge management, however, documents