Natural Language Analysis Research Articles

Mohan Ganesalingam.The Language of Mathematics: A Linguistic and Philosophical Investigation.FoLLI Publications on Logic, Language and Information.

This ambitious book sets out to provide a linguistic analysis of the language used in written mathematics, both textual and symbolic. It is a revised version of the author’s Cambridge Ph.D. thesis, a worthy recipient of FoLLI’s E.W. Beth dissertation award for 2011. Mohan Ganesalingam is a linguist with a Ph.D. in computer science, and his work combines insights from these disciplines with a substantial grasp of mathematics. However, there is much in the book that should interest philosophers of mathematics. Firstly, Ganesalingam’s project leads him to confront some significant issues in the foundations of mathematics, for which he proposes a response that is, in part, novel. Secondly, and perhaps more importantly, he demonstrates something which is often discussed but seldom attempted: he shows how his account of mathematics can be applied to a significant body of actual mathematical practice. The book is very clearly structured. Chapter 1 begins with a defence of Ganesalingam’s methodological presuppositions. Critically, and in distinction from earlier projects of more modest scope, notably the work of Aarne Ranta [1997], he insists on sufficient breadth to encompass all of pure mathematics and on what he calls ‘full adaptivity’, that any mathematical content be extracted from the text under analysis, and not baked into the analytic system (p. 3). The latter constraint prevents him from, for example, building set theory into his linguistic model. Although his account is intended to provide an analysis of the content of ‘rigorous, careful textbooks’ he confines it to what he calls the ‘formal mode’ of the language found therein: the statements exclusively concerning mathematical objects and mathematical properties (p. 7). Characteristically, such textbooks also contain much that is in an informal mode — remarks about the context, or value, or interest, of the mathematical results, say — but, as Ganesalingam notes, analysis of these comments would require a full analysis of natural language (p. 8). Conversely, one of the attractions mathematics in the formal mode holds for the linguist is its comparative simplicity.

Big Social Data Analytics: Opportunities, Challenges and Implications on Society

Big social data analysis is an interdisciplinary domain that uses advanced analytics to identify the key influence in a communication network that shrinks and grows rapidly in a near real-time fashion. It brings together various disciplines such as social media analysis, information retrieval techniques, reasoning, natural language processing (opinion mining), graph mining and analysis, linguistics, machine learning, multimedia management and big data processing. The role of big social data analysis in the growth of a business is larger than what meets the eye, but many enterprises are unaware of how this data influence their expansion. The analysis of information gathered from consumer transactions, communication devices, online activities and streaming devices are used to uncover hidden patterns. The right tools and a foolproof strategy are highly important to utilize information from social data to the fullest. The power of social media along with the emerging big data technology offers abundant opportunities for achieving business growth and if channeled properly, it could be leveraged for the betterment of society. The main goal of this paper is to emphasize the opportunities and challenges provided by dynamic social network data with its implications on the society

Selected Topics on Systems Modeling and Natural Language Processing: Editorial Introduction to the Issue 7 of CSIMQ

The seventh issue of Complex Systems Informatics and Modeling Quarterly presents five papers devoted to two distinct research topics: systems modeling and natural language processing (NLP). Both of these subjects are very important in computer science. Through modeling we can simplify the studied problem by concentrating on only one aspect at a time. Moreover, a properly constructed model allows the modeler to work on higher levels of abstraction and not having to concentrate on details. Since the size and complexity of information systems grows rapidly, creating good models of such systems is crucial. The analysis of natural language is slowly becoming a widely used tool in commerce and day to day life. Opinion mining allows recommender systems to provide accurate recommendations based on user-generated reviews. Speech recognition and NLP are the basis for such widely used personal assistants as Apple’s Siri, Microsoft’s Cortana, and Google Now. While a lot of work has already been done on natural language processing, the research usually concerns widely used languages, such as English. Consequently, natural language processing in languages other than English is very relevant subject and is addressed in this issue.

Big Data for Social Transportation

Big data for social transportation brings us unprecedented opportunities for resolving transportation problems for which traditional approaches are not competent and for building the next-generation intelligent transportation systems. Although social data have been applied for transportation analysis, there are still many challenges. First, social data evolve with time and contain abundant information, posing a crucial need for data collection and cleaning. Meanwhile, each type of data has specific advantages and limitations for social transportation, and one data type alone is not capable of describing the overall state of a transportation system. Systematic data fusing approaches or frameworks for combining social signal data with different features, structures, resolutions, and precision are needed. Second, data processing and mining techniques, such as natural language processing and analysis of streaming data, require further revolutions in effective utilization of real-time traffic information. Third, social data are connected to cyber and physical spaces. To address practical problems in social transportation, a suite of schemes are demanded for realizing big data in social transportation systems, such as crowdsourcing, visual analysis, and task-based services. In this paper, we overview data sources, analytical approaches, and application systems for social transportation, and we also suggest a few future research directions for this new social transportation field.

Cataphora, backgrounding and accessibility in discourse

We examine discourse factors that are involved in the occurrence of intra/inter-sentential cataphora. On the basis of a corpus analysis of natural language, we test two cognitive theories that attempt to explain the phenomenon of cataphora: clausal backgrounding (Harris and Bates, 2002) and Accessibility Theory (Ariel, 1990). In the first part of the paper, we investigate the presence of cataphoric he, she, it and they in a corpus annotated with nucleus-satellite labels (Mann and Thompson, 1988), which are interpreted to be discourse correlates of the foreground-background distinction. The analysis shows that cataphora cannot be restricted to backgrounded parts of texts, and that backgrounding as an explanation for the occurrence of cataphora cannot be applied at the discourse level. In the second part of the paper, we investigate a cognitively related phenomenon to backgrounding: accessibility and its influence on cataphora. We demonstrate that in different conditions accessibility parameters such as Givenness, Distance and Unity do not show a clear influence (especially when an instance of cataphora and its antecedent are in different sentences), while Saliency and (non)Competition do play a role in the presence of cataphora (both intra- and inter-sententially).

Annotating patient clinical records with syntactic chunks and named entities: the Harvey Corpus.

The free text notes typed by physicians during patient consultations contain valuable information for the study of disease and treatment. These notes are difficult to process by existing natural language analysis tools since they are highly telegraphic (omitting many words), and contain many spelling mistakes, inconsistencies in punctuation, and non-standard word order. To support information extraction and classification tasks over such text, we describe a de-identified corpus of free text notes, a shallow syntactic and named entity annotation scheme for this kind of text, and an approach to training domain specialists with no linguistic background to annotate the text. Finally, we present a statistical chunking system for such clinical text with a stable learning rate and good accuracy, indicating that the manual annotation is consistent and that the annotation scheme is tractable for machine learning.

A general protein-protein interaction extraction architecture based on word representation and feature selection

Previous researches have shown that supervised Protein-Protein Interaction Extraction PPIE can get high accuracies with elaborately selected features and kernels. However, most features and kernels rest upon domain knowledge and natural language analysis, which makes the supervised model expensive, heavy and brittle. Moreover, commonly used representation techniques, such as one-hot encoding and Vector Space Model, fail to capture the semantic similarity between words. To reduce the manual labour and take advantage of semantic representation, we put forward a general instance representation architecture for PPIE, which integrates word representation, vector composition and feature selection. Our method obtains F-scores of 69.7, 78.8, 72.3, 72.0 and 83.7 on AIMed, BioInfer, HPRD50, IEPA and LLL respectively.

An Empirical Investigation of Self-Selection Bias and Factors Influencing Review Helpfulness

This paper build on 1 489194 product reviews from 30 product categories retrieved from Amazon.com. Product categories are classified by use of natural language analysis tools with computing of subjectivity scores reflecting a search/experience product dimension. Results show a distinct effect of self-selection where the average review score gradually decreases. For most products, no undershooting period was observed, even though a limited number of products groups had this development pattern. Review length, verified purchase and use of real names contributed to increasing helpfulness ratings. The results further suggest search products to be more influenced by review length than experience products.

Semantic Similarity from Natural Language and Ontology Analysis

Artificial Intelligence federates numerous scientific fields in the aim of developing machines able to assist human operators performing complex treatments -- most of which demand high cognitive skills (e.g. learning or decision processes). Central to this quest is to give machines the ability to estimate the likeness or similarity between things in the way human beings estimate the similarity between stimuli. In this context, this book focuses on semantic measures: approaches designed for comparing semantic entities such as units of language, e.g. words, sentences, or concepts and instances defined into knowledge bases. The aim of these measures is to assess the similarity or relatedness of such semantic entities by taking into account their semantics, i.e. their meaning -- intuitively, the words tea and coffee, which both refer to stimulating beverage, will be estimated to be more semantically similar than the words toffee (confection) and coffee, despite that the last pair has a higher syntactic similarity. The two state-of-the-art approaches for estimating and quantifying semantic similarities/relatedness of semantic entities are presented in detail: the first one relies on corpora analysis and is based on Natural Language Processing techniques and semantic models while the second is based on more or less formal, computer-readable and workable forms of knowledge such as semantic networks, thesaurus or ontologies. (...) Beyond a simple inventory and categorization of existing measures, the aim of this monograph is to convey novices as well as researchers of these domains towards a better understanding of semantic similarity estimation and more generally semantic measures.

English

In this paper, we focus on the application of Natural Language Processing (NLP) in an e-assessment system for Arabic language. The development of some linguistic tools as lexicon, morphological analyzer and parser is crucial. Lexicon represents the most important resources for the system Morphological analyzer represents a decomposition, an analysis and research tool for Arab texts. But other evaluation activities require a parsing system. Parsing is a fundamental step in the process of automatic analysis of natural languages. In this paper we describe, firstly the building of a lexicon of Arabic language using the Head Driven phrase Structure Grammar (HPSG) formalism. The lexicon is represented in XML as a list of item elements, and it lists several lexical properties which are specifically targeted at morphological analysis. It also specifies morphological, syntactic and semantic features (such as gender or number), which can be used by parser and assessment system. Also we explain the ascendant approach design of parser and we give an idea on the experimentation of the realized system and its integration in e-learning environment.

기업의 SNS 노출과 주식 수익률간의 관계 분석

Can the stock market really be predicted? Stock market prediction has attracted much attention from many fields including business, economics, statistics, and mathematics. Early research on stock market pre-diction was based on random walk theory (RWT) and the efficient market hypothesis (EMH). According to the EMH, stock market are largely driven by new information rather than present and past prices. Since it is unpredictable, stock market will follow a random walk. Even though these theories, Schumaker [2010] asserted that people keep trying to predict the stock market by using artificial intelligence, statistical estimates, and mathematical models. Mathematical approaches include Percolation Methods, Log-Periodic Oscillations and Wavelet Transforms to model future prices. Examples of artificial intelligence approaches that deals with optimization and machine learning are Genetic Algorithms, Support Vector Machines (SVM) and Neural Networks. Statistical approaches typically predicts the future by using past stock market data.Recently, financial engineers have started to predict the stock prices movement pattern by using the SNS data. SNS is the place where peoples opinions and ideas are freely flow and affect others’ beliefs on certain things. Through word-of-mouth in SNS, people share product usage experiences, subjective feelings, and commonly accompanying sentiment or mood with others. An increasing number of empirical analyses of sentiment and mood are based on textual collections of public user generated data on the web. The Opinion mining is one domain of the data mining fields extracting public opinions exposed in SNS by utilizing data mining. There have been many studies on the issues of opinion mining from Web sources such as product reviews, forum posts and blogs. In relation to this literatures, we are trying to understand the effects of SNS exposures of firms on stock prices in Korea. Similarly to Bollen et al. [2011], we empirically analyze the impact of SNS exposures on stock return rates. We use Social Metrics by Daum Soft, an SNS big data analysis company in Korea. Social Metrics provides trends and public opinions in Twitter and blogs by using natural language process and analysis tools. It collects the sentences circulated in the Twitter in real time, and breaks down these sentences into the word units and then extracts keywords. In this study, we classify firms’ exposures in SNS into two groups: positive and negative. To test the correlation and causation relationship between SNS exposures and stock price returns, we first collect 252 firms’stock prices and KRX100 index in the Korea Stock Exchange (KRX) from May 25, 2012 to September 1, 2012. We also gather the public attitudes (positive, negative) about these firms from Social Metrics over the same period of time. We conduct regression analysis between stock prices and the number of SNS exposures. Having checked the correlation between the two variables, we perform Granger causality test to see the causation direction between the two variables. The research result is that the number of total SNS exposures is positively related with stock market returns. The number of positive mentions of has also positive relationship with stock market returns. Contrarily, the number of negative mentions has negative relationship with stock market returns, but this relationship is statisti-cally not significant. This means that the impact of positive mentions is statistically bigger than the impact of negative mentions. We also investigate whether the impacts are moderated by industry type and firm’s size. We find that the SNS exposures impacts are bigger for IT firms than for non-IT firms, and bigger for small sized firms than for large sized firms. The results of Granger causality test shows change of stock price return is caused by SNS exposures, while the causation of the other way round is not significant. Therefore the correlation relationship between SNS exposures and stock prices has uni-direction causality. The more a firm is exposed in SNS, the more is the stock price likely to increase, while stock price changes may not cause more SNS mentions

Text mining

Text mining is an umbrella term covering a wide range of software tools, including natural language analysis, use of statistical techniques, and machine learning, designed to extract entities (names of people and places), index terms, and relationships. This article outlines these tools, and describes how text mining is being applied in enterprises to solve user problems. A standard measure of accuracy enables text-mining tools to be compared. Text mining is often applied to unstructured content, but the most impressive results come from applying text-mining tools on structured text within a specific subject domain, using an iterative process to train the software.

AKOVIA: Automated Knowledge Visualization and Assessment

This emerging technology report reviews automated knowledge visualization and assessment (AKOVIA) which is a web-based tool for the analysis of natural language and graphical knowledge representations. The open architecture of AKOVIA enables a large variety of research and practical applications. It integrates a unique language-oriented methodology based on heuristics and generates seven quantitative similarity measures on the fly. AKOVIA has been successfully tested for reliability and validity. Given the limited availability of reliable and valid automated assessment methodologies, AKOVIA has the potential to be integrated into web-based applications and thus opening up numerous research as well as practical applications.

A toolkit for automating compliance in cloud computing services

We present an integrated approach for automating service providers’ compliance with data protection laws and regulations, business and technical requirements in cloud computing. The techniques we propose in particular include: natural language analysis (of legislative and regulatory texts, and corporate security rulebooks) and extraction of enforceable rules, use of sticky policies, automated policy enforcement and active monitoring of data, particularly in cloud environments. We currently work on developing a software tool for semantic annotation and natural language processing of cloud ToS and other related policy texts. We describe our implementations of two parts of the proposed toolkit, namely the semantic annotation editor and the EnCoRe policy enforcement framework. We also identify opportunities for future software development in the area of cloud computing compliance.

Modelling and Analysis of Natural Language Controlled Robotic Systems

Abstract Controlling a robotic system through natural language commands can provide great convenience for human users. Many researchers have investigated on high-level planning for natural language controlled robotic systems. Most of the methods designed the planning as open-loop processes and therefore cannot well handle unexpected events for realistic applications. In this paper, a closed-loop method is proposed for task-planning to overcome unexpected events occurred during implementation of assigned tasks. The designed system is modeled and theoretically proved to be able to stabilize the robotic system under unexpected events. Experimental results demonstrate effectiveness and advantages of the proposed method.

On Semantic Algebra: A Denotational Mathematics for Natural Language Comprehension and Cognitive Computing

Semantics is composed meaning of language expressions and perceptions at the levels of words, phrase, sentence, paragraph, and essay. The basic unit of formal semantics is a concept as a formal model of words in a natural language. Cognitive linguistics focuses on cognitive semantics and its interaction with underlying syntactic structures. A denotational mathematics known as semantic algebra is presented for rigorous semantics manipulations in cognitive linguistics. Semantic algebra deals with formal semantics of linguistics by a general mathematical model of semantics and a set of algebraic operators. On the basis of semantic algebra, language semantics may not only be deductively analyzed based on syntactic structures from the top down, but also be synthetically composed by the algebraic semantic operators from the bottom up at different levels of language units. Semantic algebra enables a wide range of applications in cognitive informatics, cognitive linguistics, computational linguistics, semantic computing, cognitive computing, machine learning, computing with words, as well as natural language analysis, synthesis, and comprehension.

The situation of dialectologists within the new integrated linguistics: the case of Atlantic Spanish

Abstract Linguistics and Dialectology are two sides of the same coin: the former deals with the rigorous analysis of natural languages and the latter with concrete varieties of language in its cohesive and identifying social roles. Linguistics today is moving towards an integration of its various dimensions: phonology and phonetics are now so intricately tied that the unimodular phonetological approach is gaining ground rapidly; synchrony and diachrony are moving towards a reintegration, thus moving away from their parallel paths; and, finally, the so-called ‘non-structural’ elements of language are gradually being acknowledged as an integral part of the analysis that was traditionally reserved for the ‘structural’ ones. As linguistics moves, so does dialectology, since the latter has always been the laboratory of linguists, even if they have not formally accepted it as such. A new approach to dialectal matters must therefore move away from mere description and search for a more comprehensive analysis that confirms the essential inviolability of the binomial language-society. The traditional view of Hispanic linguistics and dialectology has been a victim of the dichotomic approach: conservative versus radical, Iberian versus American, high lands versus low lands, North-Central Castilian versus ‘Atlantic’ Spanish among others. This paper aims at taking an integrated approach to linguistics and dialectology, with its case study addressing the so called ‘Atlantic’ Spanish and the phonetological changes it is going through in search of a more satisfying explanation of short-term and long-term variability.

Implementation of Nlization Framework for Verbs, Pronouns and Determiners with Eugene

UNL system is designed and implemented by a nonprofit organization, UNDL Foundation at Geneva in 1999. UNL applications are application softwaresthat allow end users to accomplish natural language tasks, such as translating, summarizing, retrieving or extracting information, etc. Two major web based application softwares are Interactive ANalyzer (IAN), which is a natural language analysis system. It represents natural language sentences as semantic networks in the UNL format. Other application software is dEep-to-sUrface GENErator (EUGENE), which is an open -source interactive NLizer. It generates natural language sentences out of semantic networksrepresented in the UNL format. In this paper, NLization framework with EUGENE is focused, while using UNL system for accomplishing the task of machine translation. In whole NLization process, EUGENE takes a UNL input and delivers an output in natural language without any human intervention. It is language -independent and has to be parametrized to the natural language input through a dictionary and a grammar, provided as separate interpretable files. In this paper, it is explained that how UNL input is synta ctically and semantically analyzed with the UNL NL T-Grammar for NLization of UNL sentences involving verbs, pronouns and determiners for Punjabi natural language.

Extended pregroup grammars applied to natural languages

Pregroups and pregroup grammars were introduced by Lambek in 1999 [14] as an algebraic tool for the syntactic analysis of natural lan-guages. The main focus in that paper was on certain extended pregroup grammars such as pregroups with modalities, product pregroup grammars and tupled pregroup grammars. Their applications to different syntactic structures of natural languages, mainly Polish, are explored/shown here.

A Quantified Temporal Logic for Ampliation and Restriction

Abstract Temporal logic as a modern discipline is separate from classical logic; it is seen as an addition or expansion of the more basic propositional and predicate logics. This approach is in contrast with logic in the Middle Ages, which was primarily intended as a tool for the analysis of natural language. Because all natural language sentences have tensed verbs, medieval logic is inherently a temporal logic. This fact is most clearly exemplified in medieval theories of supposition. As a case study, we look at the supposition theory of Lambert of Lagny (Auxerre), extracting from it a temporal logic and providing a formalization of that logic.