Logic and Natural Language

This chapter demonstrates the application of a qualitative formal method, logical formalization, to organization and management theory. Organizational arguments are usually phrased out in some natural language in the first place. After separating the premises (facts, definitions) of a natural language argument from its conclusions (predictions), this preprocessed text is translated into a logical language. Then, experimentation can begin if the logical formulae standing for the verbal premises imply the putative conclusions as formal theorems. If not, what kind of modifications can make these outcomes follow? What other theorems are implied from the same argument core? A substantial advantage of using symbolic logic over many branches of applied mathematics is that logical models can quite closely map the intended meaning of assertive sentences, while the deduction of conclusions can proceed with the rigor of mathematical proofs. The examples highlight how different logical languages, different dialects, can be used to the idiosyncrasies of the subject. The proof and the translation process from natural language statements to logical models are supported by user-friendly theorem-prover softwares. The appliers of the method need not be logic experts; what they need are analytical skills, sharp eyes at formula evaluation, and some stamina. The promise of using symbolic logic is combining the flexibility of qualitative reasoning with exactness in drawing conclusions from complex arguments. The chapter is to show how and in which extent logical formalization can fulfill this promise.

This paper describes two approaches to the automatic generation of behavioral VHDL models from descriptions written in natural language. Both approaches are based on a modeling style in which behavior is represented by a system of interconnected processes. The first approach employs a semantic grammar to directly generate a single VHDL process from a paragraph written in a restricted English called ModelSpeak. The second approach accepts more general English and generates models consisting of multiple processes. series of sentences describing the behavior of a single process and generated correct VHDL code for it. This interface requires the behavior be expressed in a highly restricted English called ModelSpeak (10). Conditional expressions (if statements) may be nested to two levels, and interaction is invoked by the interface to resolve scope ambiguity of loops. This interface is implemented with a semantic grammar (3) in Prolog. The second interface (Approach II) to the Modeler's Assistant for natural language is substantially more complex, but accepts more general English expressions and generates multiple-process models. In this approach, each sentence is parsed by a bottom-up, parallel chart parser to generate a set of valid parse trees. The trees are examined by a Semantic Analyzer (7) to determine one which is semantically correct, and a conceptual graph (14) (semantic network) of its meaning is generated. Once the conceptual graph of individual sentences are joined together (12), a program called the Linker (8) analyzes the graph to produce a Process Model Graph and VHDL process code for the Modeler's Assistant. Nodes in the conceptual graph representing verbs typically generate processes or the conditions which govern them. Nodes representing objects generate signals. The modeling style underlying the Linker produces a sizable collection of processes, each consisting of a single if_then statement. To avoid unnecessary bus resolutions, multiple processes assigning to the same signal are merged. Since signal types are generally not expressed in the English description, they may be added interactively later. Before describing the approaches in more detail, related research on natural language interfaces is reviewed briefly.

: Natural language (supplemented with diagrams and some mathematical notations) is convenient for succinct communication of technical descriptions between the various stakeholders (e.g., customers, designers, implementers) involved in the design of software systems. However, natural language descriptions can be informal, incomplete, imprecise and ambiguous, and cannot be processed easily by design and analysis tools. Formal languages, on the other hand, formulate design requirements in a precise and unambiguous mathematical notation, but are more difficult to master and use. We propose a methodology for connecting semi-formal requirements with formal descriptions through an intermediate representation. We have implemented this methodology in a research prototype called Automatic Requirements Specification Extraction from Natural Language (ARSENAL). The main novelty of ARSENAL lies in its ability to generate a fully-specified complete formal model automatically from natural language requirements. ARSENAL extracts relations from text using semantic parsing and progressively refines them over multiple stages to create a final composite model. Currently, ARSENAL generates formal models in linear-time temporal logic (LTL), but the approach can be adapted for other models, e.g., probabilistic relational models like Markov Logic Networks (MLN). The formal models of the requirements can be used to check important design and system properties, e.g., consistency, satisfiability, realizability. ARSENAL has a modular and flexible architecture that facilitates porting it from one domain to another. We evaluated ARSENAL on complex requirements from two real-world case studies: the Time-Triggered Ethernet (TTEthernet) communication platform used in space, and FAA-Isolette infant incubators used in NICU. We systematically evaluated various aspects of ARSENAL -- the accuracy of the natural language processing stage, the degree of automation, and robustness to noise.

Lawry's label semantics for modeling and computing with linguistic information in natural language provides a clear interpretation of linguistic expressions and thus a transparent model for real-world applications. Meanwhile, annotated logic programs (ALPs) and its fuzzy extension AFLPs have been developed as an extension of classical logic programs offering a powerful computational framework for handling uncertain and imprecise data within logic programs. This paper proposes annotated linguistic logic programs (ALLPs) that embed Lawry's label semantics into the ALP/AFLP syntax, providing a linguistic logic programming formalism for development of automated reasoning systems involving soft data as vague and imprecise concepts occurring frequently in natural language. The syntax of ALLPs is introduced, and their declarative semantics is studied. The ALLP SLD-style proof procedure is then defined and proved to be sound and complete with respect to the declarative semantics of ALLPs. © 2010 Wiley Periodicals, Inc.

Introduction. Donald Walker: a Remembrance. Section 1: The Task of Natural Language Processing. Natural Language Processing: an Historical Review K. Sparck Jones. On Getting a Computer to Listen J. Robinson. Utterance and Objective: Issues in Natural Language Communication B. Grosz. On the Proper Place of Semantics in Machine Translation M. King. Developing a Natural Language Interface to Complex Data G.G. Hendrix, E.D. Sacerdoti. User-Needs Analysis and Design Methodology for an Automated Document Generator K. Kukich, K. McKeown, J. Shaw, J. Robin, J. Lim, N. Morgan, J. Philips. Section 2: Building Computational Lexicons. Machine-Readable Dictionaries and Computational Linguistics Research B. Boguraev. Research Toward the Development of a Lexical Knowledge Base for Natural Language Processing R.A. Amsler. Discovering Relationships Among Word Senses R.J. Byrd. Machine Readable Dictionary as a Source of Grammatical Information E. Hajicova, A. Rosen. The ITT Lexical Database: Dream and Reality S. Pin-Ngern Conlon. Visions of the Digital Library: Views on Using Computational Linguistics and Semantic Nets in Information Retrieval J.L. Klavans. Anatomy of a Verb Entry: from Linguistic Theory to Lexicographic Practice B.T. Atkins, J. Kegl, B. Levin. Issues for Lexicon Building N. Calzolari. Outline of a Model for Lexical Databases N. Ide, J. le Maitre, J. Veronts. Construction-Based MT Lexicons L. Levin, S. Nirenburg. Dependency-Based Grammatical Information in the Lexicon P. Sgall. Semantics in the Brain's Lexicon -- Some Preliminary Remarks on its Epistemology H. Schnelle. Section 3: The Acquisition and Use of LargeCorpora. The Ecology of Language D.E. Walker. Representativeness in Corpus Design D. Biber. The Text Encoding Initiative C.M. Sperberg-McQueen. Discrimination Decisions for 100,000 Dimensional W.A. Gale, K.W. Church, D. Yarowsky. Acquisition and Exploitation of Textual Resources for NLP S. Armstrong-Warwick. The Center for Electronic Texts in the Humanities S. Hockey. Design Principles for Electronic Textual Resources: Investigating Users and Uses of Scholarly Information N.J. Belkin. Section 4: Topics, Methods and Formalisms in Syntax, Semantics and Pragmatics. Evaluating English Sentences in a Logical Model J. Friedman, D.B. Moran, D.S. Warren. Recovering Implicit Information M.S. Palmer, D.A. Dahl, R.J. Schiffman, L. Hirschman, M. Linebarger, J. Downing. Flexible Generation: Taking the User into Account C.L. Paris, V.O. Mittal. Two Principles of Parse Preference J.R. Hobbs, J. Bear. UD, yet Another Unification Device R. Johnson, M. Rosner. Varieties of Heuristics in Sentence Parsing M. Nagao. Some Recent Trends in Natural Language Processing A.K. Joshi. Stone Soup and the French Room Y. Wilks.

Chapter 44 - Natural Language Interface Systems

Despite the superior performance of large language models to generate natural language texts, it is hard to generate texts with correct logic according to a given task, due to the difficulties for neural models to capture strict logic from free-form texts. In this paper, we propose a novel graph-based language model, Logical-GLM, to extract strict logic from free-form texts and then infuse into language models. Specifically, we first capture information from natural language instructions and construct logical probability graphs that generally describe domains. Next, we generate logical skeletons to guide language model training, infusing domain knowledge into language models. At last, we alternately optimize the searching policy of graphs and language models until convergence. The experimental results show that Logical-GLM is both effective and efficient compared with traditional language models, despite using smaller-scale training data and fewer parameters. Our approach can generate instructional texts with more correct logic owing to the internalized domain knowledge. Moreover, the search of logical graphs reflects the inner mechanism of the language models, which improves the interpretability of black-box models.

Inductive Logic Programming: Issues, results and the challenge of Learning Language in Logic

As with Amazon’s Echo and its conversational agent Alexa, smart voice-controlled devices become ever more present in daily life, and many different applications can be integrated into this platform. In this paper, we present a framework that eases the development of skills in Prolog. As Prolog has a long history in natural language processing, we may integrate well-established techniques, such as reasoning about knowledge with Attempto Controlled English, instead of depending on example phrases and pre-defined slots.

For any applications related to Natural Language Processing (NLP), reasoning has been recognized as a necessary underlying aspect. Many of the existing work in NLP deals with specific NLP problems in a highly heuristic manner, yet not from an explicit reasoning perspective. Recently, there have been developments on models that allow reasoning in NLP such as language models, logical models, and so on. The goal of this special issue is to present high-quality contributions that integrate reasoning involved in different areas of natural language processing both at theoretical and/or practical levels. In this article, we give a brief overview on some major aspects of explicating reasoning in NLP and summarize the articles included in this special issue.

Law is written in a way that is not easily understandable by most people. This also hinders the translation into computer code, which would permit the creation of tools that increase access to the law. The use of controlled language in legal texts is a promising way to implement laws that are better comprehensible by people, and computer-executable at the same time. However, while the scholarship on controlled language has been concentrating on its translation into (logic) programs, the effects on people have not been investigated. We conducted an experiment to test the understandability, usability, and perceived open-texture (e.g., ambiguity, vagueness) of legal texts that are formulated in natural language and in controlled language. Among our 73 participants—including members of parliament (MPs) and public servants—we found that the use of controlled language increases understandability across legal domains but does not reduce the number of terms that are perceived as open-texture. We also found that public servants show higher comprehension of legal statutes but lower perception of open-texture than MPs, regardless of whether these are in controlled or natural language. We conclude that controlled language can therefore support a wider access to law, thereby bringing democratic societies closer to their underpinning ideals and principles.

This paper discusses a novel hybrid approach to text classification that integrates a machine learning algorithm along with DistilBERT, a pre-trained deep learning framework for natural language processing, offers a base model fine-tuned on Indian Banking News-Events with a rule-based method that is used by filtering false positives and dealing with false negatives to enhance the results given by the previous classifier. The major benefit is that by incorporating unique rules for certain chaotic or overlapping categories that have not been effectively trained, the system can be quickly fine-tuned. This research also compares the effectiveness of state-of-art deep contextual language representation DistilBERT used in our proposed hybrid model with the most preferred context independent language representation TFIDF, on supervised learning of the classification of multiclass Banking News-Events. Both representations are fed into the machine learning classifiers, Logistic Regression, Linear SVC, Decision Tree, and Random Forest. The findings indicate that DistilBERT can better transfer generic domain knowledge to other domains as compared to the baseline TFIDF and results into higher accuracy with Random Forest. The result is further fed into the Rules based method as per our proposed model. And, our proposed hybrid model resulted into improved accuracy.

CUCS-231-86 Programs interacting with users via natural language interfaces generally require more sophisticated control structures than those needed by programs interacting with users through less flexible mechanisms. This paper describes our development of Director, an interpreter (inference engine) for rule-based programs. Providing an efficient combination of forward and backward chaining, heuristic and user control of inference, and ready access to portions of its internal sttucrure, Director facilitates the construction of systems with natural language interfaces as well as other rule-based systems in which queries are expensive. This research was partially supported by Office of Naval Research grant NOOO 14-82-K-0256. Director An Interpreter for Rule-based Programs

We present a novel approach to the creation of smart contracts that takes an existing legal document and allows it to be incrementally elaborated into a tested smart contract by domain experts. Smart contracts are currently built with compiled imperative languages, and suffer from lack of agility, elevated risks from errors and security flaws, and high development costs. This paper describes a smart editor that uses a declarative language (Answer Set Programming (ASP)) to represent the business logic of legal documents. The document is incrementally elaborated in a fixed sequence of steps beginning with an ontology discovery step that identifies the explicit and implicit artefacts and applicable constraints. This information is used to generate ASP representations which provide the foundation required for modelling the legal logic. Furthermore, we have achieved the verbalisation of rules built during modelling, and have developed a method of representing artefacts visually which allows logic modelling, model validation and program verification to be visual. During these steps, the original legal document is enhanced with additional embedded information, which results in a tested executable ASP program which can then be used as a smart contract if modifications are made to the blockchain smart contract infrastructure.KeywordsAnswer Set ProgrammingLegal LogicModel ValidationOntologySmart ContractVerbalisationVisualisation

Does Frege have a metatheory for his logic? There is an obvious and uncontroversial sense in which he does. Frege introduces and discusses his new logic in natural language; he argues, in response to criticisms of Begriffsschrift, that his logic is superior to Boole's by discussing formal features of both systems. In so far as the enterprise of using natural language to introduce, discuss, and argue about features of a formal system is metatheoretic, there can be no doubt: Frege has a metatheory. There is also an obvious and uncontroversial sense in which Frege does not have a metatheory for his logic. The model theoretic semantics with which we are familiar today are a post-Fregean development. The question I address in this paper is, does Frege have a metatheory in the following sense: do his justifications of his basic laws and rules of inference employ, or even require, ineliminable use of a truth predicate and metalinguistic variables? My answer is ‘no’ on both counts. I argue that Frege neither uses, nor has any need to use, a truth predicate or metalinguistic variables in his justifications of his basic laws and rules of inference. Quine's famous explanation of the need for semantic ascent simply does not apply to Frege's logic. The purpose of the discussions that are typically understood as constituting Frege's metatheory is, rather, elucidatory. And once we see what the aim of these particular elucidations is, we can explain Frege's otherwise puzzling eschewal of the truth predicate in his discussions of the justification of the laws and rules of inference.