Unrestricted Natural Language Research Articles

DeepOCL: A deep neural network for Object Constraint Language generation from unrestricted nature language

AbstractObject Constraint Language (OCL) is one kind of lightweight formal specification, which is widely used for software verification and validation in NASA and Object Management Group projects. Although OCL provides a simple expressive syntax, it is hard for the developers to write correctly due to lacking knowledge of the mathematical foundations of the first‐order logic, which is approximately half accurate at the first stage of development. A deep neural network named DeepOCL is proposed, which takes the unrestricted natural language as inputs and automatically outputs the best‐scored OCL candidates without requiring a domain conceptual model that is compulsively required in existing rule‐based generation approaches. To demonstrate the validity of our proposed approach, ablation experiments were conducted on a new sentence‐aligned dataset named OCLPairs. The experiments show that the proposed DeepOCL can achieve state of the art for OCL statement generation, scored 74.30 on BLEU, and greatly outperformed experienced developers by 35.19%. The proposed approach is the first deep learning approach to generate the OCL expression from the natural language. It can be further developed as a CASE tool for the software industry.

Natural Language Processing in Translation of Relational Languages

Methods of data manipulation in combination with sturcture of the data and integrity constraints define data model used in the relational databases. This article focuses on the methods and processes of operation sets which are used for selection of data from relational database and translation between various formats of this manipulation. The article presents the design, implementation and experimental evaluation of tool for translating between relational algebra, tuple relational calculus, Structured Query Language and unrestricted natural language in all directions. Presented software tool translates from natural language with the use of artificial intelligence methods for natural language processing, syntactic analysis and parsing. Generative pretrained transformer of third generation (GPT3) based Codex – Davinci translation model was used as an artificial intelligence method used in the workflow of translation from English language to relational languages.

Automatic creation of acceptance tests by extracting conditionals from requirements: NLP approach and case study

Acceptance testing is crucial to determine whether a system fulfills end-user requirements. However, the creation of acceptance tests is a laborious task entailing two major challenges: (1) practitioners need to determine the right set of test cases that fully covers a requirement, and (2) they need to create test cases manually due to insufficient tool support. Existing approaches for automatically deriving test cases require semi-formal or even formal notations of requirements, though unrestricted natural language is prevalent in practice. In this paper, we present our tool-supported approach CiRA (Conditionals in Requirements Artifacts) capable of creating the minimal set of required test cases from conditional statements in informal requirements. We demonstrate the feasibility of CiRA in a case study with three industry partners. In our study, out of 578 manually created test cases, 71.8 % can be generated automatically. Additionally, CiRA discovered 80 relevant test cases that were missed in manual test case design. CiRA is publicly available at www.cira.bth.se/demo/.

Knowledge Authoring with Factual English

Knowledge representation and reasoning (KRR) systems represent knowledge as collections of facts and rules. Like databases, KRR systems contain information about domains of human activities like industrial enterprises, science, and business. KRRs can represent complex concepts and relations, and they can query and manipulate information in sophisticated ways. Unfortunately, the KRR technology has been hindered by the fact that specifying the requisite knowledge requires skills that most domain experts do not have, and professional knowledge engineers are hard to find. One solution could be to extract knowledge from English text, and a number of works have attempted to do so (OpenSesame, Google's Sling, etc.). Unfortunately, at present, extraction of logical facts from unrestricted natural language is still too inaccurate to be used for reasoning, while restricting the grammar of the language (so-called controlled natural language, or CNL) is hard for the users to learn and use. Nevertheless, some recent CNL-based approaches, such as the Knowledge Authoring Logic Machine (KALM), have shown to have very high accuracy compared to others, and a natural question is to what extent the CNL restrictions can be lifted. In this paper, we address this issue by transplanting the KALM framework to a neural natural language parser, mStanza. Here we limit our attention to authoring facts and queries and therefore our focus is what we call factual English statements. Authoring other types of knowledge, such as rules, will be considered in our followup work. As it turns out, neural network based parsers have problems of their own and the mistakes they make range from part-of-speech tagging to lemmatization to dependency errors. We present a number of techniques for combating these problems and test the new system, KALMFL (i.e., KALM for factual language), on a number of benchmarks, which show KALMFL achieves correctness in excess of 95%.

Interactive Natural Language Grounding via Referring Expression Comprehension and Scene Graph Parsing.

Natural language provides an intuitive and effective interaction interface between human beings and robots. Currently, multiple approaches are presented to address natural language visual grounding for human-robot interaction. However, most of the existing approaches handle the ambiguity of natural language queries and achieve target objects grounding via dialogue systems, which make the interactions cumbersome and time-consuming. In contrast, we address interactive natural language grounding without auxiliary information. Specifically, we first propose a referring expression comprehension network to ground natural referring expressions. The referring expression comprehension network excavates the visual semantics via a visual semantic-aware network, and exploits the rich linguistic contexts in expressions by a language attention network. Furthermore, we combine the referring expression comprehension network with scene graph parsing to achieve unrestricted and complicated natural language grounding. Finally, we validate the performance of the referring expression comprehension network on three public datasets, and we also evaluate the effectiveness of the interactive natural language grounding architecture by conducting extensive natural language query groundings in different household scenarios.

Natural Language Processing in OTF Computing: Challenges and the Need for Interactive Approaches

The vision of On-the-Fly (OTF) Computing is to compose and provide software services ad hoc, based on requirement descriptions in natural language. Since non-technical users write their software requirements themselves and in unrestricted natural language, deficits occur such as inaccuracy and incompleteness. These deficits are usually met by natural language processing methods, which have to face special challenges in OTF Computing because maximum automation is the goal. In this paper, we present current automatic approaches for solving inaccuracies and incompletenesses in natural language requirement descriptions and elaborate open challenges. In particular, we will discuss the necessity of domain-specific resources and show why, despite far-reaching automation, an intelligent and guided integration of end users into the compensation process is required. In this context, we present our idea of a chat bot that integrates users into the compensation process depending on the given circumstances.

Automatic Extraction of Access Control Policies from Natural Language Documents

A fundamental management responsibility is securing information systems. Almost all applications that deal with safety, privacy, or defense include some form of access control. There are a plethora of access control models in the information security realm such as role-based access control and attribute-based access control. However, the initial development of access control policies (ACPs) can be very challenging. Most organizations have high-level requirement specifications that include a set of ACPs, which describe allowable operations of the system. It is time consuming and error-prone to manually sift through these documents and extract ACPs. In this paper, we propose a new framework towards extracting ACPs from unrestricted natural language documents using semantic role labeling (SRL). We were able to correctly identify ACP elements with an average $F_1$ F 1 score of 75 percent, which bested the previous work by 15 percent. Furthermore, as SRL tools are often trained on publicly available corpora such as Wall Street Journal, we investigated the idea of improving SRL performance using domain-related knowledge. We utilized domain adaptation and semi-supervised learning techniques and were able to improve the SRL performance by 2 percent using only a small amount of access control data.

Automated Checking of Conformance to Requirements Templates Using Natural Language Processing

Templates are effective tools for increasing the precision of natural language requirements and for avoiding ambiguities that may arise from the use of unrestricted natural language. When templates are applied, it is important to verify that the requirements are indeed written according to the templates. If done manually, checking conformance to templates is laborious, presenting a particular challenge when the task has to be repeated multiple times in response to changes in the requirements. In this article, using techniques from natural language processing (NLP), we develop an automated approach for checking conformance to templates. Specifically, we present a generalizable method for casting templates into NLP pattern matchers and reflect on our practical experience implementing automated checkers for two well-known templates in the requirements engineering community. We report on the application of our approach to four case studies. Our results indicate that: (1) our approach provides a robust and accurate basis for checking conformance to templates; and (2) the effectiveness of our approach is not compromised even when the requirements glossary terms are unknown. This makes our work particularly relevant to practice, as many industrial requirements documents have incomplete glossaries.

BEETLE II: Deep Natural Language Understanding and Automatic Feedback Generation for Intelligent Tutoring in Basic Electricity and Electronics

Within STEM domains, physics is considered to be one of the most difficult topics to master, in part because many of the underlying principles are counter-intuitive. Effective teaching methods rely on engaging the student in active experimentation and encouraging deep reasoning, often through the use of self-explanation. Supporting such instructional approaches poses a challenge for developers of Intelligent Tutoring Systems. We describe a system that addresses this challenge by teaching conceptual knowledge about basic electronics and electricity through guided experimentation with a circuit simulator and reflective dialogue to encourage effective self-explanation. The Basic Electricity and Electronics Tutorial Learning Environment (BEETLE II) advances the state of the art in dynamic adaptive feedback generation and natural language processing (NLP) by extending symbolic NLP techniques to support unrestricted student natural language input in the context of a dynamically changing simulation environment in a moderately complex domain. This allows contextually-appropriate feedback to be generated “on the fly” without requiring curriculum designers to anticipate possible student answers and manually author multiple feedback messages. We present the results of a system evaluation. Our curriculum is highly effective, achieving effect sizes of 1.72 when comparing pre- to post-test learning gains from our system to those of a no-training control group. However, we are unable to demonstrate that dynamically generated feedback is superior to a non-NLP feedback condition. Evaluation of interpretation quality demonstrates its link with instructional effectiveness, and provides directions for future research and development.

SALL-E: Situated Agent for Language Learning

We describe ongoing research towards building a cognitively plausible system for near one-shot learning of the meanings of attribute words and object names, by grounding them in a sensory model. The system learns incrementally from human demonstrations recorded with the Microsoft Kinect, in which the demonstrator can use unrestricted natural language descriptions. We achieve near-one shot learning of simple objects and attributes by focusing solely on examples where the learning agent is confident, ignoring the rest of the data. We evaluate the system's learning ability by having it generate descriptions of presented objects, including objects it has never seen before, and comparing the system response against collected human descriptions of the same objects. We propose that our method of retrieving object examples with a k-nearest neighbor classifier using Mahalanobis distance corresponds to a cognitively plausible representation of objects. Our initial results show promise for achieving rapid, near one-shot, incremental learning of word meanings.

Error-repair parsing schemata

Robustness, the ability to analyze any input regardless of its grammaticality, is a desirable property for any system dealing with unrestricted natural language text. Error-repair parsing approaches achieve robustness by considering ungrammatical sentences as corrupted versions of valid sentences. In this article we present a deductive formalism, based on Sikkel’s parsing schemata, that can be used to define and relate error-repair parsers and study their formal properties, such as correctness. This formalism allows us to define a general transformation technique to automatically obtain robust, error-repair parsers from standard non-robust parsers. If our method is applied to a correct parsing schema verifying certain conditions, the resulting error-repair parsing schema is guaranteed to be correct. The required conditions are weak enough to be fulfilled by a wide variety of popular parsers used in natural language processing, such as CYK, Earley and Left-Corner.

Wikipedia-based Semantic Interpretation for Natural Language Processing

Adequate representation of natural language semantics requires access to vast amounts of common sense and domain-specific world knowledge. Prior work in the field was based on purely statistical techniques that did not make use of background knowledge, on limited lexicographic knowledge bases such as WordNet, or on huge manual efforts such as the CYC project. Here we propose a novel method, called Explicit Semantic Analysis (ESA), for fine-grained semantic interpretation of unrestricted natural language texts. Our method represents meaning in a high-dimensional space of concepts derived from Wikipedia, the largest encyclopedia in existence. We explicitly represent the meaning of any text in terms of Wikipedia-based concepts. We evaluate the effectiveness of our method on text categorization and on computing the degree of semantic relatedness between fragments of natural language text. Using ESA results in significant improvements over the previous state of the art in both tasks. Importantly, due to the use of natural concepts, the ESA model is easy to explain to human users.

Special Issue on Robust Methods in Analysis of Natural Language Data

The automated analysis of natural language data has become a central issue in the design of Intelligent Information Systems. The term natural language is intended to cover all the possible modalities of human communication and it is not restricted to written or spoken language. Processing unrestricted natural language is still considered as an AI-hard task. However various analysis techniques have been proposed in order to address specific aspects of natural language. In particular, recent interest has been on providing approximate analysis techniques, assuming that perfect analysis is not possible, but that partial results are still very useful.

Structured natural‐language descriptions for semantic content retrieval of visual materials

AbstractKeyword search of multimedia collections lacks precision and automatic parsing of unrestricted natural language annotations lacks accuracy. We propose a structure for natural language descriptions of the semantic content of visual materials that requires descriptions to be (modified) keywords, phrases, or simple sentences, with components that are grammatical relations common to many languages. This structure makes it easy to implement a collection's descriptions as a relational database, enabling efficient search via the application of well‐developed database‐indexing methods. Description components may be elements from external resources (thesaurus, ontology, database, or knowledge base). This provides a rich superstructure for the meaningful retrieval of images by their semantic contents.

Structured natural‐language descriptions for semantic content retrieval of visual materials

Keyword search of multimedia collections lacks precision and automatic parsing of unrestricted natural language annotations lacks accuracy. We propose a structure for natural language descriptions of the semantic content of visual materials that requires descriptions to be (modified) keywords, phrases, or simple sentences, with components that are grammatical relations common to many languages. This structure makes it easy to implement a collection's descriptions as a relational database, enabling efficient search via the application of well-developed database-indexing methods. Description components may be elements from external resources (thesaurus, ontology, database, or knowledge base). This provides a rich superstructure for the meaningful retrieval of images by their semantic contents.

The Rhetorical Parsing of Unrestricted Texts: A Surface-based Approach

Coherent texts are not just simple sequences of clauses and sentences, but rather complex artifacts that have highly elaborate rhetorical structure. This paper explores the extent to which well-formed rhetorical structures can be automatically derived by means of surface-form-based algorithms. These algorithms identify discourse usages of cue phrases and break sentences into clauses, hypothesize rhetorical relations that hold among textual units, and produce valid rhetorical structure trees for unrestricted natural language texts. The algorithms are empirically grounded in a corpus analysis of cue phrases and rely on a first-order formalization of rhetorical structure trees. The algorithms are evaluated both intrinsically and extrinsically. The intrinsic evaluation assesses the resemblance between automatically and manually constructed rhetorical structure trees. The extrinsic evaluation shows that automatically derived rhetorical structures can be successfully exploited in the context of text summarization.

Psychological Assessment Using Simulations with Unrestricted Natural Language Input

Five computerized role-playing scenarios, which accept unrestricted natural language input, were developed and administered to seventy-two freshman medical students. The scenarios, written in CASIP, measured and automatically scored each response on five psychological dimensions: Social skills, level of frustration, submissiveness, combativeness, and negotiative ability. The programmed scenarios also monitored nonverbal dimensions, which may reflect the emotional state of the testee. These included: The time it took to start an answer; the time spent reviewing the answer; the lengths of answers and of the words used. The testees behaved significantly different in handling the different role-playing scenarios. While no significant correlations were found between the psychological dimensions expressed in the different scenarios, the tests identified individual testees who displayed a pattern of extremes of psychological behavior.

Computers and the Future of Medical Practice

To the Editor. —Essin and Steen's editorial 1 notes that, Computer-aided data management has the potential to resolve the problems of legibility, completeness, retrievability, and organization, all of which are so difficult to accomplish by hand. As indicated in a previous related article, a computer-based medical-record system for ambulatory practice should ideally be designed to facilitate individualized attention to each patient to a system that is efficient, cost effective, and professionally satisfying to the physician.... The primary dilemma in the use of a computer-based medical-record system is how to reconcile the physician's custom of recording free-form narrative on a blank page with the computer's need for structure and a predefined vocabulary. 2 For nearly three years, we have used the Gabrieli Medical Information Systems Praktice medical record system which appears to satisfy these concerns. We record patient medical information by hand, in unrestricted natural language, using our customary terminology. At

Testing of a natural language retrieval system for a full text knowledge base.

Abstract“A Navigator of Natural Language Organized Data” (ANNOD) is a retrieval system which combines use of probabilistic, linguistic, and empirical means to rank individual paragraphs of full text for their similarity to natural language queries proposed by users. ANNOD includes common word deletion, word root isolation, query expansion by a thesaurus, and application of a complex empirical matching (ranking) algorithm. The Hepatitis Knowledge Base, the text of a prototype information system, was the file used for testing ANNOD. Responses to a series of users' unrestricted natural language queries were evaluated by three testers. Information needed to answer 85 to 95‰ of the queries was located and displayed in the first few selected paragraphs. It was successful in locating information in both the classified (listed in Table of Contents) and unclassified portions of text. Development of this retrieval system resulted from the complementarity of and interaction between computer science and medical domain expert knowledge. Extension of these techniques to larger knowledge bases is needed to clarify their proper role.

Modeling a paranoid mind

AbstractAlgorithmic model building in artificial intelligence provides a contemporary method for explaining certain kinds of human behavior. The paranoid mode of thought and action represents a kind of pathological behavior that has been well recognized for over twenty centuries. This article describes a computer simulation model embodying a theory that attempts to explain the paranoid mode of behavior in terms of strategies for minimizing and forestalling shame-induced distress. The model consists of two parts, a parsing module and an interpretation-action module. To bring the model into contact with the conditions of a psychiatric diagnostic interview, the parsing module attempts to understand the interview input of clinicians communicating in unrestricted natural language. The meaning of the input is passed to an interpretation-action module made up of data structures and production rules that size up the current state of the interview and decide which (linguistic) actions to perform in order to fulfill the model's intentions. This module consists of an object system which deals with interview situations and a metasystem which evaluates how well the object system is performing to attain its ends. The fidelity of the simulation has been tested using Turing-like indistinguishability tests in which clinical judges attempt to distinguish the paranoid model-patient from an actual paranoid patient. Since clinicians are unable to make the relevant distinctions, the simulation is considered successful at the input-output level of functional equivalence. Issues of underlying structural equivalence and the nature of generative pattern explanations are discussed in the light of the model's potential value in guiding clinicial decisions and intervention strategies in paranoid disorders.