Negation in Cognitive Reasoning

This study proposes a dependency grammar-based self-attention multilayered bidirectional long short-term memory (DG-M-Bi-LSTM) model for subject–predicate–object (SPO) tuple recognition from natural language (NL) sentences. To add recent knowledge to the knowledge base autonomously, it is essential to extract knowledge from numerous NL data. Therefore, this study proposes a high-accuracy SPO tuple recognition model that requires a small amount of learning data to extract knowledge from NL sentences. The accuracy of SPO tuple recognition using DG-M-Bi-LSTM is compared with that using NL-based self-attention multilayered bidirectional LSTM, DG-based bidirectional encoder representations from transformers (BERT), and NL-based BERT to evaluate its effectiveness. The DG-M-Bi-LSTM model achieves the best results in terms of recognition accuracy for extracting SPO tuples from NL sentences even if it has fewer deep neural network (DNN) parameters than BERT. In particular, its accuracy is better than that of BERT when the learning data are limited. Additionally, its pretrained DNN parameters can be applied to other domains because it learns the structural relations in NL sentences.

In this paper, we present a system that translates first order logic (FOL) formulas into natural language (NL) sentences. The motivation comes from an intelligent tutoring system teaching logic as a knowledge representation language, where it is used as a means for feedback to the users. FOL to NL conversion is achieved by using a rule-based approach, where we exploit the pattern matching capabilities of rules. So, the system consists of a rule-based component and a lexicon. The rule-based unit implements the conversion process, which is based on a linguistic analysis of a FOL sentence, and the lexicon provides lexical and grammatical information that helps in producing the NL sentences. The whole system is implemented in Jess, a java-based expert system shell. The conversion process currently covers a restricted set of FOL formulas.

Donald Davidson (1984g) famously proposed that what we want from a theory of meaning we may get from a theory of truth. What we want from a theory of meaning for a natural language, that being the case at issue, includes at least an account of the phenomena that give rise to the principle of compositionality: We want an explanation of how the meaning of a complex expression, such as a sentence, depends upon and is determined by the meanings of its syntactic parts. One central advantage of Davidson’s proposal, as he saw it, is that we know from the work of Tarski (1958) how to construct theories of truth for languages with certain sorts of structures, and such a theory does help us to understand how at least some of the semantic properties of complex expressions are determined by those of their parts. Davidson’s practice suggests he may have hoped that all sentences of natural language could be assigned logical forms of the variety familiar from mathematical logic. If so, then semantics would all but reduce to syntax: The only outstanding problem would be to uncover the ‘logical forms’ of the sentences of, say, English. This hope does not now seem reasonable. But the methods available for investigating logical form—that is, for investigating syntax—have become so powerful that it is not at all unreasonable to suppose that the syntactic part of the problem is solvable, at least in principle, and Tarski’s work can be adapted to many of the resulting structures. The work that is left for the semanticist proper then becomes to solve the problems syntax and Tarski do not solve: These include, for example, discovering what sorts of semantic values need to be assigned to novel semantic primitives, such as mass terms, and explaining the semantic significance of novel modes of composition, such as [V PV [CPS]]. It is unfortunate that a proposal with such great advantages faces such grave difficulties. Indeed, it is probably fair to say that most philosophers of language, and perhaps even most working semanticists, regard truththeoretic semantics as a non-starter, for the simple reason that it seems to have the wrong subject-matter. We will not get what we want from a theory of meaning from any theory that does not specify meanings: No theory that does not specify what the sentence ‘snow is white’ means, for example, can possibly explain how this sentence’s meaning what it does is determined by its parts’ meaning what they do. But a theory of truth for English does not specify what even one sentence of English means, since any such theory is consistent with infinitely many different suppositions concerning what any sentence of English means. For example, a theory of truth that proves this T-sentence2 for ‘snow is white’:

Several known methods allow to estimate the overall effort(s) to be used up for the software development. The approach based on story points is preferable and quite common in the context of Sсrum agile development methodology. However, it might be rather challenging for people, who are new to this methodology or to a specific Scrum team to estimate the amount of work with story points. The proposed approach involves estimation of features on the basis of linguistic terms that are both habitual and clear for everyone. The presented fuzzy inference system (Mamdani’s model) makes it possible to calculate story points using people’s opinions expressed as sentences in natural language - the study shows empirically that beginners to Scrum methodology consider the proposed approach to be more convenient and easier in use than the ‘plain’ story points estimation. Also, four groups of people with different levels of qualification in Scrum were asked to estimate several features of a certain project using the developed approach and common story points approach to prove the relevance of the approach - it was shown that the results of basic story points estimation for Scrum experts differ slightly from the results revealed by proposed approach, while for Scrum beginners such difference is significant. To the opinion of authors, the proposed approach may allow to adapt to Scrum more smoothly, with better understanding of what is implied by story points, grasping the general idea and learning faster their use in practice. The experimental study conducted as a part of the research has shown results approaching the estimations provided by Scrum experts who have been working in real projects and making use of story points for several years. Continuation of the present work can be associated with intensive studies of more complicated methods of aggregation of the experts’ opinions, analysis of alternative representation forms of confidence degrees in estimates provided as well as the development of plugin for JIRA tracking system.

Logic as a knowledge representation and reasoning language is a fundamental topic of an Artificial Intelligence (AI) course and includes a number of sub-topics. One of them, which brings difficulties to students to deal with, is converting natural language (NL) sentences into first-order logic (FOL) formulas. To assist students to overcome those difficulties, we developed the NLtoFOL system and equipped it with a strong assistance and feedback mechanism. In this work, first, we present that feedback mechanism. The mechanism can provide assistance before an answer is submitted, if requested, but mainly it provides assistance after an answer is submitted. To that end, it characterizes the answer in terms of completeness and accuracy to determine the level of incorrectness, based on an answer categorization scheme, introduced in this paper. The automatically generated natural language feedback sequences grow from general to specific and can include statements on a student’s metacognitive state. Feedback is provided as natural language sentences automatically generated through a template-based natural language generation mechanism. Second, we present an extensive evaluation of the effectiveness of the assistance and feedback mechanism on students’ learning. The evaluation of feedback with students showed that full feedback sequences lead to greater learning gains than sequences consisting of only flag feedback and bottom-out hints (n = 226), and that generic, template-based feedback sequences are comparable to the utility of problem-specific hints generated by human tutors (n = 120).

Natural language is a crucial tool to facilitate communication in our day-to-day activities. This can be achieved either in text or speech forms. Natural language processing (NLP) involves making computers understand and process natural language. NLP has enhanced the way humans interact with computers, from having computers use speech to talk to humans as well as having computers translate human speech. Apart from speech, computers also create and understand sentences in natural language in a process called morphological analysis. Morphological analysis is an important part in natural language processing, being applied as a preprocessing step in most NLP tasks. Morphological analysis consists of four subtasks, that is, lemmatization, part-of-speech (POS) tagging, word segmentation and stemming. In this paper, we explore in detail each of these tasks of morphological analysis. We then evaluate the techniques used in this NLP field. Finally, we give a summary of the results of each of these techniques.

Natural language is a crucial tool to facilitate communication in our day-to-day activities. This can be achieved either in text or speech forms. Natural language processing (NLP) involves making computers understand and process natural language. NLP has enhanced the way humans interact with computers, from having computers use speech to talk to humans as well as having computers translate human speech. Apart from speech, computers also create and understand sentences in natural language in a process called morphological analysis. Morphological analysis is an important part in natural language processing, being applied as a preprocessing step in most NLP tasks. Morphological analysis consists of four subtasks, that is, lemmatization, part-of-speech (POS) tagging, word segmentation and stemming. In this paper, we explore in detail each of these tasks of morphological analysis. We then evaluate the techniques used in this NLP field. Finally, we give a summary of the results of each of these techniques.

Text is the backbone of the web and most of the information and human knowledge is represented in natural language. Every day, a vast amount of textual information is posted in web portals, wikis and news sites and necessitates automated approaches to analyze and understand their content. In this paper, we present a case-based reasoning approach to transform natural language sentences into first order logic formulas. The formalization approach relies on the principle that natural language sentences with similar grammatical structures and dependency trees would have similar representation in first order logic. The approach consists of two main stages. First, a deep analysis of the natural language sentence is performed, where proper characteristics are extracted and dependencies are specified. After that, in the second stage a cased based reasoning approach is used to utilize existing knowledge (formalized sentences) and drive the formalization of a new sentence. The similarity between natural language sentences is conducted on their dependency trees and is calculated based on the tree edit distance. Then, if needed, the adaptation of a solution is made based on rules. Example studies have shown the applicability of the method and the results on a small number of sentences are very promising.

This paper discusses how to design robot-human communication using Ontological Semantic Technology (OST), which is to address meanings of phrases or sentences in natural languages, in a firefighting domain. The OST is a system in an ontology-based structure to deal with different natural languages. In this study, English and Korean were selected to be implemented for the OST. The problem set is designed with Natural English, direct translation from the natural English to Korean, natural Korean, and direct translation from the natural Korean to English, which can be compared to examine the similarity of meanings with a language-independent ontology in processing English and Korean.

Natural language is the main presentation means in industrial requirements documents. In such documents, system behavior is specified in the form of scenarios, with every scenario written as a sequence of sentences in natural language. To translate scenarios to executable models, message sequence charts (MSCs), we proposed an approach that analyzes textual scenarios by means of computational linguistics by L. Kof (2007). The presented paper shows that (1) a more differentiated treatment of certain sentence types than in our previous work results in better precision of the text-to-MSC translation and (2) it is possible to automate agent identification, performed semiautomatically in our previous work.

A natural language query builder interface retrieves the required data in structured form from database when query is entered in natural language. The user need not necessarily have sufficient technical knowledge of structured query language statements so nontechnical users can also use this proposed model. In natural language parsing, getting highly accurate syntactic analysis is a crucial step. Parsing of natural languages is the process of mapping an input string or a natural language sentence to its syntactic representation. Constituency parsing approach takes more time for parsing. So, natural language query builder interface is developed in which the parsing of natural language sentence is done by using dependency parsing approach. Dependency parsing technique is widespread in natural language domain because of its state-of-art accuracy and efficiency and also it performs best. In this paper, the buffering scheme is also proposed for natural language statements which will not load the whole sentence if it was done previously. Also there was a need of generalized access to all tables from database which is handled in this system.

The paper formulates the basic problem of the content automatic processing of textual information. An author describe formal rules by which we can found logical connections between natural language sentences that compose the electronic text document. Principles of synthesis of logic and linguistic models (LLM) are the conditions under which, within LLM, we can replace components identical by content and form one-dimensional arrays, elements of which are words or phrases that connect natural language sentences to each other in text’s parts. The above principles can be applied to text’s sentences, which are arranged sequential, as well as for sentences from several paragraphs. Expansion and improvement of principles of synthesis for various methods of logical connection between the parts of the text will improve the search content quality using formal logic and linguistic models.

This paper is devoted to present a new approach to natural language understanding which is called here goal-oriented parsing. The interaction in natural language with artificial systems (robots, data base systems, program generators, question-answering systems, etc.) does not require in most cases of actual interest a full (human like) comprehension of natural language in all its details and nuances. A partial understanding is often enough, wich extracts from the natural language expressions the only significant information which is necessary to construct a correct formal input for the target system. In such a model of comprehension the same meaning is assigned to several different natural language expressions, thus defining a many-to-one mapping between natural language sentences and corresponding formal representations. We argue that a bounded scope, restricted, goal-oriented understanding of natural language may greatly increase the efficency of representation models and parsing algorithms, thus allowing the construction of effective systems. This claim is supported by the design and implementation of a natural language interface to a relational data base called NLI and developed at the Milan Polytechnic Artificial Intelligence Project. In the paper the architecture of the system, the linguistic models, and the parsing algorithms are presented and illustrated through selected examples. Promising directions for future research are outlined as well.

Image Captioning is the process of generating textual descriptions of an image, which need to be syntactically and semantically correct. This paper extensively surveys very early literature that includes the advent of Artificial Intelligence, the Machine Learning pathway, the early Deep Learning and the current Deep Learning methodology for Image Captioning. This survey paper aims to develop a system to predict captions for the given images with a higher accuracy by combining the results of different Deep Learning Techniques. This model based on a neural network consists of a vision CNN followed by the language generator RNN. It generates complete sentence in natural language from an input image. The state of art is achieved by comparing three different encoder –decoder models. By comparing three models, the blue score of CNN-LSTM Model with Flikr 8k dataset is 0.44, CNN-LSTM Word Embedding with Flikr 8k dataset is 0.68 and CNN –GRU model Visual Attention with MSCOCO Dataset is 0.86.

The ability to learn optimal control policies in systems where action space is defined by sentences in natural language would allow many interesting real-world applications such as automatic optimisation of dialogue systems. Text-based games with multiple endings and rewards are a promising platform for this task, since their feedback allows us to employ reinforcement learning techniques to jointly learn text representations and control policies. We argue that the key property of AI agents, especially in the text-games context, is their ability to generalise to previously unseen games. We present a minimalistic text-game playing agent, testing its generalisation and transfer learning performance and showing its ability to play multiple games at once. We also present pyfiction, an open-source library for universal access to different text games that could, together with our agent that implements its interface, serve as a baseline for future research.