Visible to the public Biblio

Filters: Keyword is Natural languages  [Clear All Filters]
2023-05-12
Albornoz-De Luise, Romina Soledad, Arnau-González, Pablo, Arevalillo-Herráez, Miguel.  2022.  Conversational Agent Design for Algebra Tutoring. 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC). :604–609.
Conversational Intelligent Tutoring Systems (CITS) in learning environments are capable of providing personalized instruction to students in different domains, to improve the learning process. This interaction between the Intelligent Tutoring System (ITS) and the user is carried out through dialogues in natural language. In this study, we use an open source framework called Rasa to adapt the original button-based user interface of an algebraic/arithmetic word problem-solving ITS to one based primarily on the use of natural language. We conducted an empirical study showing that once properly trained, our conversational agent was able to recognize the intent related to the content of the student’s message with an average accuracy above 0.95.
ISSN: 2577-1655
Jbene, Mourad, Tigani, Smail, Saadane, Rachid, Chehri, Abdellah.  2022.  An LSTM-based Intent Detector for Conversational Recommender Systems. 2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring). :1–5.
With the rapid development of artificial intelligence (AI), many companies are moving towards automating their services using automated conversational agents. Dialogue-based conversational recommender agents, in particular, have gained much attention recently. The successful development of such systems in the case of natural language input is conditioned by the ability to understand the users’ utterances. Predicting the users’ intents allows the system to adjust its dialogue strategy and gradually upgrade its preference profile. Nevertheless, little work has investigated this problem so far. This paper proposes an LSTM-based Neural Network model and compares its performance to seven baseline Machine Learning (ML) classifiers. Experiments on a new publicly available dataset revealed The superiority of the LSTM model with 95% Accuracy and 94% F1-score on the full dataset despite the relatively small dataset size (9300 messages and 17 intents) and label imbalance.
ISSN: 2577-2465
2023-01-13
Kovačević, Ivan, Štengl, Bruno, Groš, Stjepan.  2022.  Systematic review of automatic translation of high-level security policy into firewall rules. 2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO). :1063–1068.
Firewalls are security devices that perform network traffic filtering. They are ubiquitous in the industry and are a common method used to enforce organizational security policy. Security policy is specified on a high level of abstraction, with statements such as "web browsing is allowed only on workstations inside the office network", and needs to be translated into low-level firewall rules to be enforceable. There has been a lot of work regarding optimization, analysis and platform independence of firewall rules, but an area that has seen much less success is automatic translation of high-level security policies into firewall rules. In addition to improving rules’ readability, such translation would make it easier to detect errors.This paper surveys of over twenty papers that aim to generate firewall rules according to a security policy specified on a higher level of abstraction. It also presents an overview of similar features in modern firewall systems. Most approaches define specialized domain languages that get compiled into firewall rule sets, with some of them relying on formal specification, ontology, or graphical models. The approaches’ have improved over time, but there are still many drawbacks that need to be solved before wider application.
2022-09-30
Yu, Dongqing, Hou, Xiaowei, Li, Ce, Lv, Qiujian, Wang, Yan, Li, Ning.  2021.  Anomaly Detection in Unstructured Logs Using Attention-based Bi-LSTM Network. 2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC). :403–407.
System logs record valuable information about the runtime status of IT systems. Therefore, system logs are a naturally excellent source of information for anomaly detection. Most of the existing studies on log-based anomaly detection construct a detection model to identify anomalous logs. Generally, the model treats historical logs as natural language sequences and learns the normal patterns from normal log sequences, and detects deviations from normal patterns as anomalies. However, the majority of existing methods focus on sequential and quantitative information and ignore semantic information hidden in log sequence so that they are inefficient in anomaly detection. In this paper, we propose a novel framework for automatically detecting log anomalies by utilizing an attention-based Bi-LSTM model. To demonstrate the effectiveness of our proposed model, we evaluate the performance on a public production log dataset. Extensive experimental results show that the proposed approach outperforms all comparison methods for anomaly detection.
2022-08-12
Stegemann-Philipps, Christian, Butz, Martin V..  2021.  Learn It First: Grounding Language in Compositional Event-Predictive Encodings. 2021 IEEE International Conference on Development and Learning (ICDL). :1–6.
While language learning in infants and toddlers progresses somewhat seamlessly, in artificial systems the grounding of language in knowledge structures that are learned from sensorimotor experiences remains a hard challenge. Here we introduce LEARNA, which learns event-characterizing abstractions to resolve natural language ambiguity. LEARNA develops knowledge structures from simulated sensorimotor experiences. Given a possibly ambiguous descriptive utterance, the learned knowledge structures enable LEARNA to infer environmental scenes, and events unfolding within, which essentially constitute plausible imaginations of the utterance’s content. Similar event-predictive structures may help in developing artificial systems that can generate and comprehend descriptions of scenes and events.
2022-07-29
Ismaeel, Khaled, Naumchev, Alexandr, Sadovykh, Andrey, Truscan, Dragos, Enoiu, Eduard Paul, Seceleanu, Cristina.  2021.  Security Requirements as Code: Example from VeriDevOps Project. 2021 IEEE 29th International Requirements Engineering Conference Workshops (REW). :357–363.
This position paper presents and illustrates the concept of security requirements as code – a novel approach to security requirements specification. The aspiration to minimize code duplication and maximize its reuse has always been driving the evolution of software development approaches. Object-Oriented programming (OOP) takes these approaches to the state in which the resulting code conceptually maps to the problem that the code is supposed to solve. People nowadays start learning to program in the primary school. On the other hand, requirements engineers still heavily rely on natural language based techniques to specify requirements. The key idea of this paper is: artifacts produced by the requirements process should be treated as input to the regular object-oriented analysis. Therefore, the contribution of this paper is the presentation of the major concepts for the security requirements as the code method that is illustrated with a real industry example from the VeriDevOps project.
2022-07-12
Khanzadi, Pouria, Kordnoori, Shirin, Vasigh, Zahra, Mostafaei, Hamidreza, Akhtarkavan, Ehsan.  2021.  A Cyber Physical System based Stochastic Process Language With NuSMV Model Checker. 2021 International Conference on Intelligent Technology, System and Service for Internet of Everything (ITSS-IoE). :1—8.
Nowadays, cyber physical systems are playing an important role in human life in which they provide features that make interactions between human and machine easier. To design and analysis such systems, the main problem is their complexity. In this paper, we propose a description language for cyber physical systems based on stochastic processes. The proposed language is called SPDL (Stochastic Description Process Language). For designing SPDL, two main parts are considered for Cyber Physical Systems (CSP): embedded systems and physical environment. Then these parts are defined as stochastic processes and CPS is defined as a tuple. Syntax and semantics of SPDL are stated based on the proposed definition. Also, the semantics are defined as by set theory. For implementation of SPDL, dependencies between words of a requirements are extracted as a tree data structure. Based on the dependencies, SPDL is used for describing the CPS. Also, a lexical analyzer and a parser based on a defined BNF grammar for SPDL is designed and implemented. Finally, SPDL of CPS is transformed to NuSMV which is a symbolic model checker. The Experimental results show that SPDL is capable of describing cyber physical systems by natural language.
2022-05-19
Zhang, Cheng, Yamana, Hayato.  2021.  Improving Text Classification Using Knowledge in Labels. 2021 IEEE 6th International Conference on Big Data Analytics (ICBDA). :193–197.
Various algorithms and models have been proposed to address text classification tasks; however, they rarely consider incorporating the additional knowledge hidden in class labels. We argue that hidden information in class labels leads to better classification accuracy. In this study, instead of encoding the labels into numerical values, we incorporated the knowledge in the labels into the original model without changing the model architecture. We combined the output of an original classification model with the relatedness calculated based on the embeddings of a sequence and a keyword set. A keyword set is a word set to represent knowledge in the labels. Usually, it is generated from the classes while it could also be customized by the users. The experimental results show that our proposed method achieved statistically significant improvements in text classification tasks. The source code and experimental details of this study can be found on Github11https://github.com/HeroadZ/KiL.
2022-04-19
Srinivasan, Sudarshan, Begoli, Edmon, Mahbub, Maria, Knight, Kathryn.  2021.  Nomen Est Omen - The Role of Signatures in Ascribing Email Author Identity with Transformer Neural Networks. 2021 IEEE Security and Privacy Workshops (SPW). :291–297.
Authorship attribution, an NLP problem where anonymous text is matched to its author, has important, cross-disciplinary applications, particularly those concerning cyber-defense. Our research examines the degree of sensitivity that attention-based models have to adversarial perturbations. We ask, what is the minimal amount of change necessary to maximally confuse a transformer model? In our investigation we examine a balanced subset of emails from the Enron email dataset, calculating the performance of our model before and after email signatures have been perturbed. Results show that the model's performance changed significantly in the absence of a signature, indicating the importance of email signatures in email authorship detection. Furthermore, we show that these models rely on signatures for shorter emails much more than for longer emails. We also indicate that additional research is necessary to investigate stylometric features and adversarial training to further improve classification model robustness.
2022-04-12
Chen, Huiping, Dong, Changyu, Fan, Liyue, Loukides, Grigorios, Pissis, Solon P., Stougie, Leen.  2021.  Differentially Private String Sanitization for Frequency-Based Mining Tasks. 2021 IEEE International Conference on Data Mining (ICDM). :41—50.
Strings are used to model genomic, natural language, and web activity data, and are thus often shared broadly. However, string data sharing has raised privacy concerns stemming from the fact that knowledge of length-k substrings of a string and their frequencies (multiplicities) may be sufficient to uniquely reconstruct the string; and from that the inference of such substrings may leak confidential information. We thus introduce the problem of protecting length-k substrings of a single string S by applying Differential Privacy (DP) while maximizing data utility for frequency-based mining tasks. Our theoretical and empirical evidence suggests that classic DP mechanisms are not suitable to address the problem. In response, we employ the order-k de Bruijn graph G of S and propose a sampling-based mechanism for enforcing DP on G. We consider the task of enforcing DP on G using our mechanism while preserving the normalized edge multiplicities in G. We define an optimization problem on integer edge weights that is central to this task and develop an algorithm based on dynamic programming to solve it exactly. We also consider two variants of this problem with real edge weights. By relaxing the constraint of integer edge weights, we are able to develop linear-time exact algorithms for these variants, which we use as stepping stones towards effective heuristics. An extensive experimental evaluation using real-world large-scale strings (in the order of billions of letters) shows that our heuristics are efficient and produce near-optimal solutions which preserve data utility for frequency-based mining tasks.
2022-03-10
Tiwari, Sarthak, Bansal, Ajay.  2021.  Domain-Agnostic Context-Aware Framework for Natural Language Interface in a Task-Based Environment. 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC). :15—20.
Smart home assistants are becoming a norm due to their ease-of-use. They employ spoken language as an interface, facilitating easy interaction with their users. Even with their obvious advantages, natural-language based interfaces are not prevalent outside the domain of home assistants. It is hard to adopt them for computer-controlled systems due to the numerous complexities involved with their implementation in varying fields. The main challenge is the grounding of natural language base terms into the underlying system's primitives. The existing systems that do use natural language interfaces are specific to one problem domain only.In this paper, a domain-agnostic framework that creates natural language interfaces for computer-controlled systems has been developed by creating a customizable mapping between the language constructs and the system primitives. The framework employs ontologies built using OWL (Web Ontology Language) for knowledge representation and machine learning models for language processing tasks.
2022-02-25
Abdelnabi, Sahar, Fritz, Mario.  2021.  Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding. 2021 IEEE Symposium on Security and Privacy (SP). :121–140.
Recent advances in natural language generation have introduced powerful language models with high-quality output text. However, this raises concerns about the potential misuse of such models for malicious purposes. In this paper, we study natural language watermarking as a defense to help better mark and trace the provenance of text. We introduce the Adversarial Watermarking Transformer (AWT) with a jointly trained encoder-decoder and adversarial training that, given an input text and a binary message, generates an output text that is unobtrusively encoded with the given message. We further study different training and inference strategies to achieve minimal changes to the semantics and correctness of the input text.AWT is the first end-to-end model to hide data in text by automatically learning -without ground truth- word substitutions along with their locations in order to encode the message. We empirically show that our model is effective in largely preserving text utility and decoding the watermark while hiding its presence against adversaries. Additionally, we demonstrate that our method is robust against a range of attacks.
2022-02-09
Xu, Xiaojun, Wang, Qi, Li, Huichen, Borisov, Nikita, Gunter, Carl A., Li, Bo.  2021.  Detecting AI Trojans Using Meta Neural Analysis. 2021 IEEE Symposium on Security and Privacy (SP). :103–120.
In machine learning Trojan attacks, an adversary trains a corrupted model that obtains good performance on normal data but behaves maliciously on data samples with certain trigger patterns. Several approaches have been proposed to detect such attacks, but they make undesirable assumptions about the attack strategies or require direct access to the trained models, which restricts their utility in practice.This paper addresses these challenges by introducing a Meta Neural Trojan Detection (MNTD) pipeline that does not make assumptions on the attack strategies and only needs black-box access to models. The strategy is to train a meta-classifier that predicts whether a given target model is Trojaned. To train the meta-model without knowledge of the attack strategy, we introduce a technique called jumbo learning that samples a set of Trojaned models following a general distribution. We then dynamically optimize a query set together with the meta-classifier to distinguish between Trojaned and benign models.We evaluate MNTD with experiments on vision, speech, tabular data and natural language text datasets, and against different Trojan attacks such as data poisoning attack, model manipulation attack, and latent attack. We show that MNTD achieves 97% detection AUC score and significantly outperforms existing detection approaches. In addition, MNTD generalizes well and achieves high detection performance against unforeseen attacks. We also propose a robust MNTD pipeline which achieves around 90% detection AUC even when the attacker aims to evade the detection with full knowledge of the system.
2022-01-25
Hughes, Kieran, McLaughlin, Kieran, Sezer, Sakir.  2021.  Towards Intrusion Response Intel. 2021 IEEE International Conference on Cyber Security and Resilience (CSR). :337—342.
Threat Intelligence has been a key part of the success of Intrusion Detection, with several trusted sources leading to wide adoption and greater understanding of new and trending threats to computer networks. Identifying potential threats and live attacks on networks is only half the battle, knowing how to correctly respond to these threats and attacks requires in-depth and domain specific knowledge, which may be unique to subject experts and software vendors. Network Incident Responders and Intrusion Response Systems can benefit from a similar approach to Threat Intel, with a focus on potential Response actions. A qualitative comparison of current Threat Intel Sources and prominent Intrusion Response Systems is carried out to aid in the identification of key requirements to be met to enable the adoption of Response Intel. Building on these requirements, a template for Response Intel is proposed which incorporates standardised models developed by MITRE. Similarly, to facilitate the automated use of Response Intel, a structure for automated Response Actions is proposed.
2021-12-22
Poli, Jean-Philippe, Ouerdane, Wassila, Pierrard, Régis.  2021.  Generation of Textual Explanations in XAI: The Case of Semantic Annotation. 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). :1–6.
Semantic image annotation is a field of paramount importance in which deep learning excels. However, some application domains, like security or medicine, may need an explanation of this annotation. Explainable Artificial Intelligence is an answer to this need. In this work, an explanation is a sentence in natural language that is dedicated to human users to provide them clues about the process that leads to the decision: the labels assignment to image parts. We focus on semantic image annotation with fuzzy logic that has proven to be a useful framework that captures both image segmentation imprecision and the vagueness of human spatial knowledge and vocabulary. In this paper, we present an algorithm for textual explanation generation of the semantic annotation of image regions.
2021-11-08
Ma, Qicheng, Rastogi, Nidhi.  2020.  DANTE: Predicting Insider Threat using LSTM on system logs. 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom). :1151–1156.
Insider threat is one of the most pernicious threat vectors to information and communication technologies (ICT) across the world due to the elevated level of trust and access that an insider is afforded. This type of threat can stem from both malicious users with a motive as well as negligent users who inadvertently reveal details about trade secrets, company information, or even access information to malignant players. In this paper, we propose a novel approach that uses system logs to detect insider behavior using a special recurrent neural network (RNN) model. Ground truth is established using DANTE and used as baseline for identifying anomalous behavior. For this, system logs are modeled as a natural language sequence and patterns are extracted from these sequences. We create workflows of sequences of actions that follow a natural language logic and control flow. These flows are assigned various categories of behaviors - malignant or benign. Any deviation from these sequences indicates the presence of a threat. We further classify threats into one of the five categories provided in the CERT insider threat dataset. Through experimental evaluation, we show that the proposed model can achieve 93% prediction accuracy.
2021-02-22
Alzahrani, A., Feki, J..  2020.  Toward a Natural Language-Based Approach for the Specification of Decisional-Users Requirements. 2020 3rd International Conference on Computer Applications Information Security (ICCAIS). :1–6.
The number of organizations adopting the Data Warehouse (DW) technology along with data analytics in order to improve the effectiveness of their decision-making processes is permanently increasing. Despite the efforts invested, the DW design remains a great challenge research domain. More accurately, the design quality of the DW depends on several aspects; among them, the requirement-gathering phase is a critical and complex task. In this context, we propose a Natural language (NL) NL-template based design approach, which is twofold; firstly, it facilitates the involvement of decision-makers in the early step of the DW design; indeed, using NL is a good and natural means to encourage the decision-makers to express their requirements as query-like English sentences. Secondly, our approach aims to generate a DW multidimensional schema from a set of gathered requirements (as OLAP: On-Line-Analytical-Processing queries, written according to the NL suggested templates). This approach articulates around: (i) two NL-templates for specifying multidimensional components, and (ii) a set of five heuristic rules for extracting the multidimensional concepts from requirements. Really, we are developing a software prototype that accepts the decision-makers' requirements then automatically identifies the multidimensional components of the DW model.
Rivera, S., Fei, Z., Griffioen, J..  2020.  POLANCO: Enforcing Natural Language Network Policies. 2020 29th International Conference on Computer Communications and Networks (ICCCN). :1–9.
Network policies govern the use of an institution's networks, and are usually written in a high-level human-readable natural language. Normally these policies are enforced by low-level, technically detailed network configurations. The translation from network policies into network configurations is a tedious, manual and error-prone process. To address this issue, we propose a new intermediate language called POlicy LANguage for Campus Operations (POLANCO), which is a human-readable network policy definition language intended to approximate natural language. Because POLANCO is a high-level language, the translation from natural language policies to POLANCO is straightforward. Despite being a high-level human readable language, POLANCO can be used to express network policies in a technically precise way so that policies written in POLANCO can be automatically translated into a set of software defined networking (SDN) rules and actions that enforce the policies. Moreover, POLANCO is capable of incorporating information about the current network state, reacting to changes in the network and adjusting SDN rules to ensure network policies continue to be enforced correctly. We present policy examples found on various public university websites and show how they can be written as simplified human-readable statements using POLANCO and how they can be automatically translated into SDN rules that correctly enforce these policies.
2020-11-02
Bilanová, Z., Perháč, J..  2019.  About possibilities of applying logical analysis of natural language in computer science. 2019 IEEE 13th International Symposium on Applied Computational Intelligence and Informatics (SACI). :251–256.
This paper deals with the comparison of the most popular methods of a logical analysis of natural language Montague intensional logic and Transparent intensional logic. At first, these logical apparatuses are compared in terms of their founding theoretical principles. Later, the selected sentence is examined through the logical analysis. The aim of the paper is to identify a more expressive logical method, which will be a suitable basis for the future design of an algorithm for the automated translation of the natural language into a formal representation of its meaning through a semantic machine.
2020-07-16
Velmovitsky, Pedro Elkind, Viana, Marx, Cirilo, Elder, Milidiu, Ruy Luiz, Pelegrini Morita, Plinio, Lucena, Carlos José Pereira de.  2019.  Promoting Reusability and Extensibility in the Engineering of Domain-Specific Conversational Systems. 2019 8th Brazilian Conference on Intelligent Systems (BRACIS). :473—478.

Conversational systems are computer programs that interact with users using natural language. Considering the complexity and interaction of the different components involved in building intelligent conversational systems that can perform diverse tasks, a promising approach to facilitate their development is by using multiagent systems (MAS). This paper reviews the main concepts and history of conversational systems, and introduces an architecture based on MAS. This architecture was designed to support the development of conversational systems in the domain chosen by the developer while also providing a reusable built-in dialogue control. We present a practical application in the healthcare domain. We observed that it can help developers to create conversational systems in different domains while providing a reusable and centralized dialogue control. We also present derived lessons learned that can be helpful to steer future research on engineering domain-specific conversational systems.

2020-05-22
Platonov, A.V., Poleschuk, E.A., Bessmertny, I. A., Gafurov, N. R..  2018.  Using quantum mechanical framework for language modeling and information retrieval. 2018 IEEE 12th International Conference on Application of Information and Communication Technologies (AICT). :1—4.

This article shows the analogy between natural language texts and quantum-like systems on the example of the Bell test calculating. The applicability of the well-known Bell test for texts in Russian is investigated. The possibility of using this test for the text separation on the topics corresponding to the user query in information retrieval system is shown.

2020-04-24
Emeka, Busalire Onesmus, Liu, Shaoying.  2018.  Assessing and extracting software security vulnerabilities in SOFL formal specifications. 2018 International Conference on Electronics, Information, and Communication (ICEIC). :1—4.

The growth of the internet has brought along positive gains such as the emergence of a highly interconnected world. However, on the flip side, there has been a growing concern on how secure distributed systems can be built effectively and tested for security vulnerabilities prior to deployment. Developing a secure software product calls for a deep technical understanding of some complex issues with regards to the software and its operating environment, as well as embracing a systematic approach of analyzing the software. This paper proposes a method for identifying software security vulnerabilities from software requirement specifications written in Structured Object-oriented Formal Language (SOFL). Our proposed methodology leverages on the concept of providing an early focus on security by identifying potential security vulnerabilities at the requirement analysis and verification phase of the software development life cycle.

2018-05-24
Joshaghani, R., Mehrpouyan, H..  2017.  A Model-Checking Approach for Enforcing Purpose-Based Privacy Policies. 2017 IEEE Symposium on Privacy-Aware Computing (PAC). :178–179.

With the growth of Internet in many different aspects of life, users are required to share private information more than ever. Hence, users need a privacy management tool that can enforce complex and customized privacy policies. In this paper, we propose a privacy management system that not only allows users to define complex privacy policies for data sharing actions, but also monitors users' behavior and relationships to generate realistic policies. In addition, the proposed system utilizes formal modeling and model-checking approach to prove that information disclosures are valid and privacy policies are consistent with one another.

2018-02-15
Hibshi, H., Breaux, T. D..  2017.  Reinforcing Security Requirements with Multifactor Quality Measurement. 2017 IEEE 25th International Requirements Engineering Conference (RE). :144–153.

Choosing how to write natural language scenarios is challenging, because stakeholders may over-generalize their descriptions or overlook or be unaware of alternate scenarios. In security, for example, this can result in weak security constraints that are too general, or missing constraints. Another challenge is that analysts are unclear on where to stop generating new scenarios. In this paper, we introduce the Multifactor Quality Method (MQM) to help requirements analysts to empirically collect system constraints in scenarios based on elicited expert preferences. The method combines quantitative statistical analysis to measure system quality with qualitative coding to extract new requirements. The method is bootstrapped with minimal analyst expertise in the domain affected by the quality area, and then guides an analyst toward selecting expert-recommended requirements to monotonically increase system quality. We report the results of applying the method to security. This include 550 requirements elicited from 69 security experts during a bootstrapping stage, and subsequent evaluation of these results in a verification stage with 45 security experts to measure the overall improvement of the new requirements. Security experts in our studies have an average of 10 years of experience. Our results show that using our method, we detect an increase in the security quality ratings collected in the verification stage. Finally, we discuss how our proposed method helps to improve security requirements elicitation, analysis, and measurement.

2018-01-10
Meltsov, V. Y., Lesnikov, V. A., Dolzhenkova, M. L..  2017.  Intelligent system of knowledge control with the natural language user interface. 2017 International Conference "Quality Management,Transport and Information Security, Information Technologies" (IT QM IS). :671–675.
This electronic document is a “live” template and already defines the components of your paper [title, text, heads, etc.] in its style sheet. The paper considers the possibility and necessity of using in modern control and training systems with a natural language interface methods and mechanisms, characteristic for knowledge processing systems. This symbiosis assumes the introduction of specialized inference machines into the testing systems. For the effective operation of such an intelligent interpreter, it is necessary to “translate” the user's answers into one of the known forms of the knowledge representation, for example, into the expressions (rules) of the first-order predicate calculus. A lexical processor, performing morphological, syntactic and semantic analysis, solves this task. To simplify further work with the rules, the Skolem-transformation is used, which allows to get rid of quantifiers and to present semantic structures in the form of sequents (clauses, disjuncts). The basic principles of operation of the inference machine are described, which is the main component of the developed intellectual subsystem. To improve the performance of the machine, one of the fastest methods was chosen - a parallel method of deductive inference based on the division of clauses. The parallelism inherent in the method, and the use of the dataflow architecture, allow parallel computations in the output machine to be implemented without additional effort on the part of the programmer. All this makes it possible to reduce the time for comparing the sequences stored in the knowledge base by several times as compared to traditional inference mechanisms that implement various versions of the principle of resolutions. Formulas and features of the technique of numerical estimation of the user's answers are given. In general, the development of the human-computer dialogue capabilities in test systems- through the development of a specialized module for processing knowledge, will increase the intelligence of such systems and allow us to directly consider the semantics of sentences, more accurately determine the relevance of the user's response to standard knowledge and, ultimately, get rid of the skeptical attitude of many managers to machine testing systems.