Goal oriented parsing

Natural language is poised to become a key medium for human-machine interactions in the era of large language models. In the field of biochemistry, tasks such as property prediction and molecule mining are critically important yet technically challenging. Bridging molecular expressions in natural language and chemical language can significantly enhance the interpretability and ease of these tasks. Moreover, it can integrate chemical knowledge from various sources, leading to a deeper understanding of molecules. Recognizing these advantages, we introduce the concept of conversational molecular design, a novel task that utilizes natural language to describe and edit target molecules. To better accomplish this task, we develop ChatMol, a knowledgeable and versatile generative pretrained model. This model is enhanced by incorporating experimental property information, molecular spatial knowledge, and the associations between natural and chemical languages. Several typical solutions including large language models (e.g. ChatGPT) are evaluated, proving the challenge of conversational molecular design and the effectiveness of our knowledge enhancement approach. Case observations and analysis offer insights and directions for further exploration of natural-language interaction in molecular discovery. Codes and data are provided in https://github.com/Ellenzzn/ChatMol/tree/main.

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 presented a framework for action descriptions and its connection to natural language interfaces for artificial agents. The core point of this approach is the use of a generic action/object hierarchy, which allows interpretation of natural language command sentences, issued by a human user, as well as planning and reasoning processes on the conceptual level, and connects to the level of agent executable actions. The linguistic analysis is guided by a case frame representation, which provides a connection to actions (and objects) represented on the conceptual level. Planning processes can be implemented using typical precondition and effect descriptions of actions in the conceptual hierarchy. The level of primitive actions (leaf nodes of this conceptual hierarchy) connects to the agents' executable actions. The level of primitive actions can thus be adapted to different types of physical agents with varying action sets. Further work includes the construction of a suitable, general action ontology, based on standard ontologies like FrameNet (ICSI, 2007), Ontolingua (KSL, 2007), Mikrokosmos (CRL, 1996), Cyc (Cycorp, 2007), or SUMO (Pease, 2007; IEEE SUO WG, 2003), which will be enriched with precondition and effect formulas. Other topics to be pursued relate to communication of mobile physical agents (humans) in a "speech-controlled" environment. The scenario is related to the "smart house" but instead of being adaptive and intelligent, the house (or environment) is supposed to respond to verbal instructions and questions by the human user. A special issue, we want to address, is the development of a sophisticated context model, and the use of contextual information to resolve ambiguities in the verbal input and to detect impossible or unreasonable actions.

The purpose of this chapter is to construct a mathematical model describing a system consisting of ten partial operations on the finite sequences with the elements being structured meanings of Natural Language (NL) expressions. Informally, the goal is to develop a mathematical tool being convenient for building semantic representations both of separate sentences in NL and of complex discourses of arbitrary big length pertaining to technology, medicine, economy, and other fields of professional activity. The starting point for developing this model is the definition of the class of conceptual bases introduced in the previous chapter. The constructed mathematical model includes the definition of a new class of formal systems, or calculuses – the class of K-calculuses (knowledge calculuses) and the definition of a new class of formal languages – the class of SK-languages (standard knowledge languages).

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.

An empirical study of representing adjectives over knowledge bases: Approach, lexicon and application

The aim of this paper is to justify why Natural Language (NL) interaction, of a very rich functionality, is critical to the effective use of Expert Systems and to describe what is needed and what has been done to support such interaction. Interactive functions discussed here include defining terms, paraphrasing, correcting misconceptions, avoiding misconceptions, and modifying questions.

Simulation modeling provides powerful decision support capabilities for production planning in manufacturing systems, yet widespread adoption remains limited by significant barriers in model development and maintenance. Traditional simulation approaches require substantial expertise, time investment, and financial resources, creating accessibility challenges particularly for small and medium enterprises. Current research on automatic simulation generation overlooks the significant potential that generative AI can offer in bridging the gap between natural language expression and executable model creation. This paper presents a novel methodology integrating large language models (LLMs) with automatic simulation model generation (ASMG) to enable direct generation of executable simulation models from natural language conversations. Unlike existing ASMG approaches that require formal specifications or simulation knowledge, our framework reduces programming requirements by allowing users to create functional models through conversational interaction. Our approach leverages natural language processing capabilities to transform user requests into executable simulation models without requiring specialized programming knowledge, enhancing human–machine interaction in production planning environments. The framework implements a four-step process: user intent expression through natural language interfaces, knowledge extraction using structured templates, simulation model construction via object-oriented data-driven components, and simulation execution with comprehensive result analysis for resource utilization, bottleneck identification, and production scheduling optimization. Performance testing demonstrates successful model generation across 18 supported action types with response times ranging from 8 s for simple operations to 5 min for complete manufacturing system creation. By enabling direct conversion of natural language requests into functional simulation models, this LLM-enhanced ASMG approach represents a step toward expanding access to simulation technology for non-expert users while maintaining the analytical power needed for complex manufacturing decision support and production control.

Negation is both an operation in formal logic and in natural language by which a proposition is replaced by one stating the opposite, as by the addition of "not" or another negation cue. Treating negation in an adequate way is required for cognitive reasoning, which aims at modeling the human ability to draw meaningful conclusions despite incomplete and inconsistent knowledge. One task of cognitive reasoning is answering questions given by sentences in natural language. There are tools based on discourse representation theory to convert sentences automatically into a formal logic representation, and additional knowledge can be added using the predicate names in the formula and knowledge databases. However, the knowledge in logic databases in practice always is incomplete. Hence, forward reasoning of automated reasoning systems alone does not suffice to derive answers to questions because, instead of complete proofs, often only partial positive knowledge can be derived, while negative knowledge is used only during the reasoning process. In consequence, we aim at eliminating syntactic negation, strictly speaking, the negated event or property. In this paper, we describe an effective procedure to determine the negated event or property in order to replace it by its inverse. This lays the basis of cognitive reasoning, employing both logic and machine learning for general question answering. We evaluate our procedure by several benchmarks and demonstrate its practical usefulness in our cognitive reasoning system.

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.

We present in this paper the design and implementation of the OntoNL Framework, a natural language interface generator for knowledge repositories, as well as a natural language system for interactions with multimedia repositories which was built using the OntoNL Framework. The system allows the users to specify natural language requests about the multimedia content with rich semantics that result to digital content delivery. We propose and evaluate a semantic relatedness measure for OWL domain ontologies that concludes to the semantic ranking of ontological, grammatically-related structures. This procedure is used to disambiguate in a particular domain of context and represent in an ontology query language, natural language expressions. The ontology query language that we use is the SPARQL. The construction of the queries is automated and also dependent on the semantic relatedness measurement of ontology concepts. We also present the results of experimentation with the system.

Chapter 44 - Natural Language Interface Systems

Providers of communication services must be able to respond rapidly to the growing diversity of their customers' service needs as society becomes more dependent on information technologies. This responsiveness will be enhanced if the users themselves can define their service requirements, ideally using natural language. The problem with natural language expressions is their diversity, due to the various viewpoints from which they are written. Thus, we need a means of understanding the semantics of these diverse expressions. In the study outlined here, aimed at understanding the concepts in communication service requirements written in natural language, the authors first clarify the factors causing diversity of expression. These are found to be combinations of three intersecting viewpoints, namely: the interfaces between the network, terminals, and users; the viewpoint from both sides of each interface; and the logical/physical information viewpoint. Next, the target domain of communication services is modeled from the standpoints of operation procedures and functions, communication service concepts are systematized in terms of these models, and a communication service ontology is constructed. Then a semantic recognition method is proposed based on a mapping between concepts and expressions. The effectiveness of the methodology is demonstrated by converting natural language descriptions to formal language specifications. © 1997 Scripta Technica, Inc. Electron Comm Jpn Pt 1, 80(6): 23–36, 1997

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.

Natural and intuitive interaction between users and complex systems is a crucial research topic in human‐computer interaction. A major direction is the definition and implementation of systems with natural language understanding capabilities. The interaction in natural language is often performed by means of systems called chatbots. A chatbot is a conversational agent with a proper knowledge base able to interact with users. Chatbots appearance can be very sophisticated with 3D avatars and speech processing modules. However the interaction between the system and the user is only performed through textual areas for inputs and replies. An interaction able to add to natural language also graphical widgets could be more effective. On the other side, a graphical interaction involving also the natural language can increase the comfort of the user instead of using only graphical widgets. In many applications multi‐modal communication must be preferred when the user and the system have a tight and complex interaction. Typical examples are cultural heritages applications (intelligent museum guides, picture browsing) or systems providing the user with integrated information taken from different and heterogenous sources as in the case of the iGoogle™ interface. We propose to mix the two modalities (verbal and graphical) to build systems with a reconfigurable interface, which is able to change with respect to the particular application context. The result of this proposal is the Graphical Artificial Intelligence Markup Language (GAIML) an extension of AIML allowing merging both interaction modalities. In this context a suitable chatbot system called Graphbot is presented to support this language. With this language is possible to define personalized interface patterns that are the most suitable ones in relation to the data types exchanged between the user and the system according to the context of the dialogue.