We review the scholarly contributions that utilise Natural Language Processing (NLP) methods to support the design process. Using a heuristic approach, we collected 223 articles published in 32 journals and within the period 1991-present. We present state-of-the-art NLP in-and-for design research by reviewing these articles according to the type of natural language text sources: internal reports, design concepts, discourse transcripts, technical publications, consumer opinions, and others. Upon summarizing and identifying the gaps in these contributions, we utilise an existing design innovation framework to identify the applications that are currently being supported by NLP. We then propose a few methodological and theoretical directions for future NLP in-and-for design research.

The increasing importance of resource-efficient production entails that manufacturing companies have to create a more dynamic production environment, with flexible manufacturing machines and processes. To fully utilize this potential of dynamic manufacturing through automatic production planning, formal skill descriptions of the machines are essential. However, generating those skill descriptions in a manual fashion is labor-intensive and requires extensive domain-knowledge. In this contribution an ontology-based semi-automatic skill description system that utilizes production logs and industrial ontologies through inductive logic programming is introduced and benefits and drawbacks of the proposed solution are evaluated.

A prominent problem in knowledge representation is how to answer queries taking into account also the implicit consequences of an ontology representing domain knowledge. While this problem has been widely studied within the realm of description logic ontologies, it has been surprisingly neglected within the context of vague or imprecise knowledge, particularly from the point of view of mathematical fuzzy logic. In this paper we study the problem of answering conjunctive queries and threshold queries w.r.t. ontologies in fuzzy DL-Lite. Specifically, we show through a rewriting approach that threshold query answering w.r.t. consistent ontologies remains in $AC_0$ in data complexity, but that conjunctive query answering is highly dependent on the selected triangular norm, which has an impact on the underlying semantics. For the idempodent G\"odel t-norm, we provide an effective method based on a reduction to the classical case. This paper is under consideration in Theory and Practice of Logic Programming (TPLP).

The increasing amounts of semantic resources offer valuable storage of human knowledge; however, the probability of wrong entries increases with the increased size. The development of approaches that identify potentially spurious parts of a given knowledge base is thus becoming an increasingly important area of interest. In this work, we present a systematic evaluation of whether structure-only link analysis methods can already offer a scalable means to detecting possible anomalies, as well as potentially interesting novel relation candidates. Evaluating thirteen methods on eight different semantic resources, including Gene Ontology, Food Ontology, Marine Ontology and similar, we demonstrated that structure-only link analysis could offer scalable anomaly detection for a subset of the data sets. Further, we demonstrated that by considering symbolic node embedding, explanations of the predictions (links) could be obtained, making this branch of methods potentially more valuable than the black-box only ones. To our knowledge, this is currently one of the most extensive systematic studies of the applicability of different types of link analysis methods across semantic resources from different domains.

AI Researcher, Cognitive Technologist Inventor - AI Thinking, Think Chain Innovator - AIOT, XAI, Autonomous Cars, IIOT Founder Fisheyebox Spatial Computing Savant, Transformative Leader, Industry X.0 Practitioner Are we using #artificialintelligence to determine a theory of everything? It is a real and true AI, which is about modeling and simulation everything in terms of the theory of everything. The so-called "Classic/symbolic/logical AI" is dead due to the large-scale AI projects, as GOFAI, CYC, Soar, Japan's 5th Generation CI, US SCI, WBE, failed and closed or failing. The whole construct of AI, be it weak AI or strong AI, full AI, or HL AI, is turned speculative due to its failed program of simulating human reasoning by formal logical means. Too many AI investments end up as "pretty shiny objects" that don't pay off.

We propose a methodology for extracting concepts for a target domain from large-scale linked open data (LOD) to support the construction of domain ontologies providing field-specific knowledge and definitions. The proposed method defines search entities by linking the LOD vocabulary with technical terms related to the target domain. The search entities are then used as a starting point for obtaining upper-level concepts in the LOD, and the occurrences of common upper-level entities and the chain-of-path relationships are examined to determine the range of conceptual connections in the target domain. A technical dictionary index and natural language processing are used to evaluate whether the extracted concepts cover the domain. As an example of extracting a class hierarchy from LOD, we used Wikidata to construct a domain ontology for polymer materials and physical properties. The proposed method can be applied to general datasets with class hierarchies, and it allows ontology developers to create an initial model of the domain ontology for their own purposes.

Considering a collection of RDF triples, the RDF-to-text generation task aims to generate a text description. Most previous methods solve this task using a sequence-to-sequence model or using a graph-based model to encode RDF triples and to generate a text sequence. Nevertheless, these approaches fail to clearly model the local and global structural information between and within RDF triples. Moreover, the previous methods also face the non-negligible problem of low faithfulness of the generated text, which seriously affects the overall performance of these models. To solve these problems, we propose a model combining two new graph-augmented structural neural encoders to jointly learn both local and global structural information in the input RDF triples. To further improve text faithfulness, we innovatively introduce a reinforcement learning (RL) reward based on information extraction (IE). We first extract triples from the generated text using a pretrained IE model and regard the correct number of the extracted triples as the additional RL reward. Experimental results on two benchmark datasets demonstrate that our proposed model outperforms the state-of-the-art baselines, and the additional reinforcement learning reward does help to improve the faithfulness of the generated text.

The objective of automated Question Answering (QA) systems is to provide answers to user queries in a time efficient manner. The answers are usually found in either databases (or knowledge bases) or a collection of documents commonly referred to as the corpus. In the past few decades there has been a proliferation of acquisition of knowledge and consequently there has been an exponential growth in new scientific articles in the field of biomedicine. Therefore, it has become difficult to keep track of all the information in the domain, even for domain experts. With the improvements in commercial search engines, users can type in their queries and get a small set of documents most relevant for answering their query, as well as relevant snippets from the documents in some cases. However, it may be still tedious and time consuming to manually look for the required information or answers. This has necessitated the development of efficient QA systems which aim to find exact and precise answers to user provided natural language questions in the domain of biomedicine. In this paper, we introduce the basic methodologies used for developing general domain QA systems, followed by a thorough investigation of different aspects of biomedical QA systems, including benchmark datasets and several proposed approaches, both using structured databases and collection of texts. We also explore the limitations of current systems and explore potential avenues for further advancement.

We present a model of sense-making that greatly facilitates the collaboration between an intelligent analyst and a knowledge-based agent. It is a general model grounded in the science of evidence and the scientific method of hypothesis generation and testing, where sense-making hypotheses that explain an observation are generated, relevant evidence is then discovered, and the hypotheses are tested based on the discovered evidence. We illustrate how the model enables an analyst to directly instruct the agent to understand situations involving the possible production of weapons (e.g., chemical warfare agents) and how the agent becomes increasingly more competent in understanding other situations from that domain (e.g., possible production of centrifuge-enriched uranium or of stealth fighter aircraft).

Understanding large ontologies - by humans or machines - is both a struggle and crucially important for performing ontology engineering tasks such as ontology reuse, ontology matching, ontology evaluation, and (federated) querying [2]. According to [6], existing visualisation tools fail in providing overviews of large ontologies, which is crucial for ontology understanding, while none of them allows to compare multiple ontologies. Besides the layout and interaction features, the problem lays in the lack of effective methods for producing summaries of large ontologies. Many summarisation approaches focus on analysing the data level, e.g. to reduce the size of a knowledge graph and allow simplified queries for testing its coverage [16, 3]. Available summarisation methods addressing the conceptual level are based on extractive approaches that select and return a subset of nodes from the original ontology, i.e. the key concepts, as a summary [16]. However, an overall understanding of all the facts an ontology can represent, and a comparison between multiple ontologies, are not supported. For example, we may identify that in a cultural heritage ontology the concepts Cultural Property and Collection are key ones, however this is insufficient to understand if one ontology allows to answer whether a cultural property has been in a collection. Two ontologies having the same key concept would appear they address the same modelling problem, which may not be the case.