Created at 6am, Apr 5
Ms-RAGArtificial Intelligence
0
Standardizing Knowledge Engineering Practices with a Reference Architecture
adLVkhEOum-eA5szcjnxB347BgWSQ6WDSRCTwA9Rdtc
File Type
PDF
Entry Count
123
Embed. Model
jina_embeddings_v2_base_en
Index Type
hnsw

Bradley P. Allen, University of Amsterdam, Amsterdam, The NetherlandsFilip Ilievski, Vrije Universiteit, Amsterdam, The NetherlandsAbstractKnowledge engineering is the process of creating and maintaining knowledge-producing systems.Throughout the history of computer science and AI, knowledge engineering workflows have been widelyused given the importance of high-quality knowledge for reliable intelligent agents. Meanwhile, thescope of knowledge engineering, as apparent from its target tasks and use cases, has been shifting,together with its paradigms such as expert systems, semantic web, and language modeling. Theintended use cases and supported user requirements between these paradigms have not been analyzedglobally, as new paradigms often satisfy prior pain points while possibly introducing new ones. Therecent abstraction of systemic patterns into a boxology provides an opening for aligning the requirementsand use cases of knowledge engineering with the systems, components, and software that cansatisfy them best, however, this direction has not been explored to date. This paper proposes a visionof harmonizing the best practices in the field of knowledge engineering by leveraging the softwareengineering methodology of creating reference architectures. We describe how a reference architecturecan be iteratively designed and implemented to associate user needs with recurring systemic patterns,building on top of existing knowledge engineering workflows and boxologies. We provide a six-steproadmap that can enable the development of such an architecture, consisting of scope definition, selectionof information sources, architectural analysis, synthesis of an architecture based on the informationsource analysis, evaluation through instantiation, and, ultimately, instantiation into a concretesoftware architecture. We provide an initial design and outcome of the definition of architectural scope,selection of information sources, and analysis. As the remaining steps of design, evaluation, and instantiation of the architecture are largely use-case specific, we provide a detailed description of theirprocedures and point to relevant examples. We expect that following through on this vision willlead to well-grounded reference architectures for knowledge engineering, will advance the ongoinginitiatives of organizing the neurosymbolic knowledge engineering space, and will build new linksto the software architectures and data science communities.

g., response times, throughput); costeffectiveness at different scales; system behavior under concurrent user loads
id: 72ad73485675cb185daecee085e192c2 - page: 12
g., RDF, property graphs), serializations (e.g. Turtle, JSON-LD) and query languages (e.g., SPARQL, Cypher), evaluated by ontology quality metrics, pitfall scanning use of standard serializations (e.g., CSV, JSON, Parquet), evaluated by ontology quality metrics, parsing error rate use of software industry-standard data storage mechanisms (e.g., relational databases, RDF data dumps, search engine indexes) and integration standards (e.g., serialized data dumps, publish/subscribe messaging, REST APIs), evaluated by time to deploy, storage and compute costs industry-standard user experience (e.g., command line interfaces, visual editors and browsers, reportin
id: c656ccf7306e3a0a735306f3a23ba6ca - page: 12
g., SQL, Cypher, SPARQL) and query execution strategies (e.g., federated query, centralized query, find-and-follow), with developer experience measured by time to complete tasks, user satisfaction surveys
id: 85492698ff47f65928fb46e2b2ee20b1 - page: 12
Scholar API to obtain snippets from the abstracts of each of the 139 papers described in the B. P. Allen and F. Ilievski Figure 2 Simple neurosymbolic system design patterns from the SWeMLS KG, as shown in . The F2 design pattern, appearing on the right of the figure, is a simple fusion that takes both symbolic (s) and unstructured data (d) as inputs and produces symbolic data (s) as output using a model M. Figure 3 Preliminary analysis of the relationships between quality attributes for KE identified in and the KE design patterns from that are associated with knowledge graph creation and extension. The number in each cell is the count of occurrences of the quality attributes assigned to papers by the zero-shot text classifier that describes systems with the given pattern. previous section.2 We then construct a zero-shot text classifier using prompt programming of ChatGPT that, given an articles snippet and title, assigns one or more quality attributes to
id: fc72aa3cdb3cd3edf3a79a08ad36730c - page: 12
How to Retrieve?
# Search

curl -X POST "https://search.dria.co/hnsw/search" \
-H "x-api-key: <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-d '{"rerank": true, "top_n": 10, "contract_id": "adLVkhEOum-eA5szcjnxB347BgWSQ6WDSRCTwA9Rdtc", "query": "What is alexanDRIA library?"}'
        
# Query

curl -X POST "https://search.dria.co/hnsw/query" \
-H "x-api-key: <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-d '{"vector": [0.123, 0.5236], "top_n": 10, "contract_id": "adLVkhEOum-eA5szcjnxB347BgWSQ6WDSRCTwA9Rdtc", "level": 2}'