An architectural framework for natural language interfaces to agent systems.
Bibliographic record
Abstract
Christel Kemke University of Manitoba Winnipeg, MB, R3T 2N2 Canada ckemke@cs.umanitoba.ca ABSTRACT In this paper, we describe an architectural framework for the development of natural language interfaces to agent systems. Since the communication between human and artificial agents is mostly task-related, the focus of the suggested architecture is on action representations as core structure and thread in the overall processing. The architectural framework we suggest is based on various forms of action representations and consists of a sequence of transformations, which converts the user’s verbal input into a suitable set of agent actions to produce a response to the input. This process reduces stepwise the complexity and ambiguity of the natural language input by using pre-defined sets of interim actions at different levels, and thus increases the robustness and reliability of the natural language interface. The architecture was employed in the design of several natural language interfaces to agent systems. KEY WORDS Natural Language Interfaces, Human-Agent Communication, Human-Machine Interaction, Knowledge Representation, Ontology, Agent Systems, Action Theory, Description Logic
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.002 | 0.007 |
| Scholarly communication | 0.008 | 0.010 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.004 | 0.005 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".