Designing and Generating Conversational Agents in the Safe Transportation Sector Using DSL
Bibliographic record
Abstract
The transportation sector is increasingly integrating intelligent conversational agents to enhance user experience, streamline operations, and promote safer travel. These agents serve critical functions such as providing round-the-clock information, responding to frequently asked questions, and improving customer service interactions. They are typically categorized into rule-based agents-built upon predefined rules and intents-and AI-based agents, which employ advanced techniques like deep learning and natural language processing (NLP). To simplify development, many organizations utilize graphical interfaces powered by APIs from intent recognition platforms such as IBM Watson and Dialogflow. However, these APIs present notable limitations, including vendor lock-in and high operational costs. Moreover, the absence of a dedicated development platform tailored to the transportation domain poses additional challenges. To address these gaps, this paper proposes a Domain-Specific Language (DSL) designed for the modeling and generation of conversational agents in the transportation sector. The proposed graphical DSL leverages Model-Driven Engineering (MDE) to accelerate agent creation and automatically generate necessary components-such as data files, configuration files, and source code-for training and deployment, thereby reducing development time and cost.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".