Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 1209.5663

Semi-automatic annotation process for procedural texts: An application on cooking recipes

Valmi Dufour-Lussier·Florence Le Ber·Jean Lieber·Thomas Meilender·Emmanuel Nauer
View original source ↗Read source document ↗Export metadata ↓

Abstract

Taaable is a case-based reasoning system that adapts cooking recipes to user constraints. Within it, the preparation part of recipes is formalised as a graph. This graph is a semantic representation of the sequence of instructions composing the cooking process and is used to compute the procedure adaptation, conjointly with the textual adaptation. It is composed of cooking actions and ingredients, among others, represented as vertices, and semantic relations between those, shown as arcs, and is built automatically thanks to natural language processing. The results of the automatic annotation process is often a disconnected graph, representing an incomplete annotation, or may contain errors. Therefore, a validating and correcting step is required. In this paper, we present an existing graphic tool named \kcatos, conceived for representing and editing decision trees, and show how it has been adapted and integrated in WikiTaaable, the semantic wiki in which the knowledge used by Taaable is stored. This interface provides the wiki users with a way to correct the case representation of the cooking process, improving at the same time the quality of the knowledge about cooking procedures stored in WikiTaaable.

Explore related subjects

cs.AI

Keep this discovery

BibTeXRIS

Valmi Dufour-Lussier, Florence Le Ber, Jean Lieber, Thomas Meilender, Emmanuel Nauer. 2012-09-25. Semi-automatic annotation process for procedural texts: An application on cooking recipes. https://arxiv.org/abs/1209.5663

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows

Agentic LLM workflows consist of sequences of model turns interleaved with tool interactions, so their end-to-end completion time depends not only on inference speed but also on when ready turns are released. Most runtimes release each turn immediately upon readiness. Under contention, this eager release policy can accumulate released but unfinished work; once submitted, those turns can no longer be reordered by the workflow-level policy, increasing tail latency. We present a tail-risk-aware turn release scheduling method that jointly decides which ready turn to release next and how much released but unfinished work to maintain. The method uses a mean--Conditional Value-at-Risk (CVaR) objective to capture the evolving tail risk of unfinished workflows, incorporates online estimates of turn work when prioritizing ready turns, and adapts the released work budget to observed queue pressure. We evaluate the method using real agent execution traces from software engineering tasks across multiple LLMs and workflow arrival rates. The method performs comparably to eager release under light load and substantially reduces the P95 of workflow flow time under contention, achieving up to a \(3.50\times\) speedup.

cs.AI↗
arXiv2026

Demystifying the Privacy-Utility Trade-off in LLM Interactions

The integration of Large Language Models into daily tasks relies on context-rich instructions, inevitably exposing sensitive user information. Current privacy-preserving methods typically employ context-agnostic static rules, causing severe utility degradation. However, the specific mechanisms governing how sanitization impacts downstream performance remain largely underexplored. To address this, we conduct a systematic analysis to deconstruct the privacy-utility trade-off, uncovering three underlying mechanisms: (1) Context-Dependent Utility, which first establishes when to sanitize by revealing that data value shifts from critical constraints to dispensable noise based on user intent; (2) Strategic Adaptation, which subsequently determines how to sanitize by dictating that the choice between removal and replacement depends on the task's reliance on factual integrity versus structural coherence; and (3) Combinatorial Interplay, which finally extends the protection scope by demonstrating that attributes form a semantic web of synergistic dependencies or antagonistic redundancies. Guided by these insights, we introduce an intent-driven local protection framework. By distilling a lightweight model Veilmind-4B to drive a dynamic extraction-sanitization-restoration pipeline, our approach reaches a low-leakage privacy point while preserving substantially higher response utility than existing privacy-oriented baselines, advancing the privacy-utility trade-off toward the Pareto frontier.

cs.AI↗
arXiv2026

Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks

The term agent in artificial intelligence lacks a standard definition, complicating the evaluation, comparison, and reproducibility of AI agent research. We address this ambiguity through a survey organized around five dimensions of agenticness: environmental interaction, learning and adaptation, autonomy, goal-directed behavior, and temporal coherence. For each dimension, we examine how the underlying capability has been conceptualized across prior work and synthesize the metrics, benchmarks, and evaluation frameworks used to assess it. This review provides a structured account of the current landscape of agent evaluation, highlighting both established approaches and areas where evaluation remains limited or inconsistent. We additionally introduce the Agent Compendium, a public-facing digital resource that organizes and extends the evaluation methods identified through this review. Together, the survey and compendium provide a common structure for evaluating and comparing agent capabilities across AI systems, supporting more reproducible research, clearer communication, and more systematic study of artificial agents.

cs.AI↗