Research map / Detection and segmentation / Open-set and few-shot detection
Representing Verbs as Argument Concepts
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| AC instead of equal-weight baseline BL (weights by argument quality) (ablation) | argument concepts · Probase concept accuracy, subject, k=5 | accuracy: 0.49 -> 0.88 | Helped |
| AC instead of BL (ablation) | argument concepts · Probase concept accuracy, object, k=5 | accuracy: 0.63 -> 0.97 | Helped |
| AC instead of selectional preference SP | argument concepts · Probase concept accuracy, subject, k=5 | accuracy: 0.58 -> 0.88 | Helped |
| AC instead of SP | argument concepts · Probase concept accuracy, object, k=15 | accuracy: 0.66 -> 0.91 | Helped |
| increase number of concepts k from 5 to 15 | AC · Probase concept accuracy, subject | accuracy: 0.88 -> 0.85 | Hurt |
| increase number of concepts k from 5 to 15 | AC · Probase concept accuracy, object | accuracy: 0.97 -> 0.91 | Hurt |
| AC instead of BL for argument identification (ablation) | argument concepts · Argument identification, Probase, subject, k=5 | accuracy: 0.50 -> 0.81 | Helped |
| AC instead of SP for argument identification | argument concepts · Argument identification, Probase, object, k=5 | accuracy: 0.58 -> 0.62 | Helped |
| AC instead of ReVerb | argument concepts · Argument identification, subject | accuracy: 0.54 -> 0.81 | Helped |
| AC instead of SRL tool Semafor | argument concepts · Argument identification, subject | accuracy: 0.48 -> 0.81 | Helped |
| use WordNet taxonomy instead of Probase (ablation) | AC · Argument identification, subject, k=5 | accuracy: 0.81 -> 0.55 | Hurt |
| use WordNet taxonomy instead of Probase (ablation) | AC · Argument identification, object, k=5 | accuracy: 0.62 -> 0.50 | Hurt |
Closest papers by meaning
- Verb Pattern: A Probabilistic Semantic Representation on Verbs (AAAI 2016 · similarity 0.86)
- Predicting the Argumenthood of English Prepositional Phrases (AAAI 2019 · similarity 0.85)
- Learning Action Changes by Measuring Verb-Adverb Textual Relationships (CVPR 2023 · similarity 0.83)
- Understanding Enthymemes in Deductive Argumentation Using Semantic Distance Measures (AAAI 2022 · similarity 0.82)
- Bayesian Verb Sense Clustering (AAAI 2018 · similarity 0.82)
- Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models (AAAI 2026 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.