Anchor and Broadcast: An Efficient Concept Alignment Approach for Evaluation of Semantic Graphs
In this paper, we present AnCast, an intuitive and efficient tool for evaluating graph-based meaning representations (MR). AnCast implements evaluation metrics that are well understood in the NLP community, and they include concept F1, unlabeled relation F1, labeled relation F1, and weighted relation F1. The efficiency of the tool comes from a novel anchor broadcast alignment algorithm that is not subject to the trappings of local maxima. We show through experimental results that the AnCast score is highly correlated with the widely used Smatch score, but its computation takes only about 40% the time.
Code (1)
Tasks
AMR Graph SimilarityConcept AlignmentRelationSimilar Papers 제목 키워드 기반
Semantic Anchoring for Robust Personalization in Text-to-Image Diffusion Models
Text-to-image diffusion models have achieved remarkable progress in generating diverse and realistic images from textual descriptions. However, they still struggle with personalization, which requires adapting a pretrain…
Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model
Concept Erasure, which aims to prevent pretrained text-to-image models from generating content associated with semantic-harmful concepts (i.e., target concepts), is getting increased attention. State-of-the-art methods f…
Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation
Vision transformer has demonstrated great potential in abundant vision tasks. However, it also inevitably suffers from poor generalization capability when the distribution shift occurs in testing (i.e., out-of-distributi…
Domain AdaptationPseudo LabelUnsupervised Domain AdaptationAG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
Large multimodal models (LMMs) exhibit strong task generalization capabilities, offering new opportunities for zero-shot visual anomaly segmentation (ZSAS). However, existing LMM-based segmentation approaches still face …
Who to Watch Next: Two-side Interactive Networks for Live Broadcast Recommendation
With the prevalence of live broadcast business nowadays, a new type of recommendation service, called live broadcast recommendation, is widely used in many mobile e-commerce Apps. Different from classical item recommenda…
Retrieval