paper-with-me

홈 › Papers

Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting

2023-12-19 · Haowei Du, Dinghao Zhang, Chen Li, Yang Li, Dongyan Zhao

Recent approaches in Incomplete Utterance Rewriting (IUR) fail to capture the source of important words, which is crucial to edit the incomplete utterance, and introduce words from irrelevant utterances. We propose a novel and effective multi-task information interaction framework including context selection, edit matrix construction, and relevance merging to capture the multi-granularity of semantic information. Benefiting from fetching the relevant utterance and figuring out the important words, our approach outperforms existing state-of-the-art models on two benchmark datasets Restoration-200K and CANAND in this field. Code will be provided on \url{https://github.com/yanmenxue/QR}.

📄 PDF Abstract BibTeX arXiv:2312.11945

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multiple Granularity Analysis for Fine-grained Action Detection

2014-06-01 · CVPR 2014 6 · Bingbing Ni, Vignesh R. Paramathayalan, Pierre Moulin

We propose to decompose the fine-grained human activity analysis problem into two sequential tasks with increasing granularity. Firstly, we infer the coarse interaction status, i.e., which object is being manipulated and…

Action DetectionFine-Grained Action DetectionObjectPosition

Learning Granularity Representation for Temporal Knowledge Graph Completion

2024-08-27 · Jinchuan Zhang, Tianqi Wan, Chong Mu, Guangxi Lu 외

Temporal Knowledge Graphs (TKGs) incorporate temporal information to reflect the dynamic structural knowledge and evolutionary patterns of real-world facts. Nevertheless, TKGs are still limited in downstream applications…

Knowledge Graph CompletionKnowledge GraphsLink PredictionRepresentation Learning+1

X-ReID: Multi-granularity Information Interaction for Video-Based Visible-Infrared Person Re-Identification

2025-11-22 · Chenyang Yu, Xuehu Liu, Pingping Zhang, Huchuan Lu arxiv

Large-scale vision-language models (e.g., CLIP) have recently achieved remarkable performance in retrieval tasks, yet their potential for Video-based Visible-Infrared Person Re-Identification (VVI-ReID) remains largely u…

Person Re-Identification

Multi-granularity Association Learning Framework for on-the-fly Fine-Grained Sketch-based Image Retrieval

2022-01-13 · Dawei Dai, Xiaoyu Tang, Shuyin Xia, Yingge Liu 외

Fine-grained sketch-based image retrieval (FG-SBIR) addresses the problem of retrieving a particular photo in a given query sketch. However, its widespread applicability is limited by the fact that it is difficult to dra…

Image RetrievalRetrievalSketch-Based Image Retrieval

Deferred is Better: A Framework for Multi-Granularity Deferred Interaction of Heterogeneous Features

2026-03-13 · Yi Xu, Moyu Zhang, Chaofan Fan, Jinxin Hu 외 arxiv

Click-through rate (CTR) prediction models estimates the probability of a user-item click by modeling interactions across a vast feature space. A fundamental yet often overlooked challenge is the inherent heterogeneity o…