paper-with-me

홈 › Papers

Coupling Global and Local Context for Unsupervised Aspect Extraction

2019-11-01 · IJCNLP 2019 11 · Ming Liao, Jing Li, Haisong Zhang, Lingzhi Wang, Xixin Wu, Kam-Fai Wong

Aspect words, indicating opinion targets, are essential in expressing and understanding human opinions. To identify aspects, most previous efforts focus on using sequence tagging models trained on human-annotated data. This work studies unsupervised aspect extraction and explores how words appear in global context (on sentence level) and local context (conveyed by neighboring words). We propose a novel neural model, capable of coupling global and local representation to discover aspect words. Experimental results on two benchmarks, laptop and restaurant reviews, show that our model significantly outperforms the state-of-the-art models from previous studies evaluated with varying metrics. Analysis on model output show our ability to learn meaningful and coherent aspect representations. We further investigate how words distribute in global and local context, and find that aspect and non-aspect words do exhibit different context, interpreting our superiority in unsupervised aspect extraction.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Aspect ExtractionSentence

Similar Papers 제목 키워드 기반

Decoupling Global and Local Representations via Invertible Generative Flows

2020-04-12 · ICLR 2021 1 · Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard Hovy

In this work, we propose a new generative model that is capable of automatically decoupling global and local representations of images in an entirely unsupervised setting, by embedding a generative flow in the VAE framew…

DecoderDensity EstimationImage GenerationRepresentation Learning+1

Efficiency Follows Global-Local Decoupling

2026-03-20 · Zhenyu Yang, Gensheng Pei, Tao Chen, Yichao Zhou 외 arxiv

Modern vision models must capture image-level context without sacrificing local detail while remaining computationally affordable. We revisit this tradeoff and advance a simple principle: decouple the roles of global rea…

Domain Adaptive Person Re-Identification via Coupling Optimization

2020-11-06 · Xiaobin Liu, Shiliang Zhang

Domain adaptive person Re-Identification (ReID) is challenging owing to the domain gap and shortage of annotations on target scenarios. To handle those two challenges, this paper proposes a coupling optimization method i…

Domain Adaptive Person Re-IdentificationPerson Re-IdentificationTransfer LearningUnsupervised Person Re-Identification

CoupleNet: Coupling Global Structure with Local Parts for Object Detection

2017-08-09 · ICCV 2017 10 · Yousong Zhu, Chaoyang Zhao, Jinqiao Wang, Xu Zhao 외

The region-based Convolutional Neural Network (CNN) detectors such as Faster R-CNN or R-FCN have already shown promising results for object detection by combining the region proposal subnetwork and the classification sub…

Objectobject-detectionObject DetectionPosition+1

Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context

2021-09-15 · EMNLP 2021 11 · Xinnian Liang, Shuangzhi Wu, Mu Li, Zhoujun Li

Embedding based methods are widely used for unsupervised keyphrase extraction (UKE) tasks. Generally, these methods simply calculate similarities between phrase embeddings and document embedding, which is insufficient to…

Document EmbeddingKeyphrase Extraction