Search Results for author: GuoHui Li

Found 10 papers, 5 papers with code

Intention Reasoning Network for Multi-Domain End-to-end Task-Oriented Dialogue

no code implementations EMNLP 2021 Zhiyuan Ma, Jianjun Li, Zezheng Zhang, GuoHui Li, Yongjing Cheng

Based on such a mechanism, we further propose an intention reasoning network (IR-Net), which consists of joint and multi-hop reasoning, to obtain intention-aware representations of conceptual tokens that can be used to capture the concept shifts involved in task-oriented conversations, so as to effectively identify user’s intention and generate more accurate responses.

UniTranSeR: A Unified Transformer Semantic Representation Framework for Multimodal Task-Oriented Dialog System

no code implementations ACL 2022 Zhiyuan Ma, Jianjun Li, GuoHui Li, Yongjing Cheng

Specifically, we first embed the multimodal features into a unified Transformer semantic space to prompt inter-modal interactions, and then devise a feature alignment and intention reasoning (FAIR) layer to perform cross-modal entity alignment and fine-grained key-value reasoning, so as to effectively identify user’s intention for generating more accurate responses.

Entity Alignment

GLAF: Global-to-Local Aggregation and Fission Network for Semantic Level Fact Verification

no code implementations COLING 2022 Zhiyuan Ma, Jianjun Li, GuoHui Li, Yongjing Cheng

Accurate fact verification depends on performing fine-grained reasoning over crucial entities by capturing their latent logical relations hidden in multiple evidence clues, which is generally lacking in existing fact verification models.

Fact Verification

CMAL: A Novel Cross-Modal Associative Learning Framework for Vision-Language Pre-Training

no code implementations16 Oct 2024 Zhiyuan Ma, Jianjun Li, GuoHui Li, Kaiyan Huang

With the flourishing of social media platforms, vision-language pre-training (VLP) recently has received great attention and many remarkable progresses have been achieved.

Contrastive Learning

EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning

no code implementations22 Apr 2024 Mingjie Ma, zhihuan yu, Yichao Ma, GuoHui Li

First, by emulating the cognitive process of human reasoning, an Event-Aware Pretraining auxiliary task is introduced to better activate LLM's global comprehension of intricate scenarios.

Visual Commonsense Reasoning

DualVAE: Dual Disentangled Variational AutoEncoder for Recommendation

1 code implementation10 Jan 2024 Zhiqiang Guo, GuoHui Li, Jianjun Li, Chaoyang Wang, Si Shi

To address this problem, we propose a Dual Disentangled Variational AutoEncoder (DualVAE) for collaborative recommendation, which combines disentangled representation learning with variational inference to facilitate the generation of implicit interaction data.

Collaborative Filtering Disentanglement +1

LGMRec: Local and Global Graph Learning for Multimodal Recommendation

1 code implementation27 Dec 2023 Zhiqiang Guo, Jianjun Li, GuoHui Li, Chaoyang Wang, Si Shi, Bin Ruan

The multimodal recommendation has gradually become the infrastructure of online media platforms, enabling them to provide personalized service to users through a joint modeling of user historical behaviors (e. g., purchases, clicks) and item various modalities (e. g., visual and textual).

Graph Embedding Graph Learning +2

MDGCF: Multi-Dependency Graph Collaborative Filtering with Neighborhood- and Homogeneous-level Dependencies

1 code implementation CIKM 2022 GuoHui Li, Zhiqiang Guo, Jianjun Li, Chaoyang Wang

Specifically, for neighborhood-level dependencies, we explicitly consider both popularity score and preference correlation by designing a joint neighborhood-level dependency weight, based on which we construct a neighborhood-level dependencies graph to capture higher-order interaction features.

Collaborative Filtering Graph Representation Learning +1

TopicVAE: Topic-aware Disentanglement Representation Learning for Enhanced Recommendation

1 code implementation ACM MM 2022 Zhiqiang Guo, GuoHui Li, Jianjun Li, Huaicong Chen

However, most existing methods considering content information are not well-designed to disentangle user preference features due to neglecting the diversity of user preference on different semantic topics of items, resulting in sub-optimal performance and low interpretability.

Disentanglement Recommendation Systems

A Light Heterogeneous Graph Collaborative Filtering Model using Textual Information

1 code implementation4 Oct 2020 Chaoyang Wang, Zhiqiang Guo, GuoHui Li, Jianjun Li, Peng Pan, Ke Liu

Afterward, by performing a simplified RGCN-based node information propagation on the constructed heterogeneous graph, the embeddings of users and items can be adjusted with textual knowledge, which effectively alleviates the negative effects of data sparsity.

Collaborative Filtering Recommendation Systems +1

Cannot find the paper you are looking for? You can Submit a new open access paper.