Xiuyi Chen

Xiuyi Chen

Auto-generated profile, based on publicly available information

Xiuyi Chen

Baidu Inc., Beijing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2025
Verified
Conference Paper
Open access
ZSZhengliang Shi
Zhengliang Shi
SGShen Gao
Shen Gao
LYLingyong Yan
Lingyong Yan
YFYue Feng
Yue Feng
XCXiuyi Chen
Xiuyi Chen
ZRZhaochun Ren
Zhaochun Ren

15 August 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
DZDuzhen Zhang
Duzhen Zhang
FCFeilong Chen
Feilong Chen
JCJianlong Chang
Jianlong Chang
XCXiuyi Chen
Xiuyi Chen
QTQi Tian
Qi Tian
Multi-Modal Emotion Recognition in Conversations (MMERC) is an increasingly active research field that leverages multi-modal signals to understand the feelings behind each utterance. Modeling contextual interactions and multi-modal fusion lie at the heart of this field, with graph-based models recently being widely used for MMERC to capture global multi-modal contextual information. However, these models generally mix all modality representations in a single graph, and utterances in each modality are fully connected, potentially ignoring three problems: (1) the heterogeneity of the multi-modal context, (2) the redundancy of contextual information, and (3) over-smoothing of the graph networks. To address these problems, we propose a Structure Aware Multi-Graph Network (SAMGN) for MMERC. Specifically, we construct multiple modality-specific graphs to model the heterogeneity of the multi-modal context. Instead of fully connecting the utterances in each modality, we design a structure learning module that determines whether edges exist between the utterances. This module reduces redundancy by forcing each utterance to focus on the contextual ones that contribute to its emotion recognition, acting like a message propagating reducer to alleviate over-smoothing. Then, we develop the SAMGN via Dual-Stream Propagation (DSP), which contains two propagation streams, i.e., intra- and inter-modal, performed in parallel to aggregate the heterogeneous modality information from multi-graphs. DSP also contains a gating unit that adaptively integrates the co-occurrence information from the above two propagations for emotion recognition. Experiments on two popular MMERC datasets demonstrate that SAMGN achieves new State-Of-The-Art (SOTA) results.

1 January 2021
Verified
Conference Paper
Open access
PDF file
FCFeilong Chen
Feilong Chen
FMFandong Meng
Fandong Meng
XCXiuyi Chen
Xiuyi Chen
PLPeng Li
Peng Li
Jie ZhouJie Zhou
Jie Zhou
Feilong Chen, Fandong Meng, Xiuyi Chen, Peng Li, Jie Zhou. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.

21 October 2023
Verified
Conference Paper
Open access
DZDuzhen Zhang
Duzhen Zhang
HLHongliu Li
Hongliu Li
WCWei Cong
Wei Cong
RXRongtao Xu
Rongtao Xu
JDJiahua Dong
Jiahua Dong
XCXiuyi Chen
Xiuyi Chen
Incremental Named Entity Recognition (INER) involves the sequential learning of new entity types without accessing the training data of previously learned types. However, INER faces the challenge of catastrophic forgetting specific for incremental learning, further aggravated by background shift (i.e., old and future entity types are labeled as the non-entity type in the current task). To address these challenges, we propose a method called task Relation Distillation and Prototypical pseudo label (RDP) for INER. Specifically, to tackle catastrophic forgetting, we introduce a task relation distillation scheme that serves two purposes: 1) ensuring inter-task semantic consistency across different incremental learning tasks by minimizing inter-task relation distillation loss, and 2) enhancing the model's prediction confidence by minimizing intra-task self-entropy loss. Simultaneously, to mitigate background shift, we develop a prototypical pseudo label strategy that distinguishes old entity types from the current non-entity type using the old model. This strategy generates high-quality pseudo labels by measuring the distances between token embeddings and type-wise prototypes. We conducted extensive experiments on ten INER settings of three benchmark datasets (i.e., CoNLL2003, I2B2, and OntoNotes5). The results demonstrate that our method achieves significant improvements over the previous state-of-the-art methods, with an average increase of 6.08% in Micro F1 score and 7.71% in Macro F1 score.

18 July 2023
Verified
Conference Paper
Open access
DZDuzhen Zhang
Duzhen Zhang
YYYahan Yu
Yahan Yu
FCFeilong Chen
Feilong Chen
XCXiuyi Chen
Xiuyi Chen
Incremental Named Entity Recognition (INER) aims to continually train a model with new data, recognizing emerging entity types without forgetting previously learned ones. Prior INER methods have shown that Logits Distillation (LD), which involves preserving predicted logits via knowledge distillation, effectively alleviates this challenging issue. In this paper, we discover that a predicted logit can be decomposed into two terms that measure the likelihood of an input token belonging to a specific entity type or not. However, the traditional LD only preserves the sum of these two terms without considering the change in each component. To explicitly constrain each term, we propose a novel Decomposing Logits Distillation (DLD) method, enhancing the model's ability to retain old knowledge and mitigate catastrophic forgetting. Moreover, DLD is model-agnostic and easy to implement. Extensive experiments show that DLD consistently improves the performance of state-of-the-art INER methods across ten INER settings in three datasets.

17 February 2023 in Neural Networks
Verified
Journal Article
Closed access
YLYuting Lin
Yuting Lin
PJPeng Ji
Peng Ji
XCXiuyi Chen
Xiuyi Chen
ZHZhongshi He
Zhongshi He