1 code implementation • COLING 2022 • Fei Zhao, Zhen Wu, Siyu Long, Xinyu Dai, ShuJian Huang, Jiajun Chen
Target-oriented multimodal sentiment classification (TMSC) is a new subtask of aspect-based sentiment analysis, which aims to determine the sentiment polarity of the opinion target mentioned in a (sentence, image) pair.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
no code implementations • AACL (NLP-TEA) 2020 • Yongchang Cao, Liang He, Robert Ridley, Xinyu Dai
This paper describes our proposed model for the Chinese Grammatical Error Diagnosis (CGED) task in NLPTEA2020.
no code implementations • EMNLP 2021 • Ran Wang, Xi’ao Su, Siyu Long, Xinyu Dai, ShuJian Huang, Jiajun Chen
However, the simple extension of meta-learning approaches to multi-label classification is sub-optimal for LMTC tasks due to long-tailed label distribution and coexisting of few- and zero-shot scenarios.
no code implementations • ACL 2022 • Xi’ao Su, Ran Wang, Xinyu Dai
Multi-Label Text Classification (MLTC) is a fundamental and challenging task in natural language processing.
1 code implementation • COLING 2022 • Yawen Ouyang, Zhen Wu, Xinyu Dai, ShuJian Huang, Jiajun Chen
In this paper, we propose a more desirable task, multi-label unknown intent detection, to detect whether the utterance contains the unknown intent, in which each utterance may contain multiple intents.
1 code implementation • ACL 2022 • Yu Bao, Hao Zhou, ShuJian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei LI
Recently, parallel text generation has received widespread attention due to its success in generation efficiency.
1 code implementation • 24 Mar 2024 • Taotian Pang, Xingyu Lou, Fei Zhao, Zhen Wu, Kuiyao Dong, Qiuying Peng, Yue Qi, Xinyu Dai
Specifically, we build \textit{user preference representations} and \textit{attribute fusion representations} upon the attribute information in knowledge graphs, which are utilized to enhance \textit{collaborative filtering} (CF) based user and item representations, respectively.
no code implementations • 19 Mar 2024 • Yuan Gao, Yiheng Zhu, Yuanbin Cao, Yinzhi Zhou, Zhen Wu, Yujie Chen, Shenglan Wu, Haoyuan Hu, Xinyu Dai
To alleviate this issue, we propose the Discriminate->Re-Compose->Re- Solve->Re-Decompose (Dr3) mechanism.
no code implementations • 5 Mar 2024 • Kangjie Zheng, Siyu Long, Tianyu Lu, Junwei Yang, Xinyu Dai, Ming Zhang, Zaiqing Nie, Wei-Ying Ma, Hao Zhou
Protein language models have demonstrated significant potential in the field of protein engineering.
no code implementations • 15 Feb 2024 • Shangyu Xing, Fei Zhao, Zhen Wu, Tuo An, WeiHao Chen, Chunhui Li, Jianbing Zhang, Xinyu Dai
Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon known as object hallucination.
1 code implementation • 12 Jan 2024 • Sen yang, ShuJian Huang, Xinyu Dai, Jiajun Chen
One way to speed them up is speculative decoding, which generates candidate segments (a sequence of tokens) from a fast draft model that is then verified in parallel by the target model.
no code implementations • 27 Dec 2023 • Yongchang Cao, Liang He, Zhen Wu, Xinyu Dai
Meanwhile, to incorporate implicit hierarchical linguistic knowledge within the encoder, we propose a novel form of n-gram-based layerwise self-attention to generate a multilayer representation.
no code implementations • 12 Dec 2023 • Nantao Zheng, Siyu Long, Xinyu Dai
Specifically, to fully utilize entity information, we employ an encoder to encode semantics of this information, leading to high-quality entity representations.
no code implementations • 17 Nov 2023 • Ting Xu, Zhen Wu, Huiyun Yang, Xinyu Dai
We propose to explore ASTE in the cross-domain setting, which transfers knowledge from a resource-rich source domain to a resource-poor target domain, thereby alleviating the reliance on labeled data in the target domain.
1 code implementation • 23 Oct 2023 • Fei Zhao, Chunhui Li, Zhen Wu, Yawen Ouyang, Jianbing Zhang, Xinyu Dai
Therefore, in this work, we focus on whether the negative impact of noisy images can be reduced without modifying the data.
1 code implementation • 9 Oct 2023 • Shangyu Xing, Fei Zhao, Zhen Wu, Chunhui Li, Jianbing Zhang, Xinyu Dai
Multimodal Entity Linking (MEL) is a task that aims to link ambiguous mentions within multimodal contexts to referential entities in a multimodal knowledge base.
no code implementations • 8 Oct 2023 • Zihan Yu, Liang He, Zhen Wu, Xinyu Dai, Jiajun Chen
Chain-of-Thought (CoT), a step-wise and coherent reasoning chain, shows its impressive strength when used as a prompting strategy for large language models (LLM).
1 code implementation • 30 Sep 2023 • Fei Zhao, Taotian Pang, Zhen Wu, Zheng Ma, ShuJian Huang, Xinyu Dai
Previous studies have revealed that ICL is sensitive to the selection and the ordering of demonstrations.
1 code implementation • 2 Aug 2023 • Kanzhi Cheng, Zheng Ma, Shi Zong, Jianbing Zhang, Xinyu Dai, Jiajun Chen
Generating visually grounded image captions with specific linguistic styles using unpaired stylistic corpora is a challenging task, especially since we expect stylized captions with a wide variety of stylistic patterns.
1 code implementation • 27 May 2023 • Ting Xu, Huiyun Yang, Zhen Wu, Jiaze Chen, Fei Zhao, Xinyu Dai
In this paper, we introduce a new dataset, named DMASTE, which is manually annotated to better fit real-world scenarios by providing more diverse and realistic reviews for the task.
no code implementations • 8 Apr 2023 • Zhen Wu, Yizhe Lu, Xinyu Dai
Multimodal speech emotion recognition aims to detect speakers' emotions from audio and text.
no code implementations • 22 Nov 2022 • Xuan Wu, Xinhao Zhu, Yizheng Zhao, Xinyu Dai
DF-$\mathcal{ALC}$ unifies the description logic $\mathcal{ALC}$ and neural models for symbol grounding; in particular, it infuses an $\mathcal{ALC}$ knowledge base into neural models through differentiable concept and role embeddings.
1 code implementation • 22 Oct 2022 • Bin Wang, Jiangzhou Ju, Yang Fan, Xinyu Dai, ShuJian Huang, Jiajun Chen
As one of the challenging NLP tasks, designing math word problem (MWP) solvers has attracted increasing research attention for the past few years.
no code implementations • 18 Oct 2022 • Zheng Ma, Shi Zong, Mianzhi Pan, Jianbing Zhang, ShuJian Huang, Xinyu Dai, Jiajun Chen
In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks.
1 code implementation • 9 Oct 2022 • Fei Zhao, Yuchen Shen, Zhen Wu, Xinyu Dai
Multi-Label Few-Shot Aspect Category Detection (FS-ACD) is a new sub-task of aspect-based sentiment analysis, which aims to detect aspect categories accurately with limited training instances.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • Findings (NAACL) 2022 • Ming Fang, Shi Zong, Jing Li, Xinyu Dai, ShuJian Huang, Jiajun Chen
Furthermore, we conduct a comprehensive linguistic analysis around complaints, including the connections between complaints and sentiment, and a cross-lingual comparison for complaints expressions used by Chinese and English speakers.
1 code implementation • 5 Apr 2022 • Yu Bao, Hao Zhou, ShuJian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei LI
Recently, parallel text generation has received widespread attention due to its success in generation efficiency.
no code implementations • ACL 2021 • Jiahuan Li, Yutong Shen, ShuJian Huang, Xinyu Dai, Jiajun Chen
Subword segmentation algorithms have been a \textit{de facto} choice when building neural machine translation systems.
2 code implementations • Findings (ACL) 2021 • Yawen Ouyang, Jiasheng Ye, Yu Chen, Xinyu Dai, ShuJian Huang, Jiajun Chen
Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set.
no code implementations • NAACL 2021 • Zhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie, Tao Qin, Xinyu Dai, Tie-Yan Liu
Therefore, in this paper, we integrate different dropout techniques into the training of Transformer models.
Ranked #4 on Machine Translation on IWSLT2014 English-German
1 code implementation • NAACL 2021 • Yu Bao, ShuJian Huang, Tong Xiao, Dongqi Wang, Xinyu Dai, Jiajun Chen
Non-autoregressive Transformer is a promising text generation model.
Ranked #7 on Machine Translation on WMT2014 German-English
1 code implementation • 16 Mar 2021 • Bairan Fu, Wenming Zhang, GuangNeng Hu, Xinyu Dai, ShuJian Huang, Jiajun Chen
Specifically, we first proposed a novel graph neural network to model the social relation and collaborative relation, and on top of high-order relations, a dual side deep context-aware modulation is introduced to capture the friends' information and item attraction.
no code implementations • 1 Nov 2020 • Chengcan Ying, Zhen Wu, Xinyu Dai, ShuJian Huang, Jiajun Chen
In this paper, we propose a novel joint model, Opinion Transmission Network (OTN), to exploit the potential bridge between ALSC and AOWE to achieve the goal of facilitating them simultaneously.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3
no code implementations • 1 Nov 2020 • Zhen Wu, Chengcan Ying, Xinyu Dai, ShuJian Huang, Jiajun Chen
To facilitate the research of ABSA, NLPCC 2020 Shared Task 2 releases a new large-scale Multi-Aspect Multi-Sentiment (MAMS) dataset.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • COLING 2020 • Fei Zhao, Zhen Wu, Xinyu Dai
In neural network-based methods for ASC, most works employ the attention mechanism to capture the corresponding sentiment words of the opinion target, then aggregate them as evidence to infer the sentiment of the target.
3 code implementations • Findings of the Association for Computational Linguistics 2020 • Zhen Wu, Chengcan Ying, Fei Zhao, Zhifang Fan, Xinyu Dai, Rui Xia
To validate the feasibility and compatibility of GTS, we implement three different GTS models respectively based on CNN, BiLSTM, and BERT, and conduct experiments on the aspect-oriented opinion pair extraction and opinion triplet extraction datasets.
Ranked #1 on Aspect Sentiment Triplet Extraction on Res14
Aspect-Sentiment-Opinion Triplet Extraction Aspect Sentiment Triplet Extraction