Search Results for author: Xinyu Dai

Found 40 papers, 21 papers with code

Towards Multi-label Unknown Intent Detection

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.

Intent Detection

Integrating BERT and Score-based Feature Gates for Chinese Grammatical Error Diagnosis

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.

GLAT: Glancing at Latent Variables for Parallel Text Generation

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.

Text Generation

Learning from Adjective-Noun Pairs: A Knowledge-enhanced Framework for Target-Oriented Multimodal Sentiment Classification

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

Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text Classification

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.

Meta-Learning Multi-Label Classification +3

AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability

no code implementations23 May 2024 Fei Zhao, Taotian Pang, Chunhui Li, Zhen Wu, Junjie Guo, Shangyu Xing, Xinyu Dai

In the pre-training stage, instead of treating all image-text pairs equally, we assign different levels of alignment capabilities to different image-text pairs.

Language Modelling Large Language Model

The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning

1 code implementation15 Apr 2024 Yaohui Li, Qifeng Zhou, Haoxing Chen, Jianbing Zhang, Xinyu Dai, Hao Zhou

Few-shot learning aims to further enhance the transfer capability of CLIP by giving few images in each class, aka 'few shots'.

Few-Shot Learning Zero-Shot Learning

Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation

1 code implementation29 Mar 2024 Fangxu Yu, Junjie Guo, Zhen Wu, Xinyu Dai

To achieve this, we utilize label encodings as anchors to guide the learning of utterance representations and design an auxiliary loss to ensure the effective separation of anchors for similar emotions.

Contrastive Learning Emotion Recognition in Conversation

Knowledge-aware Dual-side Attribute-enhanced Recommendation

1 code implementation24 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.

Attribute Collaborative Filtering +3

EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models

no code implementations15 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.

Hallucination

Multi-Candidate Speculative Decoding

1 code implementation12 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.

Make BERT-based Chinese Spelling Check Model Enhanced by Layerwise Attention and Gaussian Mixture Model

no code implementations27 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.

Part-Of-Speech Tagging POS +1

BED: Bi-Encoder-Decoder Model for Canonical Relation Extraction

no code implementations12 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.

Decoder Relation +1

FOAL: Fine-grained Contrastive Learning for Cross-domain Aspect Sentiment Triplet Extraction

no code implementations17 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.

Aspect Sentiment Triplet Extraction Contrastive Learning

DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking

1 code implementation9 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.

Entity Linking Relation

Towards Better Chain-of-Thought Prompting Strategies: A Survey

no code implementations8 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).

Dynamic Demonstrations Controller for In-Context Learning

1 code implementation30 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.

In-Context Learning Language Modelling +1

ADS-Cap: A Framework for Accurate and Diverse Stylized Captioning with Unpaired Stylistic Corpora

1 code implementation2 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.

Contrastive Learning Image Captioning

Measuring Your ASTE Models in The Wild: A Diversified Multi-domain Dataset For Aspect Sentiment Triplet Extraction

1 code implementation27 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.

Aspect Sentiment Triplet Extraction

Differentiable Fuzzy $\mathcal{ALC}$: A Neural-Symbolic Representation Language for Symbol Grounding

no code implementations22 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.

Structure-Unified M-Tree Coding Solver for MathWord Problem

1 code implementation22 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.

Math

Probing Cross-modal Semantics Alignment Capability from the Textual Perspective

no code implementations18 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.

Image Captioning Sentence

Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect Category Detection

1 code implementation9 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

Analyzing the Intensity of Complaints on Social Media

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.

$\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation

1 code implementation5 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.

Text Generation

Energy-based Unknown Intent Detection with Data Manipulation

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.

Intent Detection

Dual Side Deep Context-aware Modulation for Social Recommendation

1 code implementation16 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.

Relation

Opinion Transmission Network for Jointly Improving Aspect-oriented Opinion Words Extraction and Sentiment Classification

no code implementations1 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

Attention Transfer Network for Aspect-level Sentiment Classification

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.

Classification General Classification +3

Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction

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.

Aspect-Sentiment-Opinion Triplet Extraction Aspect Sentiment Triplet Extraction

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