no code implementations • Findings (ACL) 2022 • Yinan Bao, Qianwen Ma, Lingwei Wei, Wei Zhou, Songlin Hu
Besides, a clause graph is also established to model coarse-grained semantic relations between clauses.
no code implementations • COLING 2022 • Ziming Li, Yan Zhou, Weibo Zhang, Yaxin Liu, Chuanpeng Yang, Zheng Lian, Songlin Hu
Our model also achieves state-of-the-art performance on a widely used sarcasm dataset.
no code implementations • COLING 2022 • Lingwei Wei, Dou Hu, Wei Zhou, Songlin Hu
In this paper, we propose a novel dual graph-based model, Uncertainty-aware Propagation Structure Reconstruction (UPSR) for improving fake news detection.
no code implementations • COLING 2022 • Lingwei Wei, Dou Hu, Yantong Lai, Wei Zhou, Songlin Hu
Fake news’s quick propagation on social media brings severe social ramifications and economic damage.
no code implementations • 22 Mar 2024 • Xiaobin Zhang, Liangjun Zang, Qianwen Liu, Shuchong Wei, Songlin Hu
With the rise of prompt engineering, it is important to design effective prompt templates and verbalizers to extract relevant knowledge.
1 code implementation • 20 Jan 2024 • Guangyuan Ma, Xing Wu, Zijia Lin, Songlin Hu
In this study, we aim to shed light on this issue by revealing that masked auto-encoder (MAE) pre-training with enhanced decoding significantly improves the term coverage of input tokens in dense representations, compared to vanilla BERT checkpoints.
1 code implementation • 21 Dec 2023 • Dou Hu, Lingwei Wei, Yaxin Liu, Wei Zhou, Songlin Hu
It can enhance the generalization ability of pre-trained language models for better language understanding.
no code implementations • 29 Nov 2023 • Han Cao, Lingwei Wei, Mengyang Chen, Wei Zhou, Songlin Hu
However, they encounter challenges in effectively handling Chinese fact verification and the entirety of the fact-checking pipeline due to language inconsistencies and hallucinations.
no code implementations • 21 Nov 2023 • Mengyang Chen, Lingwei Wei, Han Cao, Wei Zhou, Songlin Hu
In this paper, we present a comprehensive empirical study to explore the performance of LLMs on misinformation detection tasks.
1 code implementation • 30 Oct 2023 • Zhenpeng Su, Xing Wu, Xue Bai, Zijia Lin, Hui Chen, Guiguang Ding, Wei Zhou, Songlin Hu
Experiments reveal that models incorporating the proposed MiLe Loss can gain consistent performance improvement on downstream benchmarks.
Ranked #89 on Multi-task Language Understanding on MMLU
1 code implementation • 22 Oct 2023 • Minxuan Lv, Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu
Neural network models are vulnerable to adversarial examples, and adversarial transferability further increases the risk of adversarial attacks.
1 code implementation • 6 Sep 2023 • Zhenpeng Su, Xing Wu, Wei Zhou, Guangyuan Ma, Songlin Hu
ChatGPT has gained significant interest due to its impressive performance, but people are increasingly concerned about its potential risks, particularly around the detection of AI-generated content (AIGC), which is often difficult for untrained humans to identify.
no code implementations • 16 Aug 2023 • Guangyuan Ma, Xing Wu, Peng Wang, Zijia Lin, Songlin Hu
Concretely, we leverage the capabilities of LLMs for document expansion, i. e. query generation, and effectively transfer expanded knowledge to retrievers using pre-training strategies tailored for passage retrieval.
1 code implementation • 7 Jun 2023 • Zhenpeng Su, Xing Wu, Wei Zhou, Guangyuan Ma, Songlin Hu
Dialogue response selection aims to select an appropriate response from several candidates based on a given user and system utterance history.
Ranked #1 on Conversational Response Selection on E-commerce
1 code implementation • 2 Jun 2023 • Dou Hu, Yinan Bao, Lingwei Wei, Wei Zhou, Songlin Hu
To address this, we propose a supervised adversarial contrastive learning (SACL) framework for learning class-spread structured representations in a supervised manner.
Ranked #4 on Emotion Recognition in Conversation on EmoryNLP
1 code implementation • 1 Jun 2023 • Dou Hu, Lingwei Wei, Yaxin Liu, Wei Zhou, Songlin Hu
To alleviate these, we propose a generalized multilingual system SACL-XLMR for sentiment analysis on low-resource languages.
Ranked #1 on Zero-shot Sentiment Classification on AfriSenti
1 code implementation • 25 Apr 2023 • Guangyuan Ma, Hongtao Liu, Xing Wu, Wanhui Qian, Zhepeng Lv, Qing Yang, Songlin Hu
Firstly, we introduce the user behavior masking pre-training task to recover the masked user behaviors based on their contextual behaviors.
no code implementations • 20 Apr 2023 • Guangyuan Ma, Xing Wu, Peng Wang, Songlin Hu
Siamese or fully separated dual-encoders are often adopted as basic retrieval architecture in the pre-training and fine-tuning stages for encoding queries and passages into their latent embedding spaces.
no code implementations • 5 Apr 2023 • Xing Wu, Guangyuan Ma, Peng Wang, Meng Lin, Zijia Lin, Fuzheng Zhang, Songlin Hu
As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to assist in the reconstruction of passages.
2 code implementations • 19 Dec 2022 • Xing Wu, Guangyuan Ma, Wanhui Qian, Zijia Lin, Songlin Hu
Recently, methods have been developed to improve the performance of dense passage retrieval by using context-supervised pre-training.
1 code implementation • 17 Oct 2022 • Xiaohui Song, Longtao Huang, Hui Xue, Songlin Hu
Capturing emotions within a conversation plays an essential role in modern dialogue systems.
Ranked #3 on Emotion Recognition in Conversation on EmoryNLP
1 code implementation • 13 Oct 2022 • Xing Wu, Chaochen Gao, Zijia Lin, Zhongyuan Wang, Jizhong Han, Songlin Hu
Sparse sampling is also likely to miss important frames corresponding to some text portions, resulting in textual redundancy.
2 code implementations • 8 Oct 2022 • Xing Wu, Chaochen Gao, Zijia Lin, Jizhong Han, Zhongyuan Wang, Songlin Hu
Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer.
2 code implementations • 16 Aug 2022 • Xing Wu, Guangyuan Ma, Meng Lin, Zijia Lin, Zhongyuan Wang, Songlin Hu
Dense passage retrieval aims to retrieve the relevant passages of a query from a large corpus based on dense representations (i. e., vectors) of the query and the passages.
no code implementations • 7 Jun 2022 • Yinan Bao, Qianwen Ma, Lingwei Wei, Wei Zhou, Songlin Hu
Since the dependencies between speakers are complex and dynamic, which consist of intra- and inter-speaker dependencies, the modeling of speaker-specific information is a vital role in ERC.
1 code implementation • ICASSP 2022 • Xiaohui Song, Liangjun Zang, Rong Zhang, Songlin Hu, Longtao Huang
However, the spread impact of emotions in a conversation is rarely addressed in existing researches.
Ranked #14 on Emotion Recognition in Conversation on MELD
no code implementations • 4 May 2022 • Yinan Bao, Qianwen Ma, Lingwei Wei, Wei Zhou, Songlin Hu
Besides, a clause graph is also established to model coarse-grained semantic relations between clauses.
1 code implementation • ACL 2022 • Xing Wu, Chaochen Gao, Meng Lin, Liangjun Zang, Zhongyuan Wang, Songlin Hu
Before entering the neural network, a token is generally converted to the corresponding one-hot representation, which is a discrete distribution of the vocabulary.
1 code implementation • 10 Dec 2021 • Chaochen Gao, Xing Wu, Peng Wang, Jue Wang, Liangjun Zang, Zhongyuan Wang, Songlin Hu
To tackle that, we propose an effective knowledge distillation framework for contrastive sentence embeddings, termed DistilCSE.
2 code implementations • COLING 2022 • Xing Wu, Chaochen Gao, Liangjun Zang, Jizhong Han, Zhongyuan Wang, Songlin Hu
Unsup-SimCSE takes dropout as a minimal data augmentation method, and passes the same input sentence to a pre-trained Transformer encoder (with dropout turned on) twice to obtain the two corresponding embeddings to build a positive pair.
2 code implementations • COLING 2022 • Xing Wu, Chaochen Gao, Yipeng Su, Jizhong Han, Zhongyuan Wang, Songlin Hu
Contrastive learning has been gradually applied to learn high-quality unsupervised sentence embedding.
no code implementations • ACL 2021 • Qianwen Ma, Chunyuan Yuan, Wei Zhou, Songlin Hu
Multi-label text classification is one of the fundamental tasks in natural language processing.
1 code implementation • ACL 2021 • Lingwei Wei, Dou Hu, Wei Zhou, Zhaojuan Yue, Songlin Hu
Detecting rumors on social media is a very critical task with significant implications to the economy, public health, etc.
1 code implementation • 17 Jun 2021 • Dou Hu, Lingwei Wei, Wei Zhou, Xiaoyong Huai, Zhiqi Fang, Songlin Hu
The process can strengthen the effect of relevant sequential behaviors during the preference evolution and weaken the disturbance from preference drifting.
Ranked #1 on Session-Based Recommendations on Last.FM
no code implementations • 10 May 2021 • Chunyuan Yuan, Wanhui Qian, Qianwen Ma, Wei Zhou, Songlin Hu
The rapid development of social media changes the lifestyle of people and simultaneously provides an ideal place for publishing and disseminating rumors, which severely exacerbates social panic and triggers a crisis of social trust.
1 code implementation • 29 Mar 2021 • Chen Lyu, Ruyun Wang, Hongyu Zhang, Hanwen Zhang, Songlin Hu
In recent years, many deep learning based approaches have been proposed, which can generate a sequence of code from a sequence of textual program description.
1 code implementation • COLING 2020 • Chunyuan Yuan, Qianwen Ma, Wei Zhou, Jizhong Han, Songlin Hu
In this way, we can explicitly exploit the credibility of publishers and users for early fake news detection.
no code implementations • COLING 2020 • Shangwen Lv, Fuqing Zhu, Songlin Hu
In the knowledge retrieval stage, we select relevant external event knowledge from ASER.
1 code implementation • 16 Jul 2020 • Lingwei Wei, Dou Hu, Wei Zhou, Xuehai Tang, Xiaodan Zhang, Xin Wang, Jizhong Han, Songlin Hu
Furthermore, we design a Sentiment-based Rethinking mechanism (SR) by refining the HIN with sentiment label information to learn a more sentiment-aware document representation.
no code implementations • 9 Jun 2020 • Chunyuan Yuan, Jiacheng Li, Wei Zhou, Yijun Lu, Xiaodan Zhang, Songlin Hu
For one thing, previous works cannot jointly utilize both the social network and diffusion graph for prediction, which is insufficient to model the complexity of the diffusion process and results in unsatisfactory prediction performance.
1 code implementation • 25 May 2020 • Dongjun Wei, Yaxin Liu, Fuqing Zhu, Liangjun Zang, Wei Zhou, Yijun Lu, Songlin Hu
In this paper, a novel integration method called AutoSUM is proposed for automatic feature extraction and multi-user preference simulation to overcome the drawbacks of previous methods.
no code implementations • 12 Apr 2020 • Shangwen Lv, Yuechen Wang, Daya Guo, Duyu Tang, Nan Duan, Fuqing Zhu, Ming Gong, Linjun Shou, Ryan Ma, Daxin Jiang, Guihong Cao, Ming Zhou, Songlin Hu
In this work, we introduce a learning algorithm which directly optimizes model's ability to learn text representations for effective learning of downstream tasks.
no code implementations • 22 Feb 2020 • Xiaohui Song, Liangjun Zang, Yipeng Su, Xing Wu, Jizhong Han, Songlin Hu
While several state-of-the-art approaches to dialogue state tracking (DST) have shown promising performances on several benchmarks, there is still a significant performance gap between seen slot values (i. e., values that occur in both training set and test set) and unseen ones (values that occur in training set but not in test set).
1 code implementation • 9 Nov 2019 • Qianwen Ma, Chunyuan Yuan, Wei Zhou, Jizhong Han, Songlin Hu
Based on the two types of relations, we use a graph convolutional network to learn the deep correlations between styles automatically.
1 code implementation • IJCNLP 2019 • Chunyuan Yuan, Wei Zhou, Mingming Li, Shangwen Lv, Fuqing Zhu, Jizhong Han, Songlin Hu
Existing works mainly focus on matching candidate responses with every context utterance on multiple levels of granularity, which ignore the side effect of using excessive context information.
Ranked #5 on Conversational Response Selection on RRS
1 code implementation • 10 Sep 2019 • Chunyuan Yuan, Qianwen Ma, Wei Zhou, Jizhong Han, Songlin Hu
The development of social media has revolutionized the way people communicate, share information and make decisions, but it also provides an ideal platform for publishing and spreading rumors.
no code implementations • 10 Sep 2019 • Chunyuan Yuan, Wei Zhou, Qianwen Ma, Shangwen Lv, Jizhong Han, Songlin Hu
Then, we use orthogonal decomposition and fusion attention to learn a user, review, and product representation from the review information.
1 code implementation • 9 Sep 2019 • Shangwen Lv, Daya Guo, Jingjing Xu, Duyu Tang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Songlin Hu
In this work, we propose to automatically extract evidence from heterogeneous knowledge sources, and answer questions based on the extracted evidence.
Ranked #13 on Common Sense Reasoning on CommonsenseQA
no code implementations • 5 Sep 2019 • Xing Wu, Dongjun Wei, Liangjun Zang, Jizhong Han, Songlin Hu
Automatic and human evaluation results show that TransSent can generate structured sentences with high quality, and has certain scalability in different tasks.
no code implementations • 21 Aug 2019 • Xing Wu, Tao Zhang, Liangjun Zang, Jizhong Han, Songlin Hu
So we propose a two step approach "Mask and Infill".
2 code implementations • 25 May 2019 • Dongjun Wei, Yaxin Liu, Fuqing Zhu, Liangjun Zang, Wei Zhou, Jizhong Han, Songlin Hu
Entity summarization aims at creating brief but informative descriptions of entities from knowledge graphs.
no code implementations • 28 Mar 2019 • Tao Zhang, Xing Wu, Meng Lin, Jizhong Han, Songlin Hu
Imbalanced data commonly exists in real world, espacially in sentiment-related corpus, making it difficult to train a classifier to distinguish latent sentiment in text data.
no code implementations • 21 Jan 2019 • Jinrong Guo, Wantao Liu, Wang Wang, Qu Lu, Songlin Hu, Jizhong Han, Ruixuan Li
Typically, Ultra-deep neural network(UDNN) tends to yield high-quality model, but its training process is usually resource intensive and time-consuming.
5 code implementations • 17 Dec 2018 • Xing Wu, Shangwen Lv, Liangjun Zang, Jizhong Han, Songlin Hu
BERT demonstrates that a deep bidirectional language model is more powerful than either an unidirectional language model or the shallow concatenation of a forward and backward model.