no code implementations • EMNLP 2020 • Liqiang Xiao, Lu Wang, Hao He, Yaohui Jin
Previous work is mostly based on statistical methods that estimate word-level salience, which does not consider semantics and larger context when quantifying importance.
no code implementations • COLING 2022 • Yitian Li, Jidong Tian, Wenqing Chen, Caoyun Fan, Hao He, Yaohui Jin
In this paper, we propose a systematic method to diagnose the correlations between an NLU dataset and a specific skill, and then take a fundamental reasoning skill, logical reasoning, as an example for analysis.
no code implementations • EMNLP 2021 • Jidong Tian, Yitian Li, Wenqing Chen, Liqiang Xiao, Hao He, Yaohui Jin
Recently, language models (LMs) have achieved significant performance on many NLU tasks, which has spurred widespread interest for their possible applications in the scientific and social area.
no code implementations • EMNLP 2020 • Wenqing Chen, Jidong Tian, Liqiang Xiao, Hao He, Yaohui Jin
In the field of causal inference, GS in our model is essentially a counterfactual reasoning process, trying to estimate the causal effect between tasks and utilize it to improve MTL.
1 code implementation • 25 Mar 2024 • Kaipeng Zeng, Xin Zhao, Yu Zhang, Fan Nie, Xiaokang Yang, Yaohui Jin, Yanyan Xu
Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recent years due to advancements in AI for science.
no code implementations • 24 Feb 2024 • Haoran Liao, Jidong Tian, Shaohua Hu, Hao He, Yaohui Jin
Large language models (LLMs) still grapple with complex tasks like mathematical reasoning.
2 code implementations • 24 Jan 2024 • Chang Ma, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, Lingpeng Kong, Junxian He
Evaluating large language models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications.
no code implementations • 25 Dec 2023 • Wenxuan Guo, Yanyan Xu, Yaohui Jin
Facility location problems on graphs are ubiquitous in real world and hold significant importance, yet their resolution is often impeded by NP-hardness.
1 code implementation • 14 Dec 2023 • Haoran Liao, Qinyi Du, Shaohua Hu, Hao He, Yanyan Xu, Jidong Tian, Yaohui Jin
Large language models (LLMs) face challenges in solving complex mathematical problems that require comprehensive capacities to parse the statements, associate domain knowledge, perform compound logical reasoning, and integrate the intermediate rationales.
no code implementations • 12 Dec 2023 • Caoyun Fan, Jidong Tian, Yitian Li, Hao He, Yaohui Jin
In-Context Learning (ICL) is an important paradigm for adapting Large Language Models (LLMs) to downstream tasks through a few demonstrations.
no code implementations • 9 Dec 2023 • Caoyun Fan, Jindou Chen, Yaohui Jin, Hao He
With the high alignment between the behavior of Large Language Models (LLMs) and humans, a promising research direction is to employ LLMs as substitutes for humans in game experiments, enabling social science research.
no code implementations • 18 Oct 2023 • Caoyun Fan, Jidong Tian, Yitian Li, Wenqing Chen, Hao He, Yaohui Jin
From the perspective of CoT, CoTT's two-step framework enables MLMs to implement task decomposition; CoTT's prompt tuning allows intermediate steps to be used in natural language form.
no code implementations • 11 Oct 2023 • Caoyun Fan, Wenqing Chen, Jidong Tian, Yitian Li, Hao He, Yaohui Jin
In this study, we attribute the bias to the model's misuse of label dependency, i. e., the model tends to utilize the correlation shortcut in label dependency rather than fusing text information and label dependency for prediction.
no code implementations • 10 Oct 2023 • Caoyun Fan, Wenqing Chen, Jidong Tian, Yitian Li, Hao He, Yaohui Jin
Counterfactually-Augmented Data (CAD) -- minimal editing of sentences to flip the corresponding labels -- has the potential to improve the Out-Of-Distribution (OOD) generalization capability of language models, as CAD induces language models to exploit domain-independent causal features and exclude spurious correlations.
no code implementations • 18 Feb 2023 • Caoyun Fan, Wenqing Chen, Jidong Tian, Yitian Li, Hao He, Yaohui Jin
Counterfactually-Augmented Data (CAD) has the potential to improve language models' Out-Of-Distribution (OOD) generalization capability, as CAD induces language models to exploit causal features and exclude spurious correlations.
no code implementations • 18 Feb 2023 • Caoyun Fan, Wenqing Chen, Jidong Tian, Yitian Li, Hao He, Yaohui Jin
A series of studies point out that too much gradient noise would lead to performance degradation in STL, however, in the MTL scenario, Inter-Task Gradient Noise (ITGN) is an additional source of gradient noise for each task, which can also affect the optimization process.
no code implementations • 13 Jan 2023 • Chunhui Du, Hao He, Yaohui Jin
Federated medical relation extraction enables multiple clients to train a deep network collaboratively without sharing their raw medical data.
1 code implementation • 12 Jun 2022 • Zongyuan Huang, Shengyuan Xu, Menghan Wang, Hansi Wu, Yanyan Xu, Yaohui Jin
Next location prediction is one decisive task in individual human mobility modeling and is usually viewed as sequence modeling, solved with Markov or RNN-based methods.
no code implementations • 31 Mar 2022 • Zehui Yang, Yifan Chen, Lei Luo, Runyan Yang, Lingxuan Ye, Gaofeng Cheng, Ji Xu, Yaohui Jin, Qingqing Zhang, Pengyuan Zhang, Lei Xie, Yonghong Yan
As a Mandarin speech dataset designed for dialog scenarios with high quality and rich annotations, MagicData-RAMC enriches the data diversity in the Mandarin speech community and allows extensive research on a series of speech-related tasks, including automatic speech recognition, speaker diarization, topic detection, keyword search, text-to-speech, etc.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 2 Mar 2022 • Wenxuan Guo, Junchi Yan, Hui-Ling Zhen, Xijun Li, Mingxuan Yuan, Yaohui Jin
This paper reviews the recent literature on solving the Boolean satisfiability problem (SAT), an archetypal NP-complete problem, with the help of machine learning techniques.
no code implementations • EMNLP 2021 • Liqiang Xiao, Jun Ma2, Xin Luna Dong, Pascual Martinez-Gomez, Nasser Zalmout, Wei Chen, Tong Zhao, Hao He, Yaohui Jin
Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers.
2 code implementations • 10 Sep 2021 • Zongyuan Huang, Baohua Zhang, Guoqiang Hu, Longyuan Li, Yanyan Xu, Yaohui Jin
Anomaly detection plays a crucial role in various real-world applications, including healthcare and finance systems.
no code implementations • ACL 2021 • Wenqing Chen, Jidong Tian, Yitian Li, Hao He, Yaohui Jin
The task remains challenging where deep learning models often generated linguistically fluent but logically inconsistent text.
no code implementations • 18 May 2021 • Wenqing Chen, Jidong Tian, Caoyun Fan, Hao He, Yaohui Jin
The intermediate task would help the model better understand the visual features and thus alleviate the content inconsistency problem.
no code implementations • 2 Feb 2021 • Longyuan Li, Junchi Yan, Haiyang Wang, Yaohui Jin
Our model is based on Variational Auto-Encoder (VAE), and its backbone is fulfilled by a Recurrent Neural Network to capture latent temporal structures of time series for both generative model and inference model.
no code implementations • 31 Jan 2021 • Longyuan Li, Jihai Zhang, Junchi Yan, Yaohui Jin, Yunhao Zhang, Yanjie Duan, Guangjian Tian
Time-series is ubiquitous across applications, such as transportation, finance and healthcare.
no code implementations • 31 Jan 2021 • Longyuan Li, Junchi Yan, Xiaokang Yang, Yaohui Jin
We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks and the dependency is modeled by recurrent neural nets.
no code implementations • COLING 2020 • Wenqing Chen, Jidong Tian, Liqiang Xiao, Hao He, Yaohui Jin
In this paper, we propose a semantically consistent and syntactically variational encoder-decoder framework, which uses adversarial learning to ensure the syntactic latent variable be semantic-free.
1 code implementation • 2 Jul 2019 • Honglun Zhang, Wenqing Chen, Hao He, Yaohui Jin
Facial makeup transfer is a widely-used technology that aims to transfer the makeup style from a reference face image to a non-makeup face.
no code implementations • 19 Nov 2018 • Honglun Zhang, Wenqing Chen, Jidong Tian, Yongkun Wang, Yaohui Jin
Recently unpaired multi-domain image-to-image translation has attracted great interests and obtained remarkable progress, where a label vector is utilized to indicate multi-domain information.
no code implementations • EMNLP 2018 • Liqiang Xiao, Honglun Zhang, Wenqing Chen, Yongkun Wang, Yaohui Jin
Multi-task learning has an ability to share the knowledge among related tasks and implicitly increase the training data.
no code implementations • COLING 2018 • Liqiang Xiao, Honglun Zhang, Wenqing Chen, Yongkun Wang, Yaohui Jin
Neural network based multi-task learning has achieved great success on many NLP problems, which focuses on sharing knowledge among tasks by linking some layers to enhance the performance.
no code implementations • EMNLP 2018 • Honglun Zhang, Liqiang Xiao, Wenqing Chen, Yongkun Wang, Yaohui Jin
Multi-task learning in text classification leverages implicit correlations among related tasks to extract common features and yield performance gains.
no code implementations • 10 Jul 2017 • Honglun Zhang, Liqiang Xiao, Yongkun Wang, Yaohui Jin
Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains.
no code implementations • 27 Apr 2017 • Honglun Zhang, Haiyang Wang, Xiaming Chen, Yongkun Wang, Yaohui Jin
P2P lending presents as an innovative and flexible alternative for conventional lending institutions like banks, where lenders and borrowers directly make transactions and benefit each other without complicated verifications.