Welcome!

About Us

The UC Santa Barbara NLP group studies the theoretical foundation and practical algorithms for language technologies. We tackle challenging learning and reasoning problems under uncertainty, and pursue answers via studies of machine learning, deep learning, and interdisciplinary data science.

Broadly, we are interested in designing scalable inference and learning algorithms to analyze massive datasets with complex structures. In particular, our lab concentrates in the areas of information extraction, computational social science, knowledge graph, learning to reason, dialogue systems, language & vision, summarization, statistical relational learning, reinforcement learning, structure learning, and deep learning.

News

[08/20/2022] We are excited to share the news that 38 papers from UCSB NLP group were accepted to the ECCV, ICML, NAACL, CVPR, ACL, ICLR, AAAI 2022 conferences! Preprints will be released soon.

[03/10/2021] We are excited to share the news that 8 papers from UCSB NLP group were accepted to the EACL, NAACL, and ICLR 2021 conferences! Preprints will be released soon.

[09/21/2020] We are excited to share the news that 8 papers from UCSB NLP group were accepted to the EMNLP 2020 conference! Preprints will be released soon.

[12/26/2019] Congratulations Wenhu Chen and Wenhan Xiong for their accepted ICLR 2020 papers!

[06/24/2019] Congratultions to Xin Wang on winning the CVPR 2019 Best Student Paper Award.

[05/25/2019] The NLP Group has received a new Google gift to work on language and vision research. Thanks Google!

[05/15/2019] We are excited to share the news that 7 long papers and 1 short paper from UCSB NLP group were accepted to the ACL 2019 conference! Preprints will be released soon.

[03/15/2019] The NLP lab has received a Google Faculty Research Award. Thanks Google!

[03/05/2019] Congrats Xin for his accepted CVPR 2019 oral paper on vision-language navigation with Microsoft Research collaborators!

[02/22/2019] We are excited to share the news that 6 papers from UCSB NLP group were accepted to the NAACL-HLT 2019 conference! Preprints will be released soon.

[11/06/2018] The NLP lab has received a Tencent AI Lab Rhino-Bird Gift Fund. Thanks Tencent!

[11/06/2018] The NLP lab has received two faculty research grants from Intel AI. Thanks Intel!

[11/01/2018] We are excited to share the news that 2 papers from UCSB NLP group were accepted to the AAAI 2019 conference! Preprints will be released soon.

[08/27/2018] The NLP lab has received a new IBM Faculty Award (2018). Thanks IBM!

[08/24/2018] Prof. William Wang received prestigious 2018 DARPA Young Faculty Award!

[08/10/2018] We are excited to share the news that 4 long papers from UCSB NLP group were accepted to the EMNLP 2018 conference! Preprints will be released soon.

[07/03/2018] Our paper "Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation" was accepted to ECCV 2018. Congrats Xin, Wenhan, and Hongmin!

[06/24/2018] The NLP lab has received an Amazon AWS Grant for Research. Thanks AWS!

[05/24/2018] The NLP lab has received a Facebook Research Award to work on low-resource machine translation and comparable corpora mining. Thanks Facebook!

[04/20/2018] We are excited to share the news that 5 long papers from UCSB NLP group were accepted to the ACL 2018 conference! Preprints will be released soon.

[04/16/2018] Our paper "Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents" was accepted to IJCAI-ECAI 2018. Congrats Wenhan! Preprints will be released soon.

[03/21/2018] Our paper "Hate Lingo: A Target-based Linguistic Analysis of Hate Speech in Social Media" was accepted to ICWSM 2018. Congrats Mai and Vivek! Preprints will be released soon.

[03/17/2018] The NLP lab has received an Adobe Research Award for language and vision research. Thanks Adobe!

[03/03/2018] The Brookings Institution quoted our ACL 2017 paper on automated fake news detection [LINK].

[02/28/2018] We have two short papers accepted to NAACL-HLT 2018 conference! Preprints will be released soon.

[02/26/2018] We are co-organizing SoCal NLP Symposium with Prof. Sameer Singh. Welcome to join us this April! Check the details [here].

[02/18/2018] Our paper "Video Captioning via Hierarchical Reinforcement Learning" was accepted to CVPR 2018. Congrats Xin and Wenhu! [PDF]

[02/14/2018] We are excited to share the news that 4 long papers from UCSB NLP group were accepted to the NAACL-HLT 2018 conference! Preprints will be released soon.

[02/10/2018] Two tutorials accepted at major NLP conferences. Together with Jiwei Li (Stanford/Shannon.ai) and Xiaodong He (MSR), Prof. William Wang will present a tutorial on "Deep Reinforcement Learning for NLP" at ACL 2018. Together with Xiang Ren (USC) and Nanyun Peng (USC/ISI), Prof. William Wang will present a tutorial on Scalable Construction and Reasoning of Massive Knowledge Bases at NAACL-HLT 2018.

[12/18/2017] Congrats NLP Lab's undergraduate researcher Ke Ni for being named the honorable mention for the Computing Research Association's (CRA) Outstanding Undergraduate Researcher Award 2018!

[11/22/2017] The NLP lab has received an unrestricted gift from Bytedance. Thanks Toutiao!

[11/06/2017] The NLP lab has received a Tencent AI Lab Rhino-Bird Award. Thanks Tencent!

[11/06/2017] Prof. William Wang recently discussed challenges on dialogue research with Wired [LINK] [PDF].

Recent Papers

• INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback Wenda Xu, Danqing Wang, Liangming Pan, Zhenqiao Song, Markus Freitag, William Yang Wang, Lei Li EMNLP 2023.
• MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models Deepak Nathani, David Wang, Liangming Pan, William Yang Wang EMNLP 2023.
• EDIS: Entity-Driven Image Search over Multimodal Web Content Siqi Liu, Weixi Feng, Tsu-Jui Fu, Wenhu Chen, William Yang Wang EMNLP 2023.
• Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought Vaishnavi Himakunthala, Andy Ouyang, Daniel Philip Rose, Ryan He, Alex Mei, Yujie Lu, Chinmay Sonar, Michael Saxon, William Yang Wang EMNLP 2023.
• Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation Wanrong Zhu, Xinyi Wang, Yujie Lu, Tsu-Jui Fu, Xin Eric Wang, Miguel Eckstein, William Yang Wang EMNLP 2023, Short Paper.
• Text-guided 3D Human Generation from 2D Collections Tsu-Jui Fu, Wenhan Xiong, Yixin Nie, Jingyu Liu, Barlas Oguz, William Yang Wang EMNLP 2023 Findings
• Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning Liangming Pan, Alon Albalak, Xinyi Wang, William Yang Wang EMNLP 2023 Findings
• Knowledge-Selective Pretraining for Attribute Value Extraction Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Yang Wang, Xiaodan Zhu EMNLP 2023 Findings
• ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models Alex Mei, Sharon Levy, William Yang Wang EMNLP 2023 Findings
• On the Risk of Misinformation Pollution with Large Language Models Yikang Pan, Liangming Pan, Wenhu Chen, Preslav Nakov, Min-Yen Kan, William Yang Wang EMNLP 2023 Findings
• Empowering Psychotherapy with Large Language Model: Cognitive Distortion Detection through Diagnosis of Thought Prompting Zhiyu Chen, Yujie Lu, William Yang Wang EMNLP 2023 Findings
• LayoutGPT: Compositional Visual Planning and Generation with Large Language Models Weixi Feng*, Wanrong Zhu*, Tsu-Jui Fu, Varun Jampani, Arjun Reddy Akula, Xuehai He, S Basu, Xin Eric Wang, William Yang Wang NeurIPS 2023.
• Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data Alon Albalak, Colin Raffel, William Yang Wang NeurIPS 2023.
• Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning Xinyi Wang, Wanrong Zhu, Michael Saxon, Mark Steyvers, William Yang Wang NeurIPS 2023.
• LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation Yujie Lu, Xianjun Yang, Xiujun Li, Xin Eric Wang, William Yang Wang NeurIPS 2023.
• ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers Kexun Zhang, Danqing Wang, Jingtao Xia, William Yang Wang, Lei Li NeurIPS 2023.
• Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning Zih-Yun Chiu, Yi-Lin Tuan, William Yang Wang, Michael C. Yip NeurIPS 2023.
• Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text Wanrong Zhu*, Jack Hessel*, Anas Awadalla, Samir Yitzhak Gadre, Jesse Dodge, Alex Fang, Youngjae Yu, Ludwig Schmidt, William Yang Wang, Yejin Choi NeurIPS D&B 2023.
• Pre-trained Language Models can be Fully Zero-Shot Learners Xuandong Zhao, Siqi Ouyang, Zhiguo Yu, Ming Wu and Lei Li ACL 2023, Long Paper.
• Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge Jiangjie Chen, Wei Shi, Ziquan Fu, Sijie Cheng, Lei Li and Yanghua Xiao ACL 2023, Long Paper.
• WACO: Word-Aligned Contrastive Learning for Speech Translation Siqi Ouyang, Rong Ye and Lei Li ACL 2023, Long Paper.
• Multilingual Conceptual Coverage in Text-to-Image Models Michael Saxon and William Yang Wang ACL 2023, Long Paper.
• Retrieval Augmented Pretraining for Text Generation Evaluation Wenda Xu, Xian Qian, Mingxuan Wang, Lei Li, and William Yang Wang ACL 2023, Long Paper.
• Fact-Checking Complex Claims with Program-Guided Reasoning Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, and Preslav Nakov ACL 2023, Long Paper.
• Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation Fei Yuan, Yinquan Lu, Wenhao Zhu, Lingpeng Kong, Lei Li, Yu Qiao and Jingjing Xu Findings of ACL 2023, Long Paper.
• CausalDialogue: Modeling Utterance-level Causality in Conversations Yi-Lin Tuan, Alon Albalak, Wenda Xu, Michael Saxon, Connor F. Pryor, Lise Getoor, and William Yang Wang Findings of ACL 2023, Long Paper.
• Foveate, Attribute, and Rationalize: Towards Safe and Trustworthy AI Alex Mei, Sharon Levy, and William Yang Wang Findings of ACL 2023, Long Paper.
• Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models Guanhua Zhang, Jiabao Ji, Yang Zhang, Mo Yu, Tommi Jaakkola, Shiyu Chang ICML 2023.
• PromptBoosting: Black-Box Text Classification with Ten Forward Passes Bairu Hou, Joe O'Connor, Jacob Andreas, Shiyu Chang, Yang Zhang ICML 2023.
• Importance Weighted Variational Bayes for Protein Sequence Design Zhenqiao Song, Lei Li ICML 2023.
• Protecting Language Generation Models via Invisible Watermarking Xuandong Zhao, Yu-Xiang Wang, Lei Li ICML 2023.
• ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval Kexun Zhang, Xianjun Yang, William Yang Wang, and Lei Li ICML 2023.
• Offline Reinforcement Learning with Closed-Form Policy Improvement Operators Jiachen Li, Eddie Zhang, Ming Yin, Qinxun Bai, Yu-Xiang Wang, and William Yang Wang ICML 2023.
• WikiWhy: Answering and Explaining Cause-and-Effect Questions Matthew Ho, Aditya Sharma, Justin Chang, Michael Saxon, Sharon Levy, Yujie Lu, William Yang Wang ICLR 2023, Oral Paper: Top 5% out of all 4019 submissions
• Neuro-Symbolic Procedural Planning with Commonsense Prompting Yujie Lu, Weixi Feng, Wanrong Zhu, Wenda Xu, Xin Eric Wang, Miguel Eckstein, William Yang Wang ICLR 2023, Spotlight Paper.
• Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis Weixi Feng, Xuehai He, Tsu-Jui Fu, Varun Jampani, Arjun Reddy Akula, Pradyumna Narayana, Sugato Basu, Xin Eric Wang, William Yang Wang ICLR 2023.
• Causal Balancing for Domain Generalization Xinyi Wang, Michael Saxon, Jiachen Li, Hongyang Zhang, Kun Zhang, William Yang Wang ICLR 2023.
• TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization Bairu Hou, Jinghan Jia, Yihua Zhang, Guanhua Zhang, Yang Zhang, Sijia Liu, and Shiyu Chang ICLR 2023.
• PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers Michael S. Saxon, Xinyi Wang, Wenda Xu and William Yang Wang EACL 2023.
• Visualize Before You Write: Imagination-Guided Open-Ended Text Generation Wanrong Zhu, An Yan, Yujie Lu, Wenda Xu, Xin Eric Wang, Miguel Eckstein and William Yang Wang Findings of EACL 2023.
• ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation Wanrong Zhu, Xin Eric Wang, An Yan, Miguel Eckstein and William Yang Wang Findings of EACL 2023).
• Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models Qiucheng Wu, Yujian Liu, Handong Zhao, Ajinkya Kale, Trung Bui, Tong Yu, Zhe Lin, Yang Zhang, Shiyu Chang CVPR 2023.
• Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation Tsu-Jui Fu, Licheng Yu, Ning Zhang, Cheng-Yang Fu, Jong-Chyi Su, William Yang Wang, Sean Bell CVPR 2023.
• An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling Tsu-Jui Fu, Linjie Li, Zhe Gan, Kevin Lin, William Yang Wang, Lijuan Wang, Zicheng Liu CVPR 2023.
• Converge to the Truth: Factual Error Correction via Iterative Constrained Editing Jiangjie Chen, Rui Xu, Wenxuan Zeng, Changzhi Sun, Lei Li, and Yanghua Xiao. AAAI 2023.