@misc{https://doi.org/10.48550/arxiv.2205.07455,
  doi = {10.48550/ARXIV.2205.07455},
  url = {https://arxiv.org/abs/2205.07455},
  author = {Zhang, Li},
  keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Reasoning about Procedures with Natural Language Processing: A Tutorial},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}
        

@misc{zhang2023openpi20,
  title={OpenPI2.0: An Improved Dataset for Entity Tracking in Texts}, 
  author={Li Zhang and Hainiu Xu and Abhinav Kommula and Niket Tandon and Chris Callison-Burch},
  year={2023},
  eprint={2305.14603},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}
          

@inproceedings{zhang-etal-2023-causal,
  title = "Causal Reasoning of Entities and Events in Procedural Texts",
  author = "Zhang, Li  and
    Xu, Hainiu  and
    Yang, Yue  and
    Zhou, Shuyan  and
    You, Weiqiu  and
    Arora, Manni  and
    Callison-burch, Chris",
  booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
  month = may,
  year = "2023",
  address = "Dubrovnik, Croatia",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2023.findings-eacl.31",
  pages = "415--431",
  abstract = "Entities and events are crucial to natural language reasoning and common in procedural texts. Existing work has focused either exclusively on entity state tracking (e.g., whether a pan is hot) or on event reasoning (e.g., whether one would burn themselves by touching the pan), while these two tasks are often causally related. We propose CREPE, the first benchmark on causal reasoning of event plausibility and entity states. We show that most language models, including GPT-3, perform close to chance at .35 F1, lagging far behind human at .87 F1. We boost model performance to .59 F1 by creatively representing events as programming languages while prompting language models pretrained on code. By injecting the causal relations between entities and events as intermediate reasoning steps in our representation, we further boost the performance to .67 F1. Our findings indicate not only the challenge that CREPE brings for language models, but also the efficacy of code-like prompting combined with chain-of-thought prompting for multihop event reasoning.",
}
          

@misc{majumder2023clin,
  title={CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization}, 
  author={Bodhisattwa Prasad Majumder and Bhavana Dalvi Mishra and Peter Jansen and Oyvind Tafjord and Niket Tandon and Li Zhang and Chris Callison-Burch and Peter Clark},
  year={2023},
  eprint={2310.10134},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}
          

@misc{lal2023size,
  title={One Size Does Not Fit All: Customizing Open-Domain Procedures}, 
  author={Yash Kumar Lal and Li Zhang and Faeze Brahman and Bodhisattwa Prasad Majumder and Peter Clark and Niket Tandon},
  year={2023},
  eprint={2311.09510},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}
          

@inproceedings{cho-etal-2022-unsupervised,
  title = "Unsupervised Entity Linking with Guided Summarization and Multiple-Choice Selection",
  author = "Cho, Young Min  and
    Zhang, Li  and
    Callison-Burch, Chris",
  booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
  month = dec,
  year = "2022",
  address = "Abu Dhabi, United Arab Emirates",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2022.emnlp-main.638",
  pages = "9394--9401",
  abstract = "Entity linking, the task of linking potentially ambiguous mentions in texts to corresponding knowledge-base entities, is an important component for language understanding. We address two challenge in entity linking: how to leverage wider contexts surrounding a mention, and how to deal with limited training data. We propose a fully unsupervised model called SumMC that first generates a guided summary of the contexts conditioning on the mention, and then casts the task to a multiple-choice problem where the model chooses an entity from a list of candidates. In addition to evaluating our model on existing datasets that focus on named entities, we create a new dataset that links noun phrases from WikiHow to Wikidata. We show that our SumMC model achieves state-of-the-art unsupervised performance on our new dataset and on exiting datasets.",
}
            

@inproceedings{zhang-etal-2020-reasoning,
  title = "Reasoning about Goals, Steps, and Temporal Ordering with {W}iki{H}ow",
  author = "Zhang, Li  and
    Lyu, Qing  and
    Callison-Burch, Chris",
  booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
  month = nov,
  year = "2020",
  address = "Online",
  publisher = "Association for Computational Linguistics",
  url = "https://www.aclweb.org/anthology/2020.emnlp-main.374",
  pages = "4630--4639",
}
          

@inproceedings{yang-etal-2021-visual,
title = "Visual Goal-Step Inference using wiki{H}ow",
author = "Yang, Yue  and
  Panagopoulou, Artemis  and
  Lyu, Qing  and
  Zhang, Li  and
  Yatskar, Mark  and
  Callison-Burch, Chris",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.165",
pages = "2167--2179",
abstract = "Understanding what sequence of steps are needed to complete a goal can help artificial intelligence systems reason about human activities. Past work in NLP has examined the task of goal-step inference for text. We introduce the visual analogue. We propose the Visual Goal-Step Inference (VGSI) task, where a model is given a textual goal and must choose which of four images represents a plausible step towards that goal. With a new dataset harvested from wikiHow consisting of 772,277 images representing human actions, we show that our task is challenging for state-of-the-art multimodal models. Moreover, the multimodal representation learned from our data can be effectively transferred to other datasets like HowTo100m, increasing the VGSI accuracy by 15 - 20{\%}. Our task will facilitate multimodal reasoning about procedural events.",
}
        

@inproceedings{zhou-etal-2022-show,
title = "Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data",
author = "Zhou, Shuyan  and
  Zhang, Li  and
  Yang, Yue  and
  Lyu, Qing  and
  Yin, Pengcheng  and
  Callison-Burch, Chris  and
  Neubig, Graham",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.214",
pages = "2998--3012",
abstract = "Procedures are inherently hierarchical. To {``}make videos{''}, one may need to {``}purchase a camera{''}, which in turn may require one to {``}set a budget{''}. While such hierarchical knowledge is critical for reasoning about complex procedures, most existing work has treated procedures as shallow structures without modeling the parent-child relation. In this work, we attempt to construct an open-domain hierarchical knowledge-base (KB) of procedures based on wikiHow, a website containing more than 110k instructional articles, each documenting the steps to carry out a complex procedure. To this end, we develop a simple and efficient method that links steps (e.g., {``}purchase a camera{''}) in an article to other articles with similar goals (e.g., {``}how to choose a camera{''}), recursively constructing the KB. Our method significantly outperforms several strong baselines according to automatic evaluation, human judgment, and application to downstream tasks such as instructional video retrieval.",
}
      

@inproceedings{lyu-etal-2021-goal,
title = "Goal-Oriented Script Construction",
author = "Lyu, Qing  and
Zhang, Li  and
Callison-Burch, Chris",
booktitle = "Proceedings of the 14th International Conference on Natural Language Generation",
month = aug,
year = "2021",
address = "Aberdeen, Scotland, UK",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.inlg-1.19",
pages = "184--200",
abstract = "The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a sequence of steps to accomplish a given goal. We pilot our task on the first multilingual script learning dataset supporting 18 languages collected from wikiHow, a website containing half a million how-to articles. For baselines, we consider both a generation-based approach using a language model and a retrieval-based approach by first retrieving the relevant steps from a large candidate pool and then ordering them. We show that our task is practical, feasible but challenging for state-of-the-art Transformer models, and that our methods can be readily deployed for various other datasets and domains with decent zero-shot performance.",
}
      

@inproceedings{zhang-etal-2020-intent,
  title = "Intent Detection with {W}iki{H}ow",
  author = "Zhang, Li  and
    Lyu, Qing  and
    Callison-Burch, Chris",
  booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
  month = dec,
  year = "2020",
  address = "Suzhou, China",
  publisher = "Association for Computational Linguistics",
  url = "https://www.aclweb.org/anthology/2020.aacl-main.35",
  pages = "328--333",
  abstract = "Modern task-oriented dialog systems need to reliably understand users{'} intents. Intent detection is even more challenging when moving to new domains or new languages, since there is little annotated data. To address this challenge, we present a suite of pretrained intent detection models which can predict a broad range of intended goals from many actions because they are trained on wikiHow, a comprehensive instructional website. Our models achieve state-of-the-art results on the Snips dataset, the Schema-Guided Dialogue dataset, and all 3 languages of the Facebook multilingual dialog datasets. Our models also demonstrate strong zero- and few-shot performance, reaching over 75{\%} accuracy using only 100 training examples in all datasets.",
}
          

@misc{hou2023choice75,
  title={Choice-75: A Dataset on Decision Branching in Script Learning}, 
  author={Zhaoyi Joey Hou and Li Zhang and Chris Callison-Burch},
  year={2023},
  eprint={2309.11737},
  archivePrefix={arXiv},
  primaryClass={cs.AI}
}
        

@Inproceedings{Pennsylvania2022,
  author = {Panagopoulou, Artemis and Arora, Manni and Zhang, Li and Cugini, Dimitri and You, Weiqiu and Yang, Yue and Zhou, Liyang and Wang, Yuxuan and Hou, Zhaoyi and Hwang, Alyssa and Martin, Lara and Shi, Sherry and Callison-Burch, Chris and Yatskar, Mark},
  title = {QuakerBot: A household dialog system powered by large language models},
  year = {2022},
  url = {https://www.amazon.science/alexa-prize/proceedings/quakerbot-a-household-dialog-system-powered-by-large-language-models},
  booktitle = {Alexa Prize TaskBot Challenge Proceedings},
  }
        

@inproceedings{zhang-etal-2023-human,
  title = "Human-in-the-loop Schema Induction",
  author = "Zhang, Tianyi  and
    Tham, Isaac  and
    Hou, Zhaoyi  and
    Ren, Jiaxuan  and
    Zhou, Leon  and
    Xu, Hainiu  and
    Zhang, Li  and
    Martin, Lara  and
    Dror, Rotem  and
    Li, Sha  and
    Ji, Heng  and
    Palmer, Martha  and
    Brown, Susan Windisch  and
    Suchocki, Reece  and
    Callison-Burch, Chris",
  booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
  month = jul,
  year = "2023",
  address = "Toronto, Canada",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2023.acl-demo.1",
  pages = "1--10",
  abstract = "Schema induction builds a graph representation explaining how events unfold in a scenario. Existing approaches have been based on information retrieval (IR) and information extraction (IE), often with limited human curation. We demonstrate a human-in-the-loop schema induction system powered by GPT-3. We first describe the different modules of our system, including prompting to generate schematic elements, manual edit of those elements, and conversion of those into a schema graph. By qualitatively comparing our system to previous ones, we show that our system not only transfers to new domains more easily than previous approaches, but also reduces efforts of human curation thanks to our interactive interface.",
}
    

  @InProceedings{gpt3drum,
    author    = {Li Zhang  and  Chris Callison-Burch},
    title     = {Language Models are Drummers: Drum Composition with Natural Language Pre-Training},
    venue = {AAAI 2023 1st workshop on Creative AI across Modalities},
    month     = {Feburary},
    year      = {2023},
    address   = {Washington, D.C., USA},
    abstract  = {Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary findings on the possibility for deep models to transfer knowledge from language to music, by finetuning large language models pre-trained on a massive text corpus on only hundreds of MIDI files of drum performances. We show that by doing so, one of the largest, state-of-the-art models (GPT3) is capable of generating reasonable drum grooves, while models that are not pre-trained (Transformer) shows no such ability beyond naive repetition. Evaluating generated music is a challenging task, more so is evaluating drum grooves with little precedence in literature. Hence, we propose a tailored structural evaluation method and analyze drum grooves produced by GPT3 compared to those played by human professionals, exposing the strengths and weaknesses of such generation by language-to-music transfer. Our findings suggest that language-to-music transfer learning with large language models is viable and promising.},
    url       = {https://arxiv.org/abs/2301.01162},
    software  = {https://github.com/zharry29/drums-with-llm},
  }