李响 Xiang Lorraine Li

I'm a young investigator work with the AI2 Mosaic team. I defended my PhD at UMass Amherst working in IESL with my advisor Andrew McCallum in August 2022. I received my B.S. from East China Normal Univerisity in Shanghai, and completed a M.S. from the Univerisity of Chicago, during when I spend some time at TTIC working with Kevin Gimpel. My pronouns are she/her.

Research Interest: My research is at the intersection of natural language processing, commonsense reasoning, knowledge representation, and machine learning. More specifically, I'm interested in designing probabilistic models and evaluation methods for implicit commonsense knowledge in language.

Industry Experience: During the summer of 2017 and 2018, I worked at Google Mountain View on knowledge graphs, focusing on hierarchical relationships. I spent the summer of 2019 working with the Bloomberg Data Science Team on generating test cases for programs with seq2seq models. In 2020, I finished a remote internship at Meta AI Research, where I focused on multi-hop question answering. Furthermore, I had the opportunity to work remotely with the DeepMind Language Team in 2021, trying to understand commonsense in large language models.

Publications

• A Systematic Investigation of Commonsense Knowledge in Large Language Models
  Xiang Lorraine Li, Adhiguna Kuncoro, Jordan Hoffmann, Cyprien de Masson d'Autume, Phil Blunsom, Aida Nematzadeh.
  The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP). Abu Dhabi, the United Arab Emirates. December 2022.
  [pre-print]
• Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings。
  Shib Sankar Dasgupta∗, Michael Boratko∗, Siddhartha Mishra, Shriya Atmakuri, Dhruvesh Patel, Xiang Lorraine Li, Andrew McCallum (*Equal Contribution)
  Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland. May, 2022.
• Box-To-Box Transformations for Modeling Joint Hierarchies.
  Shib Sankar Dasgupta, Xiang Lorraine Li, Michael Boratko, Dongxu Zhang, Andrew McCallum.
  The Sixth Workshop on Representation Learning for NLP at ACL (Rep4NLP@ACL 2021) Virtual. August, 2021.
  
• Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning.
  Xuelu Chen*, Michael Boratko*, Muhao Chen, Shib Sankar Dasgupta, Xiang Lorraine Li, Andrew McCallum. (*Equal Contribution)
  2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021) Virtual. June, 2021.
  
• Looking Beyond Short-Premise Natural Language Inference for Downstream Tasks.
  Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Lorraine Li, Pavan Kapanipathi, Kartik Talamadupula.
  2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021) Virtual. June, 2021.
  
• Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval.
  Wenhan Xiong*, Xiang Lorraine Li*, Srini Iyer, Jingfei Du, Patrick Lewis, William Yang Wang, Yashar Mehdad, Wen-tau Yih, Sebastian Riedel, Douwe Kiela, Barlas Oğuz. (*Equal Contribution)
  Ninth International Conference on Learning Representations (ICLR). Virtual. May, 2021. [code]
• Improving Local Identifiability in Probabilistic Box Embeddings.
  Shib Sankar Dasgupta*, Michael Boratko*, Dongxu Zhang, Luke Vilnis, Xiang Lorraine Li , Andrew McCallum. (*Equal Contribution)
  Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS). Virtual. Dec, 2020.
  [code]
• Reading Comprehension as Natural Language Inference: A Semantic Analysis.
  Anshuman Mishra*, Dhruvesh Patel*, Aparna Vijayakumar*, Xiang Lorraine Li, Pavan Kapanipathi, Kartik Talamadupula. (*Equal Contribution)
  The 9th Joint Conference on Lexical and Computational Semantics (*SEM) Virtual. December, 2020.
  
• ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning.
  Michael Boratko*, Xiang Lorraine Li*, Tim O'Gorman*, Rajarshi Das*, Dan Le, Andrew McCallum. (*Equal Contribution)
  The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Virtual. November 2020.
  [data] [project page] [slides]
• Representing joint hierarchies with box embeddings.
  Dhruvesh Patel*, Shib Sankar Dasgupta*, Michael Boratko, Xiang Li, Luke Vilnis, Andrew McCallum. (*Equal Contribution)
  Automated Knowledge Base Construction (AKBC). Virtual. May 2020.
  [code] [video]
• Smoothing the geometry of probabilistic box embeddings. (Oral Presentation 1.5%)
  Xiang Li*, Luke Vilnis*, Dongxu Zhang, Michael Boratko, Andrew McCallum. (*Equal Contribution)
  International Conference on Learning Representations. (ICLR) New Orleans, US. May 2019.
  [code] [video] [slides]
• Probabilistic embedding of knowledge graphs with box lattice measures.
  Luke Vilnis*, Xiang Li*, Shikhar Murty, Andrew McCallum. (*Equal Contribution)
  Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL). Melbourne, Australia. July 2018.
  [poster] [code] [bibtex]
• Improved representation learning for predicting commonsense ontologies.
  Xiang Li, Luke Vilnis, Andrew McCallum.
  Workshop of the International Conference on Machine Learning (ICML WS). Sydney, Australia. August 2017.
  
• Commonsense knowledge base completion.
  Xiang Li, Aynaz Taheri, Lifu Tu, Kevin Gimpel.
  Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany. August 2016.
  [code] [bibtex] [project page]
• Interactive provenance summaries for reproducible science..
  Xiang Li, Xiaoyang Xu, Tanu Malik.
  2016 IEEE 12th International Conference on e-Science (e-Science). Baltimore, MD, October 2016.
  

---

Pre-prints

• Faith and Fate: Limits of Transformers on Compositionality.
  Nouha Dziri*, Ximing Lu*, Melanie Sclar*, Xiang Lorraine Li†, Liwei Jiang†, Bill Yuchen Lin, Peter West, Chandra Bhagavatula, Ronan Le Bras, Jena D. Hwang, Soumya Sanyal, Sean Welleck, Xiang Ren, Allyson Ettinger, Zaid Harchaoui and Yejin Choi (* First co-authors; † Second co-authors)
  [pre-print]
• PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning.
  Faeze Brahman, Chandra Bhagavatula, Valentina Pyatkin, Jena D. Hwang, Xiang Lorraine Li, Hirona J. Arai, Soumya Sanyal, Keisuke Sakaguchi, Xiang Ren and Yejin Choi
  [pre-print]
• Editing Commonsense Knowledge in GPT.
  Anshita Gupta*, Debanjan Mondal*, Akshay Krishna Sheshadri*, Wenlong Zhao, Xiang Lorraine Li, Sarah Wiegreffe, Niket Tandon. (* Equal Contribution)``
  [pre-print]
• Scaling Language Models: Methods, Analysis & Insights from Training Gopher.
  Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, Eliza Rutherford, Tom Hennigan, Jacob Menick, Albin Cassirer, Richard Powell, George van den Driessche, Lisa Anne Hendricks, Maribeth Rauh, Po-Sen Huang, Amelia Glaese, Johannes Welbl, Sumanth Dathathri, Saffron Huang, Jonathan Uesato, John Mellor, Irina Higgins, Antonia Creswell, Nat McAleese, Amy Wu, Erich Elsen, Siddhant Jayakumar, Elena Buchatskaya, David Budden, Esme Sutherland, Karen Simonyan, Michela Paganini, Laurent Sifre, Lena Martens, Xiang Lorraine Li, Adhiguna Kuncoro, Aida Nematzadeh, Elena Gribovskaya, Domenic Donato, Angeliki Lazaridou, Arthur Mensch, Jean-Baptiste Lespiau, Maria Tsimpoukelli, Nikolai Grigorev, Doug Fritz, Thibault Sottiaux, Mantas Pajarskas, Toby Pohlen, Zhitao Gong, Daniel Toyama, Cyprien de Masson d’Autume, Yujia Li, Tayfun Terzi, Vladimir Mikulik, Igor Babuschkin, Aidan Clark, Diego de Las Casas, Aurelia Guy, Chris Jones, James Bradbury, Matthew Johnson, Blake Hechtman, Laura Weidinger, Iason Gabriel, William Isaac, Ed Lockhart, Simon Osindero, Laura Rimell, Chris Dyer, Oriol Vinyals, Kareem Ayoub, Jeff Stanway, Lorrayne Bennett, Demis Hassabis, Koray Kavukcuoglu and Geoffrey Irving
  [pre-print] [DeepMind Blog]

Teaching

• Guest Lecture for UMass Amherst CS 685 Advanced Natural Language Processing Fall 2020. [slides] [recordings]
• Guest Lecture for JHU Computer Science EN.601.464 Artificial Intelligence Fall 2020. [slides] [recordings]
• Teaching Assistant for COMPSCI 696DS: MS Industry Mentorship independent study for Spring 2021

Service

• Area Chair: Inference and Question Answering track at COLING 2022.
• Workshop Organizer: The 1st workshop on Commonsense Representation and Reasoning at ACL 2022
• Workshop Organizer: The 7th workshop on Representation Learning for NLP at ACL 2022
• Workshop Organizer: The 1st workshop on Commonsense Reasoning and Knowledge Bases at AKBC 2021
• Reviewers: NAACL 2019, ACL 2019, AKBC 2019, EMNLP 2019, AAAI 2020, ACL 2020, AKBC 2020, AACL 2020, CoNLL 2020, AAAI 2021, NAACL 2021, ARR 2021 and workshops
• Conference Volunteer: NAACL 2016, NeurIps 2017
• PhD Volunteer: PhD Applicant Support Program at UMass Amherst CICS 2020, 2021

Others

My chinese first name is challenging to pronounce. Here is how to prounouce 响 (xiǎng) for phonics enthusiast.

I sometims bake, and play piano.

I'm also learning how to dance Salsa!

---