Stanford AI Lab Papers at ACL-IJCNLP 2021

The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th
International Joint Conference on Natural Language Processing
is being hosted virtually this week. We’re excited to share all the work from SAIL that’s being presented, and you’ll find links to papers, videos and blogs below. Feel free to reach out to the contact authors directly to learn more about the work that’s happening at Stanford!

List of Accepted Long Papers

Neural Event Semantics for Grounded Language Understanding


Authors: Shyamal Buch, Li Fei-Fei, Noah D. Goodman

Contact: shyamal@cs.stanford.edu

Links: Paper | Project Webpage

Keywords: grounded language, compositionality, modular networks, event semantics

Notes: Accepted as a paper to TACL 2021, presented at ACL-IJCNLP 2021!


Measuring Conversational Update: A Case Study on Student-Teacher Interactions


Authors: Dorottya Demszky, Jing Liu, Zid Mancenido, Julie Cohen, Heather Hill, Dan Jurafsky, Tatsunori Hashimoto

Contact: ddemszky@stanford.edu

Links: Paper | Code & Data

Keywords: conversational uptake, education


Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering


Authors: Siddharth Karamcheti, Ranjay Krishna, Li Fei-Fei, Christopher D. Manning

Contact: skaramcheti@cs.stanford.edu

Links: Paper | Code

Keywords: active learning, visual question answering, interpretability

Notes: Outstanding Paper Award


Relevance-guided Supervision for OpenQA with ColBERT


Authors: Omar Khattab, Christopher Potts, Matei Zaharia

Contact: okhattab@stanford.edu

Links: Paper | Code

Keywords: open-domain question answering, neural retrieval, weak supervision

Notes: Accepted as a paper to TACL 2021, presented at ACL-IJCNLP 2021!


Prefix Tuning: Optimizing Continuous Prompts for Generation


Authors: Xiang Lisa Li, Percy Liang

Contact: xlisali@stanford.edu

Links: Paper | Code

Keywords: prefix-tuning, fine-tuning for generation, large-scale fine-tuning


DynaSent: A Dynamic Benchmark for Sentiment Analysis


Authors: Christopher Potts*, Zhengxuan Wu*, Atticus Geiger, Douwe Kiela

Contact: cgpotts@stanford.edu

Links: Paper | Code | Video


Keywords: sentiment analysis, crowdsourcing, adversarial datasets


List of Accepted Short Papers

Attention Flows are Shapley Values


Authors: Kawin Ethyarajh, Dan Jurafsky

Contact: kawin@stanford.edu

Links: Paper

Keywords: explainability; interpretability


Question Generation for Adaptive Education


Authors: Megha Srivastava, Noah D. Goodman

Contact: meghas@stanford.edu

Links: Paper

Keywords: education, nlp, language generation


We look forward to seeing you at ACL-IJCNLP 2021!

Read More