The 61st Annual Meeting of the Association for Computational Linguistics (ACL) 2023 is being hosted in Toronto, Canada on July 9th - 14th. 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 Papers

Main Conference

Grokking of Hierarchical Structure in Vanilla Transformers

Authors: Shikhar Murty, Pratyusha Sharma, Jacob Andreas, Christopher Manning
Contact: shikhar.murty@gmail.com
Keywords: emergent syntactic structure, grokking, transformer interpretability, generalization

Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation

Authors: Martijn Bartelds, Nay San, Bradley McDonnell, Dan Jurafsky, Martijn Wieling
Contact: m.bartelds@rug.nl
Links: Paper | Video
Keywords: asr, data augmentation, language variants, low-resource languages, self-training, speech recognition, tts

Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models

Authors: Myra Cheng, Esin Durmus, Dan Jurafsky
Contact: myra1@stanford.edu
Award nominations: Nominated for best paper awards
Links: Paper
Keywords: bias in language models, stereotypes, markedness, personas, intersectionality, unsupervised, prompting

Neural Machine Translation for Mathematical Formulae

Authors: Felix Petersen, Moritz Schubotz, Andre Greiner-Petter, Bela Gipp
Contact: felixp@stanford.edu
Links: Paper | Video
Keywords: formula translation, equations, special functions, mathematical language processing, content language, presentation language, latex, semantic latex, mathematica

On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning

Authors: Omar Shaikh, Hongxin Zhang, William Held, Michael Bernstein, Diyi Yang
Contact: oshaikh@stanford.edu
Links: Paper
Keywords: cot, bias, social nlp, reasoning

ACL Findings

Modeling Cross-Cultural Pragmatic Inference with Codenames Duet

Authors: Omar Shaikh, Caleb Ziems, William Held, Aryan J. Pariani, Fred Morstatter, Diyi Yang
Contact: oshaikh@stanford.edu
Links: Paper
Keywords: common ground, pragmatic inference, social nlp, games!

Authors: Yuhui Zhang*, Michihiro Yasunaga*, Zhengping Zhou*, Jeff Z. HaoChen*, James Zou, Percy Liang, Serena Yeung
Contact: yuhuiz@stanford.edu
Links: Paper | Video | Website
Keywords: scaling, language model, negation

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Authors: Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc Le, Ed Chi, Denny Zhou, Jason Wei
Contact: msuzgun@cs.stanford.edu
Links: Paper | Website
Keywords: big bench hard, bbh, chain-of-thought, codex, palm, reasoning

Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding

Authors: Mirac Suzgun, Luke Melas-Kyriazi, Dan Jurafsky
Contact: msuzgun@cs.stanford.edu
Links: Paper | Website
Keywords: minimum bayes risk decoding, wisdom of the crowd, crowd sampling, open-ended generation, majority voting

Workshops

SIGHT: A Large Annotated Dataset on Student Insights Gathered from Higher Education Transcripts

Authors: Rose E. Wang*, Pawan Wirawarn*, Noah Goodman, Dorottya (Dora) Demszky
Contact: rewang@cs.stanford.edu
Links: Paper
Keywords: education, nlp, dataset
Workshop: Proceedings of Innovative Use of NLP for Building Educational Applications

Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction

Authors: Rose E. Wang, Dorottya (Dora) Demszky
Contact: rewang@cs.stanford.edu
Links: Paper | Video
Keywords: education, nlp, coaching
Workshop: Proceedings of Innovative Use of NLP for Building Educational Applications

Authors: Joel Niklaus, Daniele Giofré
Contact: jniklaus@stanford.edu
Links: Paper
Keywords: legal, efficient, pretraining, longformer, electra, billsum, pubmed, summarization
Workshop: SustaiNLP

We look forward to seeing you at ACL!