All past recordings: Youtube
New methods for automated collection of sarcasm and affective data
The curious case of Figurative Language
Learning and Using Natural Language in Interaction
Romanization with Friends: Deciphering Informally Romanized Text
How do cross-lingual semantic divergences impact neural machine translation?
Do transformer models do phonology like a linguist?
Sarah F. Phillips
Toward a linguistically inclusive model of language processing
Teaching a Language Model to be Grounded: First Steps and Discoveries
Fostering Research in Arabic NLP via Open Source Collaboration
It ain’t all good”: Machinic Abuse Detection and Marginalisation in Machine Learning
Shortformer: Better Language Modeling using Shorter Inputs
Everyone is trying to improve language models by having them look at more words, we show that we can improve them by giving them less words
Tongshuang (Sherry) Wu
Principles and Tools for Evaluating and Improving NLP Models
Active word learning through self-supervision
Language Learning in Interactive Environments
Textual Complexity is in the Eye of the Beholder
Achieving Genuine Progress in Machine Translation
Measuring Association Between Labels and Free-Text Rationales
If Beam Search is the Answer, what was the Question?
John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs
Toward low-latency and accurate simultaneous interpretations from speech
Learning, evaluating and explaining transferable text representations from grumpy ~~Big~~ Small Data.
Fernando Alva Manchego
Challenges in Automatic Evaluation of Text Simplification
Pratik Joshi and Sebastin Santy
The State and Fate of Linguistic Diversity and Inclusion in the NLP World
Through the lens of our taxonomy, you can see mountains of technical progress, but also thousands of languages on the ground without a way to climb them.
Modeling the Second Player in Distributionally Robust Optimization
A classifier and a language model are put head-to-head in a ferocious face-off, distributional robustness ensues.
Su Lin Blodgett
Language and Justice: A Collection of Thoughts on the Social Implications of Language Technologies
Learning Dynamics of LSTM Language Models
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
Commonsense Reasoning from the Angle of Eventualities
Development of NLP datasets and models for African Languages
“Everyone can build a model for an African language, no one can evaluate it like Masakhane can!” – Jade Abbott
Language Probes as V-information Estimators
Sabrina J. Mielke
Fair comparisons for generative language models---with a bit of Information Theory
Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics
Social and Ethical Considerations in English Toxic Language Detection
Automated hate speech detection backfires, but people are awful online so maybe we should just cancel the internet.