b'Dan Jurafsky'

research

∙ 09/14/2023

Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Training large language models to follow instructions makes them perform...

0 Federico Bianchi, et al. ∙

research

∙ 08/16/2023

Learning the meanings of function words from grounded language using a visual question answering model

Interpreting a seemingly-simple function word like "or", "behind", or "m...

0 Eva Portelance, et al. ∙

research

∙ 07/14/2023

Othering and low prestige framing of immigrant cuisines in US restaurant reviews and large language models

Identifying and understanding implicit attitudes toward food can help ef...

0 Yiwei Luo, et al. ∙

research

∙ 07/12/2023

Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes

Machine learning is traditionally studied at the model level: researcher...

0 Connor Toups, et al. ∙

research

∙ 06/09/2023

Developing Speech Processing Pipelines for Police Accountability

Police body-worn cameras have the potential to improve accountability an...

0 Anjalie Field, et al. ∙

research

∙ 05/29/2023

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

To recognize and mitigate harms from large language models (LLMs), we ne...

0 Myra Cheng, et al. ∙

research

∙ 05/18/2023

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

The performance of automatic speech recognition (ASR) systems has advanc...

4 Martijn Bartelds, et al. ∙

research

∙ 04/27/2023

string2string: A Modern Python Library for String-to-String Algorithms

We introduce string2string, an open-source library that offers a compreh...

0 Mirac Suzgun, et al. ∙

research

∙ 04/25/2023

Pretrain on just structure: Understanding linguistic inductive biases using transfer learning

Both humans and transformer language models are able to learn language w...

0 Isabel Papadimitriou, et al. ∙

research

∙ 03/28/2023

Foundation Models and Fair Use

Existing foundation models are trained on copyrighted material. Deployin...

0 Peter Henderson, et al. ∙

research

∙ 02/26/2023

Navigating the Grey Area: Expressions of Overconfidence and Uncertainty in Language Models

Despite increasingly fluent, relevant, and coherent language generation,...

0 Kaitlyn Zhou, et al. ∙

research

∙ 02/09/2023

Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions

Recent research using pre-trained transformer models suggests that just ...

1 Nay San, et al. ∙

research

∙ 11/27/2022

Self-Destructing Models: Increasing the Costs of Harmful Dual Uses in Foundation Models

A growing ecosystem of large, open-source foundation models has reduced ...

0 Eric Mitchell, et al. ∙

research

∙ 11/25/2022

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

As the scope of machine learning broadens, we observe a recurring theme ...

0 Rishi Bommasani, et al. ∙

research

∙ 11/14/2022

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

In open-ended natural-language generation, existing text decoding method...

0 Mirac Suzgun, et al. ∙

research

∙ 11/07/2022

Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale

Machine learning models are now able to convert user-written text descri...

0 Federico Bianchi, et al. ∙

research

∙ 10/11/2022

Multilingual BERT has an accent: Evaluating English influences on fluency in multilingual models

While multilingual language models can improve NLP performance on low-re...

0 Isabel Papadimitriou, et al. ∙

research

∙ 10/04/2022

When and why vision-language models behave like bags-of-words, and what to do about it?

Despite the success of large vision and language models (VLMs) in many d...

0 Mert Yüksekgönül, et al. ∙

research

∙ 07/08/2022

Computationally Identifying Funneling and Focusing Questions in Classroom Discourse

Responsive teaching is a highly effective strategy that promotes student...

0 Sterling Alic, et al. ∙

research

∙ 07/01/2022

Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset

One concern with the rise of large language models lies with their poten...

0 Peter Henderson, et al. ∙

research

∙ 05/24/2022

How Human is Human Evaluation? Improving the Gold Standard for NLG with Utility Theory

Human ratings are treated as the gold standard in NLG evaluation. The st...

0 Kawin Ethayarajh, et al. ∙

research

∙ 05/23/2022

Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models

We propose a method for arbitrary textual style transfer (TST)–the task ...

0 Mirac Suzgun, et al. ∙

research

∙ 05/10/2022

Richer Countries and Richer Representations

We examine whether some countries are more richly represented in embeddi...

0 Kaitlyn Zhou, et al. ∙

research

∙ 05/10/2022

Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words

Cosine similarity of contextual embeddings is used in many NLP tasks (e....

0 Kaitlyn Zhou, et al. ∙

research

∙ 04/26/2022

Modular Domain Adaptation

Off-the-shelf models are widely used by computational social science res...

0 Junshen K. Chen, et al. ∙

research

∙ 04/15/2022

Automated speech tools for helping communities process restricted-access corpora for language revival efforts

Many archival recordings of speech from endangered languages remain unan...

2 Nay San, et al. ∙

research

∙ 10/11/2021

Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference

Performing event and entity coreference resolution across documents vast...

0 William Held, et al. ∙

research

∙ 09/13/2021

The Emergence of the Shape Bias Results from Communicative Efficiency

By the age of two, children tend to assume that new word categories are ...

7 Eva Portelance, et al. ∙

research

∙ 06/07/2021

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

In conversation, uptake happens when a speaker builds on the contributio...

0 Dorottya Demszky, et al. ∙

research

∙ 05/31/2021

Attention Flows are Shapley Value Explanations

Shapley Values, a solution to the credit assignment problem in cooperati...

0 Kawin Ethayarajh, et al. ∙

research

∙ 04/21/2021

Sensitivity as a Complexity Measure for Sequence Classification Tasks

We introduce a theoretical framework for understanding and predicting th...

6 Michael Hahn, et al. ∙

research

∙ 04/17/2021

Frequency-based Distortions in Contextualized Word Embeddings

How does word frequency in pre-training data affect the behavior of simi...

0 Kaitlyn Zhou, et al. ∙

research

∙ 03/26/2021

Leveraging neural representations for facilitating access to untranscribed speech from endangered languages

For languages with insufficient resources to train speech recognition sy...

3 Nay San, et al. ∙

research

∙ 11/09/2020

Language Through a Prism: A Spectral Approach for Multiscale Language Representations

Language exhibits structure at different scales, ranging from subwords t...

0 Alex Tamkin, et al. ∙

research

∙ 10/28/2020

DeSMOG: Detecting Stance in Media On Global Warming

Citing opinions is a powerful yet understudied strategy in argumentation...

0 Yiwei Luo, et al. ∙

research

∙ 10/24/2020

Causal Effects of Linguistic Properties

We consider the problem of estimating the causal effects of linguistic p...

0 Reid Pryzant, et al. ∙

research

∙ 10/20/2020

Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation

Neural image-to-text radiology report generation systems offer the poten...

0 Yasuhide Miura, et al. ∙

research

∙ 10/13/2020

With Little Power Comes Great Responsibility

Despite its importance to experimental design, statistical power (the pr...

5 Dallas Card, et al. ∙

research

∙ 10/01/2020

Nearest Neighbor Machine Translation

We introduce k-nearest-neighbor machine translation (kNN-MT), which pred...

0 Urvashi Khandelwal, et al. ∙

research

∙ 09/29/2020

Utility is in the Eye of the User: A Critique of NLP Leaderboards

Benchmarks such as GLUE have helped drive advances in NLP by incentivizi...

12 Kawin Ethayarajh, et al. ∙

research

∙ 06/16/2020

The Role of Verb Semantics in Hungarian Verb-Object Order

Hungarian is often referred to as a discourse-configurational language, ...

0 Dorottya Demszky, et al. ∙

research

∙ 05/20/2020

Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models

Recent models for unsupervised representation learning of text have empl...

0 Dan Iter, et al. ∙

research

∙ 04/30/2020

Pretraining on Non-linguistic Structure as a Tool for Analyzing Learning Bias in Language Models

We propose a novel methodology for analyzing the encoding of grammatical...

0 Isabel Papadimitriou, et al. ∙

research

∙ 03/06/2020

A Framework for the Computational Linguistic Analysis of Dehumanization

Dehumanization is a pernicious psychological process that often leads to...

0 Julia Mendelsohn, et al. ∙

research

∙ 01/31/2020

Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning

Accurate reporting of energy and carbon usage is essential for understan...

0 Peter Henderson, et al. ∙

research

∙ 11/21/2019

Automatically Neutralizing Subjective Bias in Text

Texts like news, encyclopedias, and some social media strive for objecti...

26 Reid Pryzant, et al. ∙

research

∙ 11/10/2019

Social Bias Frames: Reasoning about Social and Power Implications of Language

Language has the power to reinforce stereotypes and project social biase...

0 Maarten Sap, et al. ∙

research

∙ 11/01/2019

Generalization through Memorization: Nearest Neighbor Language Models

We introduce kNN-LMs, which extend a pre-trained neural language model (...

0 Urvashi Khandelwal, et al. ∙

research

∙ 05/21/2019

Sample Efficient Text Summarization Using a Single Pre-Trained Transformer

Language model (LM) pre-training has resulted in impressive performance ...

0 Urvashi Khandelwal, et al. ∙

research

∙ 04/19/2019

Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts

Computing author intent from multimodal data like Instagram posts requir...

18 Julia Kruk, et al. ∙

Dan Jurafsky

Featured Co-authors