Search Results for author: John Thickstun

Found 17 papers, 14 papers with code

Robust Distortion-free Watermarks for Language Models

2 code implementations28 Jul 2023 Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto, Percy Liang

We generate watermarked text by mapping a sequence of random numbers -- which we compute using a randomized watermark key -- to a sample from the language model.

Language Modelling

Anticipatory Music Transformer

no code implementations14 Jun 2023 John Thickstun, David Hall, Chris Donahue, Percy Liang

We achieve this by interleaving sequences of events and controls, such that controls appear following stopping times in the event sequence.

Music Generation

Backpack Language Models

1 code implementation26 May 2023 John Hewitt, John Thickstun, Christopher D. Manning, Percy Liang

We can interpret a sense vector by inspecting its (non-contextual, linear) projection onto the output space, and intervene on these interpretable hooks to change the model's behavior in predictable ways.

Language Modelling Text Generation +1

MAUVE Scores for Generative Models: Theory and Practice

1 code implementation30 Dec 2022 Krishna Pillutla, Lang Liu, John Thickstun, Sean Welleck, Swabha Swayamdipta, Rowan Zellers, Sewoong Oh, Yejin Choi, Zaid Harchaoui

We present MAUVE, a family of comparison measures between pairs of distributions such as those encountered in the generative modeling of text or images.


Evaluating Human-Language Model Interaction

1 code implementation19 Dec 2022 Mina Lee, Megha Srivastava, Amelia Hardy, John Thickstun, Esin Durmus, Ashwin Paranjape, Ines Gerard-Ursin, Xiang Lisa Li, Faisal Ladhak, Frieda Rong, Rose E. Wang, Minae Kwon, Joon Sung Park, Hancheng Cao, Tony Lee, Rishi Bommasani, Michael Bernstein, Percy Liang

To evaluate human-LM interaction, we develop a new framework, Human-AI Language-based Interaction Evaluation (HALIE), that defines the components of interactive systems and dimensions to consider when designing evaluation metrics.

Language Modelling Question Answering

Melody transcription via generative pre-training

1 code implementation4 Dec 2022 Chris Donahue, John Thickstun, Percy Liang

The combination of generative pre-training and a new dataset for this task results in $77$% stronger performance on melody transcription relative to the strongest available baseline.

Chord Recognition Information Retrieval +2

Diffusion-LM Improves Controllable Text Generation

1 code implementation27 May 2022 Xiang Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B. Hashimoto

Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation.

Language Modelling Sentence +1

MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

3 code implementations NeurIPS 2021 Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Sean Welleck, Yejin Choi, Zaid Harchaoui

As major progress is made in open-ended text generation, measuring how close machine-generated text is to human language remains a critical open problem.

Text Generation

Faster Policy Learning with Continuous-Time Gradients

3 code implementations12 Dec 2020 Samuel Ainsworth, Kendall Lowrey, John Thickstun, Zaid Harchaoui, Siddhartha Srinivasa

We study the estimation of policy gradients for continuous-time systems with known dynamics.

Rethinking Evaluation Methodology for Audio-to-Score Alignment

1 code implementation30 Sep 2020 John Thickstun, Jennifer Brennan, Harsh Verma

This paper offers a precise, formal definition of an audio-to-score alignment.

Sound Audio and Speech Processing

An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction

2 code implementations EMNLP 2020 Bhargavi Paranjape, Mandar Joshi, John Thickstun, Hannaneh Hajishirzi, Luke Zettlemoyer

Decisions of complex language understanding models can be rationalized by limiting their inputs to a relevant subsequence of the original text.

Source Separation with Deep Generative Priors

1 code implementation ICML 2020 Vivek Jayaram, John Thickstun

This paper introduces a Bayesian approach to source separation that uses generative models as priors over the components of a mixture of sources, and noise-annealed Langevin dynamics to sample from the posterior distribution of sources given a mixture.

Convolutional Composer Classification

no code implementations26 Nov 2019 Harsh Verma, John Thickstun

This paper investigates end-to-end learnable models for attributing composers to musical scores.

Classification General Classification

Coupled Recurrent Models for Polyphonic Music Composition

no code implementations20 Nov 2018 John Thickstun, Zaid Harchaoui, Dean P. Foster, Sham M. Kakade

This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music.

Time Series Analysis

Invariances and Data Augmentation for Supervised Music Transcription

1 code implementation13 Nov 2017 John Thickstun, Zaid Harchaoui, Dean Foster, Sham M. Kakade

This paper explores a variety of models for frame-based music transcription, with an emphasis on the methods needed to reach state-of-the-art on human recordings.

Data Augmentation Music Transcription +1

Learning Features of Music from Scratch

2 code implementations29 Nov 2016 John Thickstun, Zaid Harchaoui, Sham Kakade

This paper introduces a new large-scale music dataset, MusicNet, to serve as a source of supervision and evaluation of machine learning methods for music research.

BIG-bench Machine Learning Multi-Label Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.