Taylor Berg-Kirkpatrick

research

∙ 05/29/2023

Membership Inference Attacks against Language Models via Neighbourhood Comparison

Membership Inference attacks (MIAs) aim to predict whether a data sample...

0 Justus Mattern, et al. ∙

research

∙ 05/24/2023

Text Conditional Alt-Text Generation for Twitter Images

In this work we present an approach for generating alternative text (or ...

0 Nikita Srivatsan, et al. ∙

research

∙ 05/17/2023

Smaller Language Models are Better Black-box Machine-Generated Text Detectors

With the advent of fluent generative language models that can produce co...

0 Fatemehsadat Mireshghallah, et al. ∙

research

∙ 05/11/2023

Universal Source Separation with Weakly Labelled Data

Universal source separation (USS) is a fundamental research task for com...

0 Qiuqiang Kong, et al. ∙

research

∙ 01/11/2023

ClimaBench: A Benchmark Dataset For Climate Change Text Understanding in English

The topic of Climate Change (CC) has received limited attention in NLP d...

0 Tanmay Laud, et al. ∙

research

∙ 12/21/2022

Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval

Contrastive learning has been successfully used for retrieval of semanti...

0 John Wieting, et al. ∙

research

∙ 12/14/2022

CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos

Recent years have seen progress beyond domain-specific sound separation ...

6 Hao-Wen Dong, et al. ∙

research

∙ 11/12/2022

Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation

Contrastive learning has shown remarkable success in the field of multim...

0 Yusong Wu, et al. ∙

research

∙ 09/13/2022

Non-Parametric Temporal Adaptation for Social Media Topic Classification

User-generated social media data is constantly changing as new trends in...

0 Fatemehsadat Mireshghallah, et al. ∙

research

∙ 09/12/2022

Checklist Models for Improved Output Fluency in Piano Fingering Prediction

In this work we present a new approach for the task of predicting finger...

0 Nikita Srivatsan, et al. ∙

research

∙ 09/07/2022

Improving Choral Music Separation through Expressive Synthesized Data from Sampled Instruments

Choral music separation refers to the task of extracting tracks of voice...

0 Ke Chen, et al. ∙

research

∙ 07/14/2022

Multitrack Music Transformer: Learning Long-Term Dependencies in Music with Diverse Instruments

Existing approaches for generating multitrack music with transformer mod...

0 Hao-Wen Dong, et al. ∙

research

∙ 05/25/2022

Memorization in NLP Fine-tuning Methods

Large language models are shown to present privacy risks through memoriz...

0 Fatemehsadat Mireshghallah, et al. ∙

research

∙ 04/29/2022

Prompt Consistency for Zero-Shot Task Generalization

One of the most impressive results of recent NLP history is the ability ...

0 Chunting Zhou, et al. ∙

research

∙ 03/24/2022

Mix and Match: Learning-free Controllable Text Generation using Energy Language Models

Recent work on controlled text generation has either required attribute-...

0 Fatemehsadat Mireshghallah, et al. ∙

research

∙ 03/22/2022

Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection

A limitation of current neural dialog models is that they tend to suffer...

0 Bodhisattwa Prasad Majumder, et al. ∙

research

∙ 03/08/2022

Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks

The wide adoption and application of Masked language models (MLMs) on se...

9 Fatemehsadat Mireshghallah, et al. ∙

research

∙ 02/12/2022

Deep Performer: Score-to-Audio Music Performance Synthesis

Music performance synthesis aims to synthesize a musical score into a na...

0 Hao-Wen Dong, et al. ∙

research

∙ 02/02/2022

TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music

Singing melody extraction is an important problem in the field of music ...

0 Ke Chen, et al. ∙

research

∙ 02/02/2022

HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection

Audio classification is an important task of mapping audio samples into ...

0 Ke Chen, et al. ∙

research

∙ 01/07/2022

An Unsupervised Masking Objective for Abstractive Multi-Document News Summarization

We show that a simple unsupervised masking objective can approach near s...

0 Nikolai Vogler, et al. ∙

research

∙ 12/16/2021

Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription

We present a self-supervised pre-training approach for learning rich vis...

7 Nikolai Vogler, et al. ∙

research

∙ 12/16/2021

Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context

Physical measurements constitute a large portion of numbers in academic ...

0 Daniel Spokoyny, et al. ∙

research

∙ 12/15/2021

Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data

Deep learning techniques for separating audio into different sound sourc...

0 Ke Chen, et al. ∙

research

∙ 10/08/2021

Towards a Unified View of Parameter-Efficient Transfer Learning

Fine-tuning large pre-trained language models on downstream tasks has be...

0 Junxian He, et al. ∙

research

∙ 10/05/2021

Truth-Conditional Captioning of Time Series Data

In this paper, we explore the task of automatically generating natural l...

0 Harsh Jhamtani, et al. ∙

research

∙ 10/01/2021

UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis

Global models are trained to be as generalizable as possible, with user ...

0 Fatemehsadat Mireshghallah, et al. ∙

research

∙ 09/10/2021

Scalable Font Reconstruction with Dual Latent Manifolds

We propose a deep generative model that performs typography analysis and...

0 Nikita Srivatsan, et al. ∙

research

∙ 09/10/2021

Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness

Text style can reveal sensitive attributes of the author (e.g. race or a...

0 Fatemehsadat Mireshghallah, et al. ∙

research

∙ 09/09/2021

Efficient Nearest Neighbor Language Models

Non-parametric neural language models (NLMs) learn predictive distributi...

0 Junxian He, et al. ∙

research

∙ 08/03/2021

An Empirical Evaluation of End-to-End Polyphonic Optical Music Recognition

Previous work has shown that neural architectures are able to perform op...

0 Sachinda Edirisooriya, et al. ∙

research

∙ 07/13/2021

Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music

Modern keyboards allow a musician to play multiple instruments at the sa...

0 Hao-Wen Dong, et al. ∙

research

∙ 06/15/2021

Unsupervised Enrichment of Persona-grounded Dialog with Background Stories

Humans often refer to personal narratives, life experiences, and events ...

0 Bodhisattwa Prasad Majumder, et al. ∙

research

∙ 06/04/2021

Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis–Hastings

While recent work has shown that scores from models trained by the ubiqu...

0 Kartik Goyal, et al. ∙

research

∙ 04/30/2021

Paraphrastic Representations at Scale

We present a system that allows users to train their own state-of-the-ar...

0 John Wieting, et al. ∙

research

∙ 04/16/2021

An Empirical Study of Extrapolation in Text Generation with Scalar Control

We conduct an empirical evaluation of extrapolation performance when con...

0 Aashi Jain, et al. ∙

research

∙ 03/12/2021

Privacy Regularization: Joint Privacy-Utility Optimization in Language Models

Neural language models are known to have a high capacity for memorizatio...

0 Fatemehsadat Mireshghallah, et al. ∙

research

∙ 10/07/2020

Narrative Text Generation with a Latent Discrete Plan

Past work on story generation has demonstrated the usefulness of conditi...

6 Harsh Jhamtani, et al. ∙

research

∙ 10/07/2020

Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions

Existing persona-grounded dialog models often fail to capture simple imp...

4 Bodhisattwa Prasad Majumder, et al. ∙

research

∙ 08/05/2020

MusPy: A Toolkit for Symbolic Music Generation

In this paper, we present MusPy, an open source Python library for symbo...

169 Hao-Wen Dong, et al. ∙

research

∙ 08/04/2020

Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm

Drawing an analogy with automatic image completion systems, we propose M...

29 Ke Chen, et al. ∙

research

∙ 06/29/2020

Learning Sparse Prototypes for Text Generation

Prototype-driven text generation uses non-parametric models that first c...

0 Junxian He, et al. ∙

research

∙ 05/05/2020

Phonetic and Visual Priors for Decipherment of Informal Romanization

Informal romanization is an idiosyncratic process used by humans in info...

0 Maria Ryskina, et al. ∙

research

∙ 05/04/2020

A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing

We propose a deep and interpretable probabilistic generative model to an...

0 Kartik Goyal, et al. ∙

research

∙ 02/10/2020

A Probabilistic Formulation of Unsupervised Text Style Transfer

We present a deep generative model for unsupervised text style transfer ...

0 Junxian He, et al. ∙

research

∙ 01/21/2020

Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods

We perform statistical analysis of the phenomenon of neology, the proces...

0 Maria Ryskina, et al. ∙

research

∙ 11/10/2019

A Bilingual Generative Transformer for Semantic Sentence Embedding

Semantic sentence embedding models encode natural language sentences int...

0 John Wieting, et al. ∙

research

∙ 10/02/2019

A Deep Factorization of Style and Structure in Fonts

We propose a deep factorization model for typographic analysis that dise...

28 Akshay Srivatsan, et al. ∙

research

∙ 09/30/2019

Simple and Effective Paraphrastic Similarity from Parallel Translations

We present a model and methodology for learning paraphrastic sentence em...

0 John Wieting, et al. ∙

research

∙ 09/15/2019

Learning Rhyming Constraints using Structured Adversaries

Existing recurrent neural language models often fail to capture higher-l...

0 Harsh Jhamtani, et al. ∙

Taylor Berg-Kirkpatrick

Featured Co-authors