Taylor Berg-Kirkpatrick

From sunblock to softblock: Analyzing the correlates of neology in published writing and on social media EACL 2026 Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages ACL 2026 Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation ICML 2025 ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models ICLR 2025 Optimizing Hidden Markov Language Models: An Empirical Study of Reparameterization and Initialization Techniques NAACL 2025 Presto! Distilling Steps and Layers for Accelerating Music Generation ICLR 2025 Synthesizing Composite Hierarchical Structure from Symbolic Music Corpora IJCAI 2025 TeaserGen: Generating Teasers for Long Documentaries ICLR 2025 Aligning Unstructured Paris Agreement Climate Plans with Sustainable Development Goals ACL 2024 Alt-Text with Context: Improving Accessibility for Images on Twitter ICLR 2024 Classification of Paleographic Artifacts at Scale: Mitigating Confounds and Distribution Shift in Cuneiform Tablet Dating ACL 2024 DITTO: Diffusion Inference-Time T-Optimization for Music Generation ICML 2024 Grammar-Aligned Decoding NeurIPS 2024 HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis NeurIPS 2024 Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation Interspeech 2024 Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability ICLR 2024 LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP ACL 2024 MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization EMNLP 2024 Retrieval Guided Music Captioning via Multimodal Prefixes IJCAI 2024 Smaller Language Models are Better Zero-shot Machine-Generated Text Detectors EACL 2024 A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation CoNLL 2023 Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval ACL 2023 CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos ICLR 2023 Contrastive Attention Networks for Attribution of Early Modern Print AAAI 2023 Membership Inference Attacks against Language Models via Neighbourhood Comparison ACL 2023 Simple Temporal Adaptation to Changing Label Sets: Hashtag Prediction via Dense KNN EMNLP 2023 Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection ACL 2022 An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models EMNLP 2022 Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings ICLR 2022 HeLo: Learning-Free Lookahead Decoding for Conversation Infilling EMNLP 2022 HOLM: Hallucinating Objects with Language Models for Referring Expression Recognition in Partially-Observed Scenes ACL 2022 Lacuna Reconstruction: Self-Supervised Pre-Training for Low-Resource Historical Document Transcription NAACL 2022 Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context NAACL 2022 Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models ACL 2022 Paraphrastic Representations at Scale EMNLP 2022 Prompt Consistency for Zero-Shot Task Generalization EMNLP 2022 Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks EMNLP 2022 Towards a Unified View of Parameter-Efficient Transfer Learning ICLR 2022 UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis NAACL 2022 Zero-Shot Audio Source Separation through Query-Based Learning from Weakly-Labeled Data AAAI 2022 Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction ACL 2021 Efficient Nearest Neighbor Language Models EMNLP 2021 Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation ACL 2021 Investigating Robustness of Dialog Models to Popular Figurative Language Constructs EMNLP 2021 Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels NAACL 2021 Scalable Font Reconstruction with Dual Latent Manifolds EMNLP 2021 Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness EMNLP 2021 Truth-Conditional Captions for Time Series Data EMNLP 2021 Unsupervised Enrichment of Persona-grounded Dialog with Background Stories ACL 2021 A Bilingual Generative Transformer for Semantic Sentence Embedding EMNLP 2020 An Empirical Investigation of Contextualized Number Prediction EMNLP 2020 A Probabilistic Formulation of Unsupervised Text Style Transfer ICLR 2020 A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing ACL 2020 Learning Sparse Prototypes for Text Generation NeurIPS 2020 Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions EMNLP 2020 Narrative Text Generation with a Latent Discrete Plan EMNLP 2020 Phonetic and Visual Priors for Decipherment of Informal Romanization ACL 2020 Refer360∘: A Referring Expression Recognition Dataset in 360∘ Images ACL 2020 A Deep Factorization of Style and Structure in Fonts EMNLP 2019 An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search NAACL 2019 A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text EMNLP 2019 Beyond BLEU: Training Neural Machine Translation with Semantic Similarity ACL 2019 Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections ACL 2019 Lagging Inference Networks and Posterior Collapse in Variational Autoencoders ICLR 2019 Learning Rhyming Constraints using Structured Adversaries EMNLP 2019 Simple and Effective Paraphrastic Similarity from Parallel Translations ACL 2019 Learning to Describe Differences Between Pairs of Similar Images EMNLP 2018 Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data ACL 2018 Modeling Online Discourse with Coupled Distributed Topics EMNLP 2018 Speaker-Follower Models for Vision-and-Language Navigation NeurIPS 2018 Unsupervised Learning of Syntactic Structure with Invertible Neural Projections EMNLP 2018 Unsupervised Text Style Transfer using Language Models as Discriminators NeurIPS 2018 Visual Referring Expression Recognition: What Do Systems Actually Learn? NAACL 2018 Automatic Compositor Attribution in the First Folio of Shakespeare ACL 2017 Differentiable Scheduled Sampling for Credit Assignment ACL 2017 Identifying Products in Online Cybercrime Marketplaces: A Dataset for Fine-grained Domain Adaptation EMNLP 2017 Improved Variational Autoencoders for Text Modeling using Dilated Convolutions ICML 2017 Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints ACL 2016 An Empirical Analysis of Optimization for Max-Margin NLP EMNLP 2015 GPU-Friendly Local Regression for Voice Conversion NAACL 2015 Unsupervised Code-Switching for Multilingual Historical Document Transcription NAACL 2015 Improved Typesetting Models for Historical OCR ACL 2014 Sparser, Better, Faster GPU Parsing ACL 2014 Unsupervised Transcription of Piano Music NeurIPS 2014 Decipherment with a Million Random Restarts EMNLP 2013 Learning Whom to Trust with MACE NAACL 2013 Unsupervised Transcription of Historical Documents ACL 2013 An Empirical Investigation of Statistical Significance in NLP EMNLP 2012 Jointly Learning to Extract and Compress ACL 2011 Simple Effective Decipherment via Combinatorial Optimization EMNLP 2011 Painless Unsupervised Learning with Features NAACL 2010 Phylogenetic Grammar Induction ACL 2010 Learning Bilingual Lexicons from Monolingual Corpora ACL 2008