End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to
understand. This has given rise to numerous efforts towards model explainability in recent …

Despite their impressive performance, large language models (LMs) still struggle with
reliably generating complex output structures when not finetuned to follow the required …

Recent research has shown that integrating domain knowledge into deep learning
architectures is effective; It helps reduce the amount of required data, improves the accuracy …

Large Language Models (LLMs) are nowadays expected to generate content aligned with
human preferences. Current work focuses on alignment at model training time, through …

Determining the role of event arguments is a crucial subtask of event extraction. Most
previous supervised models leverage costly annotations, which is not practical for open …

Many real-world structured prediction problems need machine learning to capture data
distribution and constraint reasoning to ensure structure validity. Nevertheless, constrained …

In recent years, marked temporal point processes (MTPPs) have emerged as a powerful
modeling machinery to characterize asynchronous events in a wide variety of applications …

LMs are often expected to generate strings in some formal language; for example, structured
data, API calls, or code snippets. Although LMs can be tuned to improve their adherence to …

Abstract Sequence-to-Sequence (S2S) models have achieved remarkable success on
various text generation tasks. However, learning complex structures with S2S models …

One challenge in speech translation is that plenty of spoken content is long-form, but short
units are necessary for obtaining high-quality translations. To address this mismatch, we …