We have created layers of annotation on the English Gigaword v. 5 corpus to render it
useful as a standardized corpus for knowledge extraction and distributional semantics. Most …

As model context lengths continue to increase, the number of demonstrations that can be
provided in-context approaches the size of entire training datasets. We study the behavior of in-…

Compositional embedding models build a representation (or embedding) for a linguistic
structure based on its component word embeddings. We propose a Feature-rich Compositional …

Recent work on bilingual lexicon induction (BLI) has frequently depended either on aligned
bilingual lexicons or on distribution matching, often with an assumption about the isometry of …

Standard autoregressive language models perform only polynomial-time computation to
compute the probability of the next symbol. While this is attractive, it means they cannot model …

Multi-label document classification (MLDC) problems can be challenging, especially for long
documents with a large label set and a long-tail distribution over labels. In this paper, we …

Fine-tuning pretrained models for automatically summarizing doctor-patient conversation
transcripts presents many challenges: limited training data, significant domain shift, long and …

Minimum Bayes Risk (MBR) decoding is a method for choosing the outputs of a machine
learning system based not on the output with the highest probability, but the output with the …

Medical dialogue summarization is challenging due to the unstructured nature of medical
conversations, the use of medical terminologyin gold summaries, and the need to identify key …

We introduce a dataset for evidence/rationale extraction on an extreme multi-label classification
task over long medical documents. One such task is Computer-Assisted Coding (CAC) …