Aakanksha Naik

STAGE: Tool for Automated Extraction of Semantic Time Cues to Enrich Neural Temporal Ordering Models

2021 · arXiv (Cornell University)

Despite achieving state-of-the-art accuracy on temporal ordering of events, neural models showcase significant gaps in performance. Our work seeks to fill one of these gaps by leveraging an under-explored dimension of textual semantics: rich semantic …

LongBoX: Evaluating Transformers on Long-Sequence Clinical Tasks

2023 · arXiv (Cornell University)

Many large language models (LLMs) for medicine have largely been evaluated on short texts, and their ability to handle longer sequences such as a complete electronic health record (EHR) has not been systematically explored. Assessing …

SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature

2024 · arXiv (Cornell University)

We present SciRIFF (Scientific Resource for Instruction-Following and Finetuning), a dataset of 137K instruction-following instances for training and evaluation, covering 54 tasks. These tasks span five core scientific literature understanding capabilities: information extraction, summarization, question …

Exploring Numeracy in Word Embeddings

2019

Word embeddings are now pervasive across NLP subfields as the de-facto method of forming text representataions. In this work, we show that existing embedding models are inadequate at constructing representations that capture salient aspects of …