1 code implementation • • Adam Poliak, Max Fleming, Cash Costello, Kenton Murray, Mahsa Yarmohammadi, Shivani Pandya, Darius Irani, Milind Agarwal, Udit Sharma, Shuo Sun, Nicola Ivanov, Lingxi Shang, Kaushik Srinivasan, Seolhwa Lee, Xu Han, Smisha Agarwal, João Sedoc
We release a dataset of over 2, 100 COVID19 related Frequently asked Question-Answer pairs scraped from over 40 trusted websites.
We provide an overview of a new Computational Text Analysis course that will be taught at Barnard College over a six week period in May and June 2021.
We describe our straight-forward approach for Tasks 5 and 6 of 2021 Social Media Mining for Health Applications (SMM4H) shared tasks.
We introduce Uncertain Natural Language Inference (UNLI), a refinement of Natural Language Inference (NLI) that shifts away from categorical labels, targeting instead the direct prediction of subjective probability assessments.
In contrast to standard approaches to NLI, our methods predict the probability of a premise given a hypothesis and NLI label, discouraging models from ignoring the premise.
Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases.
The jiant toolkit for general-purpose text understanding models
Our results show that pretraining on language modeling performs the best on average across our probing tasks, supporting its widespread use for pretraining state-of-the-art NLP models, and CCG supertagging and NLI pretraining perform comparably.
We propose a process for investigating the extent to which sentence representations arising from neural machine translation (NMT) systems encode distinct semantic phenomena.
We present a large-scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation captures distinct types of reasoning.
no code implementations • • Benjamin Van Durme, Tom Lippincott, Kevin Duh, Deana Burchfield, Adam Poliak, Cash Costello, Tim Finin, Scott Miller, James Mayfield, Philipp Koehn, Craig Harman, Dawn Lawrie, Ch May, ler, Max Thomas, Annabelle Carrell, Julianne Chaloux, Tongfei Chen, Alex Comerford, Mark Dredze, Benjamin Glass, Shudong Hao, Patrick Martin, Pushpendre Rastogi, Rashmi Sankepally, Travis Wolfe, Ying-Ying Tran, Ted Zhang
It combines a multitude of analytics together with a flexible environment for customizing the workflow for different users.
We study how different frame annotations complement one another when learning continuous lexical semantics.
The popular skip-gram model induces word embeddings by exploiting the signal from word-context coocurrence.
We propose ECO: a new way to generate embeddings for phrases that is Efficient, Compositional, and Order-sensitive.