activity
20162024
most citedBeyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

565 citations · 818 across the 32 of their papers we have counts for

collaborators
Showing 2016Show all

10 papers · 1 filter

cs.CL2016

Emergent Predication Structure in Hidden State Vectors of Neural Readers

Hai Wang, Takeshi Onishi, Kevin Gimpel +1

A significant number of neural architectures for reading comprehension have recently been developed and evaluated on large cloze-style datasets. We present experiments supporting t…

cs.CL2016★ 3 cited

End-to-End Training Approaches for Discriminative Segmental Models

Hao Tang, Weiran Wang, Kevin Gimpel +1

Recent work on discriminative segmental models has shown that they can achieve competitive speech recognition performance, using features based on deep neural frame classifiers. Ho…

cs.CL2016★ 6 cited

Broad Context Language Modeling as Reading Comprehension

Zewei Chu, Hai Wang, Kevin Gimpel +1

Progress in text understanding has been driven by large datasets that test particular capabilities, like recent datasets for reading comprehension (Hermann et al., 2015). We focus…

cs.NE2016

A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

Dan Hendrycks, Kevin Gimpel

We consider the two related problems of detecting if an example is misclassified or out-of-distribution. We present a simple baseline that utilizes probabilities from softmax distr…

cs.CL2016★ 29 cited

Who did What: A Large-Scale Person-Centered Cloze Dataset

Takeshi Onishi, Hai Wang, Mohit Bansal +2

We have constructed a new "Who-did-What" dataset of over 200,000 fill-in-the-gap (cloze) multiple choice reading comprehension problems constructed from the LDC English Gigaword ne…

cs.CL2016

Efficient Segmental Cascades for Speech Recognition

Hao Tang, Weiran Wang, Kevin Gimpel +1

Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational require…