activity
20162026
most citedParaphrasing evades detectors of AI-generated text, but retrieval is an effective defense

91 citations · 357 across the 71 of their papers we have counts for

collaborators
Showing 2018 · cs.CLShow all

6 papers · 2 filters

cs.CL2018

QuAC : Question Answering in Context

Eunsol Choi, He He, Mohit Iyyer +5

We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1)…

cs.CL2018

Revisiting the Importance of Encoding Logic Rules in Sentiment Classification

Kalpesh Krishna, Preethi Jyothi, Mohit Iyyer

We analyze the performance of different sentiment classification models on syntactically complex inputs like A-but-B sentences. The first contribution of this analysis addresses re…

cs.CL2018

Adversarial Example Generation with Syntactically Controlled Paraphrase Networks

Mohit Iyyer, John Wieting, Kevin Gimpel +1

We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency pa…

cs.CL2018

Inducing and Embedding Senses with Scaled Gumbel Softmax

Fenfei Guo, Mohit Iyyer, Jordan Boyd-Graber

Methods for learning word sense embeddings represent a single word with multiple sense-specific vectors. These methods should not only produce interpretable sense embeddings, but s…

cs.CL2018

Pathologies of Neural Models Make Interpretations Difficult

Shi Feng, Eric Wallace, Alvin Grissom +3

One way to interpret neural model predictions is to highlight the most important input features---for example, a heatmap visualization over the words in an input sentence. In exist…

cs.CL2018

Deep contextualized word representations

Matthew E. Peters, Mark Neumann, Mohit Iyyer +4

We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses var…