activity
20162020
most citedMathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

119 citations · 144 across the 5 of their papers we have counts for

collaborators

8 papers

cs.CL2020★ 7 cited

Extracting Summary Knowledge Graphs from Long Documents

Zeqiu Wu, Rik Koncel-Kedziorski, Mari Ostendorf +1

Knowledge graphs capture entities and relations from long documents and can facilitate reasoning in many downstream applications. Extracting compact knowledge graphs containing onl…

cs.CL2020★ 2 cited

A Controllable Model of Grounded Response Generation

Zeqiu Wu, Michel Galley, Chris Brockett +8

Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting respon…

cs.CL2019★ 13 cited

DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling

Sachin Mehta, Rik Koncel-Kedziorski, Mohammad Rastegari +1

For sequence models with large vocabularies, a majority of network parameters lie in the input and output layers. In this work, we describe a new method, DeFINE, for learning deep…

cs.CL2019★ 119 cited

MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

Aida Amini, Saadia Gabriel, Peter Lin +3

We introduce a large-scale dataset of math word problems and an interpretable neural math problem solver that learns to map problems to operation programs. Due to annotation challe…

cs.CL2019

Text Generation from Knowledge Graphs with Graph Transformers

Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan +2

Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohib…

cs.CL2018

Pyramidal Recurrent Unit for Language Modeling

Sachin Mehta, Rik Koncel-Kedziorski, Mohammad Rastegari +1

LSTMs are powerful tools for modeling contextual information, as evidenced by their success at the task of language modeling. However, modeling contexts in very high dimensional sp…