activity
20172025
most citedLanguage Generation with Recurrent Generative Adversarial Networks without Pre-training

90 citations · 427 across the 29 of their papers we have counts for

collaborators
Showing 2020Show all

14 papers · 1 filter

cs.CL2020

Transformer Feed-Forward Layers Are Key-Value Memories

Mor Geva, Roei Schuster, Jonathan Berant +1

Feed-forward layers constitute two-thirds of a transformer model's parameters, yet their role in the network remains under-explored. We show that feed-forward layers in transformer…

cs.CL2020

Improving Compositional Generalization in Semantic Parsing

Inbar Oren, Jonathan Herzig, Nitish Gupta +2

Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes…

cs.CL2020

SmBoP: Semi-autoregressive Bottom-up Semantic Parsing

Ohad Rubin, Jonathan Berant

The de-facto standard decoding method for semantic parsing in recent years has been to autoregressively decode the abstract syntax tree of the target program using a top-down depth…

cs.CV20206 cited

Learning Object Detection from Captions via Textual Scene Attributes

Achiya Jerbi, Roei Herzig, Jonathan Berant +2

Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect, as annotators need to label objects and their bounding…

cs.CL2020

A Simple Global Neural Discourse Parser

Yichu Zhou, Omri Koshorek, Vivek Srikumar +1

Discourse parsing is largely dominated by greedy parsers with manually-designed features, while global parsing is rare due to its computational expense. In this paper, we propose a…

cs.CL2020

Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering

Ben Bogin, Sanjay Subramanian, Matt Gardner +1

Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-of-the-art mod…