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 2021Show all

13 papers · 1 filter

cs.CL2021

COVR: A test-bed for Visually Grounded Compositional Generalization with real images

Ben Bogin, Shivanshu Gupta, Matt Gardner +1

While interest in models that generalize at test time to new compositions has risen in recent years, benchmarks in the visually-grounded domain have thus far been restricted to syn…

cs.CL2021

Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization

Inbar Oren, Jonathan Herzig, Jonathan Berant

Modern semantic parsers suffer from two principal limitations. First, training requires expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize…

cs.CL2021

Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills

Ori Yoran, Alon Talmor, Jonathan Berant

Models pre-trained with a language modeling objective possess ample world knowledge and language skills, but are known to struggle in tasks that require reasoning. In this work, we…

cs.CL20215 cited

Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition

Mor Geva, Tomer Wolfson, Jonathan Berant

Recent efforts to create challenge benchmarks that test the abilities of natural language understanding models have largely depended on human annotations. In this work, we introduc…

cs.CL2021

Memory-efficient Transformers via Top- Attention

Ankit Gupta, Guy Dar, Shaya Goodman +2

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input le…

cs.CL20215 cited

Question Decomposition with Dependency Graphs

Matan Hasson, Jonathan Berant

QDMR is a meaning representation for complex questions, which decomposes questions into a sequence of atomic steps. While state-of-the-art QDMR parsers use the common sequence-to-s…