565 citations · 1.2k across the 57 of their papers we have counts for
13 papers · 2 filters
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…
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…
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…
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…
Span-based Semantic Parsing for Compositional Generalization
Jonathan Herzig, Jonathan Berant
Despite the success of sequence-to-sequence (seq2seq) models in semantic parsing, recent work has shown that they fail in compositional generalization, i.e., the ability to general…
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…