18 citations · 46 across the 5 of their papers we have counts for
11 papers · 1 filter
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…
What's in your Head? Emergent Behaviour in Multi-Task Transformer Models
Mor Geva, Uri Katz, Aviv Ben-Arie +1
The primary paradigm for multi-task training in natural language processing is to represent the input with a shared pre-trained language model, and add a small, thin network (head)…
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
Mor Geva, Daniel Khashabi, Elad Segal +3
A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly. In this work, we introduce Strate…
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…
Injecting Numerical Reasoning Skills into Language Models
Mor Geva, Ankit Gupta, Jonathan Berant
Large pre-trained language models (LMs) are known to encode substantial amounts of linguistic information. However, high-level reasoning skills, such as numerical reasoning, are di…
Break It Down: A Question Understanding Benchmark
Tomer Wolfson, Mor Geva, Ankit Gupta +4
Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decom…