Amir Globerson
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Amir Globerson has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Avia Efrat
Tel Aviv University
1 shared publication - Aviv Shamsian
Bar-Ilan University
1 shared publication - Elad Segal
Tel Aviv University
1 shared publication - Gal Chechik
Bar-Ilan University, Ramat Gan, Israel
1 shared publication - Jonathan Berant
Carnegie Mellon University τ Tel Aviv University
1 shared publication - Mor Shoham
Tel Aviv University
1 shared publication
Latest Publications
- Open Access
A Simple and Effective Model for Answering Multi-span Questions
Models for reading comprehension (RC) commonly restrict their output space to the set of all single contiguous spans from the input, in order to alleviate the learning problem and avoid the need for a model that generates text explicitly. However, forcing an answer to be a single span can be restrictive, and some recent datasets also include multi-span questions, i.e., questions whose answer is a set of non-contiguous spans in the text. Naturally, models that return single spans cannot answer these questions. In this work, we propose a simple architecture for answering multi-span questions by casting the task as a sequence tagging problem, namely, predicting for each input token whether it should be part of the output or not. Our model substantially improves performance on span extraction questions from DROP and Quoref by 9.9 and 5.5 EM points respectively.
Open AccessA Simple and Effective Model for Answering Multi-span Questions
Models for reading comprehension (RC) commonly restrict their output space to the set of all single contiguous spans from the input, in order to alleviate the learning problem and avoid the need for a model that generates text explicitly. However, forcing an answer to be a single span can be restrictive, and some recent datasets also include multi-span questions, i.e., questions whose answer is a set of non-contiguous spans in the text. Naturally, models that return single spans cannot answer these questions. In this work, we propose a simple architecture for answering multi-span questions by casting the task as a sequence tagging problem, namely, predicting for each input token whether it should be part of the output or not. Our model substantially improves performance on span extraction questions from DROP and Quoref by 9.9 and 5.5 EM points respectively.