Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

A Simple and Effective Model for Answering Multi-span Questions

Elad SegalAvia EfratMor ShohamJonathan Berant
2020
EMNLP

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… 

Do Language Embeddings Capture Scales?

Xikun ZhangDeepak RamachandranIan TenneyDan Roth
2020
Findings of EMNLP • BlackboxNLP Workshop

Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense, and factual knowledge. One form of knowledge that has not been studied yet in this context is… 

Improving Compositional Generalization in Semantic Parsing

Inbar OrenJonathan HerzigNitish GuptaJonathan Berant
2020
Findings of EMNLP

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

QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines

Valentina PyatkinAyal KleinReut TsarfatyIdo Dagan
2020
EMNLP

Discourse relations describe how two propositions relate to one another, and identifying them automatically is an integral part of natural language understanding. However, annotating discourse… 

ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization

Tzuf Paz-ArgamanY. AtzmonGal ChechikReut Tsarfaty
2020
Findings of EMNLP

We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to… 

Evaluating Models' Local Decision Boundaries via Contrast Sets

M. GardnerY. ArtziV. Basmovaet al
2020
Findings of EMNLP

Standard test sets for supervised learning evaluate in-distribution generalization. Unfortunately, when a dataset has systematic gaps (e.g., annotation artifacts), these evaluations are misleading:… 

Learning Object Detection from Captions via Textual Scene Attributes

Achiya JerbiRoei HerzigJonathan BerantAmir Globerson
2020
arXiv

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 boxes. Thus, it is… 

Scene Graph to Image Generation with Contextualized Object Layout Refinement

Maor IvgiYaniv BennyAvichai Ben-DavidLior Wolf
2020
arXiv

Generating high-quality images from scene graphs, that is, graphs that describe multiple entities in complex relations, is a challenging task that attracted substantial interest recently. Prior work… 

Span-based Semantic Parsing for Compositional Generalization

Jonathan HerzigJonathan Berant
2020
arXiv

Despite the success of sequence-tosequence (seq2seq) models in semantic parsing, recent work has shown that they fail in compositional generalization, i.e., the ability to generalize to new… 

Reading Akkadian cuneiform using natural language processing

Shai GordinGai GutherzAriel ElazaryY. Cohen
2020
PLoS ONE

In this paper we present a new method for automatic transliteration and segmentation of Unicode cuneiform glyphs using Natural Language Processing (NLP) techniques. Cuneiform is one of the earliest…