Recent studies show that instruction tuning and learning from human feed...
Spurious correlations were found to be an important factor explaining mo...
In this paper, we explore the question of whether language models (LLMs)...
We develop computational models to analyze court statements in order to
...
Weird, unusual, and uncanny images pique the curiosity of observers beca...
Machine translation (MT) requires a wide range of linguistic capabilitie...
We present a large, multilingual study into how vision constrains lingui...
A core process in human cognition is analogical mapping: the ability to
...
Proper noun compounds, e.g., "Covid vaccine", convey information in a
su...
Multilingual models have been widely used for cross-lingual transfer to
...
While vision-and-language models perform well on tasks such as visual
qu...
Recent advances in self-supervised modeling of text and images open new
...
We show that the choice of pretraining languages affects downstream
cros...
Recent work has shown that deep learning models in NLP are highly sensit...
We present the task of Automated Punishment Extraction (APE) in sentenci...
We present models which complete missing text given transliterations of
...
Recent works have found evidence of gender bias in models of machine
tra...
Masked language modeling (MLM) is one of the key sub-tasks in vision-lan...
We point out that common evaluation practices for cross-document corefer...
Coreference resolution has been mostly investigated within a single docu...
Recent works have shown that supervised models often exploit data artifa...
We develop Process Execution Graphs (PEG), a document-level representati...
Leaderboards have eased model development for many NLP datasets by
stand...
Gender bias in machine translation can manifest when choosing gender
inf...
Posing reading comprehension as a generation problem provides a great de...
Recent evaluation protocols for Cross-document (CD) coreference resoluti...
We improve upon pairwise annotation for active learning in coreference
r...
Large-scale natural language understanding (NLU) systems have made impre...
Question-answer driven Semantic Role Labeling (QA-SRL) has been proposed...
Distinguishing between singular and plural "you" in English is a challen...
One of the goals of natural language understanding is to develop models ...
A comprehensive and up-to-date analysis of Computer Science literature (...
We present the first challenge set and evaluation protocol for the analy...
Reading comprehension has recently seen rapid progress, with systems mat...
We introduce Question-Answer Meaning Representations (QAMRs), which repr...
Semantic NLP applications often rely on dependency trees to recognize ma...