Natural Language Generation (NLG) has improved exponentially in recent years thanks to
the development of sequence-to-sequence deep learning technologies such as Transformer …

Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in
various fields, including science, engineering, finance, and everyday life. The development …

Consistency of a model—that is, the invariance of its behavior under meaning-preserving
alternations in its input—is a highly desirable property in natural language processing. In …

The impressive performance of recent language models across a wide range of tasks
suggests that they possess a degree of abstract reasoning skills. Are these skills general …

Fine-tuning pretrained language models (LMs) without making any architectural changes
has become a norm for learning various language downstream tasks. However, for non …

Recent studies report that autoregressive language models can successfully solve many
NLP tasks via zero-and few-shot learning paradigms, which opens up new possibilities for …

Language models: past, present, and future Page 1 56 COMMUNICATIONS OF THE ACM |
JULY 2022 | VOL. 65 | NO. 7 contributed articles NATURAL LANGUAGE PROCESSING (NLP) …

NLP systems rarely give special consideration to numbers found in text. This starkly
contrasts with the consensus in neuroscience that, in the brain, numbers are represented …

The application of machine learning (ML) in a range of geospatial tasks is increasingly
common but often relies on globally available covariates such as satellite imagery that can …

Publicly traded companies are required to submit periodic reports with eXtensive Business
Reporting Language (XBRL) word-level tags. Manually tagging the reports is tedious and …