Text Generation aims to produce plausible and readable text in human language from input
data. The resurgence of deep learning has greatly advanced this field, in particular, with the …

In this work, we aim to capitalize on the unique few-shot capabilities of large-scale language
models (LSLMs) to overcome some of their challenges with respect to grounding to factual …

Entities are at the center of how we represent and aggregate knowledge. For instance,
Encyclopedias such as Wikipedia are structured by entities (eg, one per Wikipedia article) …

Text style transfer is an important task in natural language generation, which aims to control
certain attributes in the generated text, such as politeness, emotion, humor, and many …

The dominant paradigm for neural text generation is left-to-right decoding from
autoregressive language models. Constrained or controllable generation under complex …

Recently, large-scale pre-trained language models have demonstrated impressive
performance on several commonsense-reasoning benchmark datasets. However, building …

Large language models can be prompted to pro-duce fluent output for a wide range of tasks
without being specifically trained to do so. Nevertheless, it is notoriously difficult to control …

Consistency is a key requirement of high-quality translation. It is especially important to
adhere to pre-approved terminology and adapt to corrected translations in domain-specific …

Neural encoder-decoder models for language generation can be trained to predict words
directly from linguistic or non-linguistic inputs. When generating with these so-called end-to …

Current summarization systems yield generic summaries that are disconnected from users'
preferences and expectations. To address this limitation, we present CTRLsum, a novel …