Despite the seeming success of contemporary grounded text generation sys...
Trustworthy answer content is abundant in many high-resource languages a...
Reliable automatic evaluation of summarization systems is challenging du...
Factual consistency evaluation is often conducted using Natural Language...
Automatically determining whether a text and a corresponding image are
s...
Ensuring that large language models (LMs) are fair, robust and useful
re...
One of the exciting capabilities of recent language models for dialog is...
Abstractive summarization has enjoyed renewed interest in recent years,
...
Recent work attributes progress in NLP to large language models (LMs) wi...
Question answering models commonly have access to two sources of "knowle...
Grounded text generation systems often generate text that contains factu...
Neural knowledge-grounded generative models for dialogue often produce
c...
We propose a simple and effective method for machine translation evaluat...
We propose a lightweight real-time sign language detection model, as we
...
The notion of "in-domain data" in NLP is often over-simplistic and vague...
Phenomenon-specific "adversarial" datasets have been recently designed t...
Multilingual Neural Machine Translation (NMT) models are capable of
tran...
When translating from a language that does not morphologically mark
info...
Multilingual neural machine translation (NMT) enables training a single ...
Splitting and rephrasing a complex sentence into several shorter sentenc...
We present a simple method to incorporate syntactic information about th...
We present a neural model for morphological inflection generation which
...