Trustworthy answer content is abundant in many high-resource languages a...
Factual consistency evaluation is often conducted using Natural Language...
Automatically determining whether a text and a corresponding image are
s...
Abstractive summarization has enjoyed renewed interest in recent years,
...
Existing benchmarks for open-domain question answering (ODQA) typically ...
Despite their strong performance on many tasks, pre-trained language mod...
Grounded text generation systems often generate text that contains factu...
In-context learning is a recent paradigm in natural language understandi...
Modern semantic parsers suffer from two principal limitations. First,
tr...
Recent advances in open-domain QA have led to strong models based on den...
Generalization of models to out-of-distribution (OOD) data has captured
...
Despite the success of sequence-to-sequence (seq2seq) models in semantic...
Answering natural language questions over tables is usually seen as a
se...
We present a novel system providing summaries for Computer Science
publi...
A major hurdle on the road to conversational interfaces is the difficult...
Currently, no large-scale training data is available for the task of
sci...
Training models to map natural language instructions to programs given t...
When answering a question, people often draw upon their rich world knowl...
Building a semantic parser quickly in a new domain is a fundamental chal...
Virtual agents are becoming a prominent channel of interaction in custom...
A fundamental challenge in developing semantic parsers is the paucity of...