Large Language Models (LLMs) have issues with document question answerin...
Academic literature does not give much guidance on how to build the best...
In real-world scenarios, labeled samples for dialogue summarization are
...
Effective figure captions are crucial for clear comprehension of scienti...
Document images are a ubiquitous source of data where the text is organi...
Many language tasks (e.g., Named Entity Recognition, Part-of-Speech tagg...
We provide a quantitative and qualitative analysis of self-repetition in...
Keeping the performance of language technologies optimal as time passes ...
The ability to quantify incivility online, in news and in congressional
...
The best evidence concerning comparative treatment effectiveness comes f...
We introduce Trialstreamer, a living database of clinical trial reports....
Named Entity Recognition systems achieve remarkable performance on domai...
Named entity recognition systems perform well on standard datasets compr...
Modern NLP systems require high-quality annotated data. In specialized
d...
People are often entities of interest in tasks such as search and inform...
We present a corpus of 5,000 richly annotated abstracts of medical artic...
Medical professionals search the published literature by specifying the ...
Content-dense news report important factual information about an event i...
We present a robust approach for detecting intrinsic sentence importance...