MuLD (Multitask Long Document Benchmark)
Introduced by Hudson et al. in MuLD: The Multitask Long Document Benchmark
MuLD (Multitask Long Document Benchmark) is a set of 6 NLP tasks where the inputs consist of at least 10,000 words. The benchmark covers a wide variety of task types including translation, summarization, question answering, and classification. Additionally there is a range of output lengths from a single word classification label all the way up to an output longer than the input text.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
MuLD (NarrativeQA)
|
Longformer
|
|||
|
MuLD (HotpotQA)
|
Longformer
|
|||
|
MuLD (Style Change)
|
Longformer
|
|||
|
MuLD (Character Type)
|
Longformer
|
|||
|
MuLD (VLSP)
|
Longformer
|
|||
|
MuLD (OpenSubtitles)
|
T5
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
