We tackle this problem by introducing scenario-based semantic parsing: a variant of the original task which first requires disambiguating an utterance's "scenario" (an intent-slot template with variable leaf spans) before generating its frame, complete with ontology and utterance tokens.
Many NLP tasks require processing long contexts beyond the length limit of pretrained models.
Our evaluations show a clear improvement in the efficiency of using human editors and an improved video generation quality.
Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data.
Ranked #2 on Passage Retrieval on Natural Questions
1 code implementation • 28 Jul 2021 • Barlas Oğuz, Kushal Lakhotia, Anchit Gupta, Patrick Lewis, Vladimir Karpukhin, Aleksandra Piktus, Xilun Chen, Sebastian Riedel, Wen-tau Yih, Sonal Gupta, Yashar Mehdad
Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased performance across almost all NLP tasks.
Ranked #1 on Passage Retrieval on Natural Questions (using extra training data)
We propose pre-finetuning, an additional large-scale learning stage between language model pre-training and fine-tuning.
Ranked #1 on Sentence Completion on HellaSwag
Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets.
Although widely adopted, existing approaches for fine-tuning pre-trained language models have been shown to be unstable across hyper-parameter settings, motivating recent work on trust region methods.
We evaluate the quality of our platform, the diversity of demonstrations in our dataset, and the utility of our dataset via quantitative and qualitative analysis.
We present an overview of SURREAL-System, a reproducible, flexible, and scalable framework for distributed reinforcement learning (RL).
Imitation Learning has empowered recent advances in learning robotic manipulation tasks by addressing shortcomings of Reinforcement Learning such as exploration and reward specification.
Finally, we show experimentally that our algorithm performs well and computes succinct policies on a number of POMDP instances from the literature that were naturally enhanced with energy levels.