Query-focused summarization (QFS) aims to produce summaries that answer particular questions of interest, enabling greater user control and personalization.
We train our experts using reinforcement learning (RL) to minimize the error defined by two factual consistency metrics: entity overlap and dependency arc entailment.
If not, how easily can such a system be repurposed for their use case?
Novel neural architectures, training strategies, and the availability of large-scale corpora haven been the driving force behind recent progress in abstractive text summarization.
Despite impressive performance on standard benchmarks, deep neural networks are often brittle when deployed in real-world systems.
As a case study, we apply this methodology to analyzing gender bias in pre-trained Transformer language models.
Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield useful representations for downstream tasks.
Transformer architectures have proven to learn useful representations for protein classification and generation tasks.
Common methods for interpreting neural models in natural language processing typically examine either their structure or their behavior, but not both.
The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach.
The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks.