Multi Task Training

AbstractRecent work has explored the syntactic abilities of RNNs using the subject-verb agreement task, which diagnoses sensitivity to sentence structure. RNNs performed this task well in common cases, but faltered …...

AbstractNatural language understanding has recently seen a surge of progress with the use of sentence encoders like ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2019) which are …...

AbstractPrior work on controllable text generation usually assumes that the controlled attribute can take on one of a small set of values known a priori. In this work, we propose …...

AbstractIn online discussion fora, speakers often make arguments for or against something, say birth control, by highlighting certain aspects of the topic. In social science, this is referred to as …...

AbstractBeing engaging, knowledgeable, and empathetic are all desirable general qualities in a conversational agent. Previous work has introduced tasks and datasets that aim to help agents to learn those qualities …...

AbstractThis paper describes our system participated in Task 7 of SemEval-2021: Detecting and Rating Humor and Offense. The task is designed to detect and score humor and offense which are …...

AbstractWhen intelligent agents communicate to accomplish shared goals, how do these goals shape the agents’ language? We study the dynamics of learning in latent language policies (LLPs), in which instructor …...

AbstractThe primary paradigm for multi-task training in natural language processing is to represent the input with a shared pre-trained language model, and add a small, thin network (head) per task. …...

AbstractQuality Estimation (QE) models have the potential to change how we evaluate and maybe even train machine translation models. However, these models still lack the robustness to achieve general adoption. …...

AbstractRecent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has …...

AbstractSummaries, keyphrases, and titles are different ways of concisely capturing the content of a document. While most previous work has released the datasets of keyphrases and summarization separately, in this …...

AbstractTeaching neural models to generate narrative coherent texts is a critical problem. Recent pre-trained language models have achieved promising results, but there is still a gap between human written texts …...

AbstractIn this paper, we present a novel approach for data-to-text generation that addresses the limitations of current methods that primarily focus on specific types of structured data. Our proposed method …...