Traditional multi-task learning architectures train a single model across multiple tasks through a shared encoder followed by task-specific decoders. Learning these models often requires specialized training algorithms that address task-conflict in the shared parameter updates, which otherwise can lead to negative transfer. A new type of multi-task learning within NLP homogenizes multi-task architectures as a shared encoder and language model decoder, which does surprisingly well across a range of diverse tasks. Does this new architecture suffer from task-conflicts that require specialized training algorithms? We study how certain factors in the shift towards text-to-text models affects multi-task conflict and negative transfer, finding that both directional conflict and transfer are surprisingly constant across architectures.

The Natural Language Decathlon is a multitask challenge that spans ten tasks: question answering (SQuAD), machine translation (IWSLT), summarization (CNN/DM), natural language inference (MNLI), sentiment analysis (SST), semantic role labeling(QA‑SRL), zero-shot relation extraction (QA‑ZRE), goal-oriented dialogue (WOZ, semantic parsing (WikiSQL), and commonsense reasoning (MWSC). Each task is cast as question answering, which makes it possible to use our new Multitask Question Answering Network (MQAN). This model jointly learns all tasks in decaNLP without any task-specific modules or parameters in the multitask setting. For a more thorough introduction to decaNLP and the tasks, see the main website, our blog post, or the paper. While the research direction associated with this repository focused on multitask learning, the framework itself is designed in a way that should make single-task training, transfer learning, and zero-shot evaluation simple.

Sanyam Bhutani: Hello Richard, Thank you so much for doing this interview. You've also taught one of the best and most famous courses on NLP and you hold a Ph.D. in the ML domain. Could you tell the readers about how you got started? What got you interested in Deep Learning? Dr. Richard Socher: Growing up I was always interested in math.

Deep learning has significantly improved state-of-the-art performance for natural language processing tasks like machine translation, summarization, question answering, and text classification. Each of these tasks is typically studied with a specific metric, and performance is often measured on a set of standard benchmark datasets. This has led to the development of architectures designed specifically for those tasks and metrics, but it does not necessarily promote the emergence of general NLP models, those which can perform well across a wide variety of NLP tasks. In order to explore the possibility of such models as well as the tradeoffs that arise in optimizing for them, we introduce the Natural Language Decathlon (decaNLP). The goal of the Decathlon is to explore models that generalize to all ten tasks and investigate how such models differ from those trained for single tasks.

Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten tasks: question answering, machine translation, summarization, natural language inference, sentiment analysis, semantic role labeling, zero-shot relation extraction, goal-oriented dialogue, semantic parsing, and commonsense pronoun resolution. We cast all tasks as question answering over a context. Furthermore, we present a new Multitask Question Answering Network (MQAN) jointly learns all tasks in decaNLP without any task-specific modules or parameters in the multitask setting. MQAN shows improvements in transfer learning for machine translation and named entity recognition, domain adaptation for sentiment analysis and natural language inference, and zero-shot capabilities for text classification. We demonstrate that the MQAN's multi-pointer-generator decoder is key to this success and performance further improves with an anti-curriculum training strategy. Though designed for decaNLP, MQAN also achieves state of the art results on the WikiSQL semantic parsing task in the single-task setting. We also release code for procuring and processing data, training and evaluating models, and reproducing all experiments for decaNLP.