The Natural Language Decathlon: Multitask Learning as Question Answering
Bryan McCann, Nitish Shirish Keskar, Caiming Xiong, Richard Socher Salesforce Research
Abstract
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, 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) that jointly learns all tasks in decaNLP without any task-specific modules or parameters. 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 that performance further improves with an anti-curriculum training strategy. Though designed for decaNLP, MQAN als
中文速览
深度学习虽然在各类自然语言处理任务上单独表现出色，但过度聚焦单一任务会阻碍通用模型的涌现。研究者提出了"自然语言十项全能"（Natural Language Decathlon，decaNLP）这一挑战基准，将问答、机器翻译、摘要生成、情感分析等十项任务统一表述为"基于上下文的问答"形式，让模型通过自然语言问题来理解任务描述，而无需任何任务专属模块或参数。为此，他们设计了多任务问答网络（Multitask Question Answering Network，MQAN），其核心在于双协同注意力编码器与多指针生成器解码器，能够同时应对所有任务。实验表明，MQAN在机器翻译和命名实体识别的迁移学习、情感分析与自然语言推理的领域自适应，以及文本分类的零样本场景中均有显著提升，还在WikiSQL语义解析单任务设置上达到了当时最优水平。这项工作的重要意义在于：它提供了一套完整的多任务学习评测框架与强基线，推动NLP领域向真正通用的语言理解模型迈进。
原文 arXiv:1806.08730;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1806.08730v1