Category: NLP

2019
0
NLP

A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling

本文研究的是联合意图识别和序列标注问题，在slot-gate基础上综合考虑ID->SF和SF->ID两方面的影响，同时提出了一种多重交互的机制来增强两个任务之间的联系，在ATIS和Snips公开数据集上取得了很好的效果。 paper: https://drive.google.com/open?id=13fCcaL87EMYgDq6R_mH5a56LqSQ2axglsource: ACL 2019 short papercode: https://github.com/ZephyrChenzf/SF-ID-Network-For-NLU

0
NLP

Few-Shot Text Classification With Distributional Signatures

本文提出了一种少样本下的元学习方法，用于文本分类，在多个数据集上取得较好效果。 paper: https://drive.google.com/open?id=19HtiZOH1jKWtEu_pq38wVYtYOwNIvPiPcode: https://github.com/YujiaBao/Distributional-Signaturessource: Work in Progress for ICLR2020

0
NLP

A Survey of User Simulator in Task-Oriented Dialog System

Introduction任务导向型对话系统用于帮助用户完成某个任务如查电影、找餐馆等，它一般由四个模块组成：自然语言理解模块（Natural Language Understanding, NLU）、对话状态跟踪模块（Dialog State Tracking, DST）、对话策略模块（Dialog Policy, DP）和自然语言生成模块（Natural language Generation

0
NLP

Meta-Learning Learning to Learn

Meta-learning, also known as “learning to learn”, intends to design models that can learn new skills or adapt to new environments rapidly with a few training examples. There are three common approaches: 1) learn an efficient distance metric (metric-based); 2) use (recurrent) network with external or internal memory (model-based); 3) optimize the model parameters explicitly for fast learning (optimization-based).