iamkissg
  • PaperHighlights
  • 2019
    • 03
      • Not All Contexts Are Created Equal Better Word Representations with Variable Attention
      • Learning Context-Sensitive Word Embeddings with Neural Tensor Skip-Gram Model
      • Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
      • pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference
      • Contextual Word Representations: A Contextual Introduction
      • Not All Neural Embeddings are Born Equal
      • High-risk learning: acquiring new word vectors from tiny data
      • Learning word embeddings from dictionary definitions only
      • Dependency-Based Word Embeddings
    • 02
      • Improving Word Embedding Compositionality using Lexicographic Definitions
      • From Word Embeddings To Document Distances
      • Progressive Growing of GANs for Improved Quality, Stability, and Variation
      • Retrofitting Word Vectors to Semantic Lexicons
      • Bag of Tricks for Image Classification with Convolutional Neural Networks
      • Multi-Task Deep Neural Networks for Natural Language Understanding
      • Snapshot Ensembles: Train 1, get M for free
      • EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks
      • Counter-fitting Word Vectors to Linguistic Constraints
      • AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling
      • Learning semantic similarity in a continuous space
      • Progressive Neural Networks
      • BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
      • Language Models are Unsupervised Multitask Learners
    • 01
      • Querying Word Embeddings for Similarity and Relatedness
      • Data Distillation: Towards Omni-Supervised Learning
      • A Rank-Based Similarity Metric for Word Embeddings
      • Dict2vec: Learning Word Embeddings using Lexical Dictionaries
      • Graph Convolutional Networks for Text Classification
      • Improving Distributional Similarity with Lessons Learned from Word Embeddings
      • Real-time Personalization using Embeddings for Search Ranking at Airbnb
      • Glyce: Glyph-vectors for Chinese Character Representations
      • Auto-Encoding Dictionary Definitions into Consistent Word Embeddings
      • Distilling the Knowledge in a Neural Network
      • Uncovering divergent linguistic information in word embeddings with lessons for intrinsic and extrin
      • The (Too Many) Problems of Analogical Reasoning with Word Vectors
      • Linear Ensembles of Word Embedding Models
      • Intrinsic Evaluation of Word Vectors Fails to Predict Extrinsic Performance
      • Dynamic Meta-Embeddings for Improved Sentence Representations
  • 2018
    • 11
      • Think Globally, Embed Locally — Locally Linear Meta-embedding of Words
      • Learning linear transformations between counting-based and prediction-based word embeddings
      • Learning Word Meta-Embeddings by Autoencoding
      • Learning Word Meta-Embeddings
      • Frustratingly Easy Meta-Embedding – Computing Meta-Embeddings by Averaging Source Word Embeddings
    • 6
      • Universal Language Model Fine-tuning for Text Classification
      • Semi-supervised sequence tagging with bidirectional language models
      • Consensus Attention-based Neural Networks for Chinese Reading Comprehension
      • Attention-over-Attention Neural Networks for Reading Comprehension
      • Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
      • Convolutional Neural Networks for Sentence Classification
      • Deep contextualized word representations
      • Neural Architectures for Named Entity Recognition
      • Improving Language Understanding by Generative Pre-Training
      • A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence C
      • Teaching Machines to Read and Comprehend
    • 5
      • Text Understanding with the Attention Sum Reader Network
      • Effective Approaches to Attention-based Neural Machine Translation
      • Distance-based Self-Attention Network for Natural Language Inference
      • Deep Residual Learning for Image Recognition
      • U-Net: Convolutional Networks for Biomedical Image Segmentation
      • Memory Networks
      • Neural Machine Translation by Jointly Learning to Align and Translate
      • Convolutional Sequence to Sequence Learning
      • An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
      • Graph Attention Networks
      • Attention is All You Need
      • DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
      • A Structured Self-attentive Sentence Embedding
      • Hierarchical Attention Networks for Document Classification
      • Grammar as a Foreign Language
      • Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
      • Transforming Auto-encoders
      • Self-Attention with Relative Position Representations
    • 1
      • 20180108-20180114
  • 2017
    • 12
      • 20171218-2017124 论文笔记
    • 11
      • 20171127-20171203 论文笔记 1
      • 20171106-20171126 论文笔记
      • 20171030-20171105 论文笔记 1
  • Paper Title as Note Title
Powered by GitBook
On this page
  • TL;DR
  • Key Points
  • Notes/Questions

Was this helpful?

  1. 2018
  2. 6

Teaching Machines to Read and Comprehend

PreviousA Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence CNext5

Last updated 5 years ago

Was this helpful?

论文地址:

TL;DR

本文提出两个 attnention-based 机器阅读模型: attentive reader 和 impatient reader. 实验表明: attention 是机器阅读/QA 中关键要素, 因为比 RNN 能传递更长期的依赖.

Key Points

  • 本文提出了一种构造机器阅读语料的方法, 即自动生成文本的摘要, 以原文本为 context, 摘要为 question (query), 再从摘要中挖掉一个词作为 answer, 就得到了.

  • 为了使机器阅读的模型能专注于阅读和理解单一文本, 即不依靠常识等, 文章对语料中的实体名进行了匿名和随机化处理.

  • 本文提出了两个 attention-based reader models

  • attentive reader:

    1. 将 context 和 question 通过两个分离的 Bi-LSTM 进行编码. 对于 question encoder, 将最后的前向/反向输出拼接作为 question 的表示, 记作 u;

    2. 对于 context, 每个时刻的前向/反向输出都作拼接, 得到一个序列. 以 u 为 query, context encoder 的输出序列为 key 和 value, 进行 attention 的计算, 得到输出序列的加权和, 作为 context 的表示, 记作 r;

    3. 最后通过一个非线性结合计算 answer: $g^{AR}(d, q)=tanh(W{rg}r+W{ug}u)$.

  • impatient reader: 与 attention reader 不同之处在于 attention 的计算方式, question 的每个单词都用于计算 attention, 此时得到的 context 的表示 r 是长度与 question 等长的序列, 且第 i 时刻的 r(i) 依赖于 r(i-1): $r(i)=yd^T s(i)+tanh(W{rr} r(i-1))$ ($s(i)$ 表示第 i 个question 单词计算得到 attention weight)

  • impatient reader 的设计模拟了人阅读的做法: 时不时地回过头去文本中搜索答案, 保留 r(i) 对 r(i-1) 的依赖就是 RNN 的一个实现.

Notes/Questions

  • 本文使用的两个 baselines 挺有意思的, 第一个直接选择 context 中最频繁出现的词, 第二个在第一个的基础上, 排除在 query 中出现的词. 后者的理由是出题人不会在 query 提到一个词两次. 这就变成三短一长选长的玄学了呀.

  • 文中科普了一些 QA 的传统方法:

    • Frame-Semantic Parsing: 通过识别谓词及其变化, 让模型学到"who did what to whom"的知识(baseline);

    • Word distance benchmark: 该方法将 question 中挖掉的词和 context 中可能的实体进行对齐, 即以可能对齐的实体为锚点, 度量 question 与 context 的相似度, 具体方法是: 计算 question 中每个单词到与 context 中与它们对齐的最近的词的距离之和 (baseline);

    • Deep LSTM encoder: 将 context 和 question 通过一个 delimiter 连接作为模型输入, context 在前或 question 在前都可以, 使用 skip connection (baseline);

https://arxiv.org/abs/1506.03340
attentive_reader_impatient_reader.png