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. 5

Text Understanding with the Attention Sum Reader Network

Previous5NextEffective Approaches to Attention-based Neural Machine Translation

Last updated 5 years ago

Was this helpful?

论文地址:

TL;DR

本文基于(机器阅读的)答案出自材料的思想, 提出了 Attention Sum Reader, ASReader, 以 question embedding 作为 query, 通过注意力机制计算它与 context document 中各单词的相关程度, 即各单词是答案的概率, 最后求各 unique word 的总得概率, 最高者即为答案.

Key Points

  • 本文提出了 Attention Sum Reader 模型, 流程如下:

    1. 对 question 进行编码得到一个向量作为 query (Bi-GRU 首尾状态的拼接);

    2. 计算 context document 中的每个单词的 word vector (称为 contextual embedding);

    3. 计算 query 与每个 contextual embedding 的 dot product, 再对结果使用 softmax 得到每个单词作为答案的概率, 最后求同一个单词在所有位置上作为答案的概率和, 最高者为答案.

Notes/Questions

  • ASReader 的答案出自材料. 这是一把双刃剑. 一方面它摒弃掉了 vocabularity 中其他的词, 99.9% 是噪声, 使得模型更简单更专注; 但对于复杂的情况, 答案不在 document 中, 需要再推理一下的情况就不太适用了. (关于这一点, 我觉得可以用一个 mask 来做一个权衡, 此时相当于不在 document 中的词的值都是 0, 可以用一个比较小的值来代替, 这样真正作为答案的词依然能出头).

  • 本文提出的模型很简单, 但嘈点颇多:

    • 通过概率累加的方法求解答案, 强调了频率高的单词, attention 的作用被弱化了 (文中演示了一个错误用例);

    • 有一段很搞笑的分析, 话说一个问题的答案是一月和三月, 一般的 attention model, 两月的权值相等, 加权平均的结果就变成了二月, 且不说 embedding 之后还有其他层对 word vector 进行加工, 就是在 vector space, 月份会聚集在一起, 但也不意味着二月就处在一月和三月的中间 (就这样的论文, 还发在 ACL2016 上, 审稿人, 喵喵喵?);

    • 本文取得的 SOTA 是因为使用了 ensemble 方法, single asreader 和 single pre-SOTA 的模型有至少 1.9% 的差距, 科学的做法应该要提供其他模型的 ensemble 版, single vs single, ensemble vs ensemble;

    • 针对上一点, 文中说前人的模型都采用了 dropout, 有助于提升 single model 的性能, 那 single vs ensemble 也说不通, 正确的做法是, 再创建一个 dropout version asreader, 其他方法的 ensemble version 依然需要;

    • 因为另一篇论文中提到本文所采用的数据集给人做也很难, 然后就说 ensemble asreader 已经接近数据集的极限了, 计算机在某些任务上超越人类早就屡见不鲜了吧?

    • 搜了下, 在 openreview 上有一个 short paper 版, 那时候还不含提交到 ACL2016 时新冒出来的模型, 对当时的 baseline 有巨大优势, 后来扩成 long paper, 加了新的 baseline, 只剩 ensemble 有优势了.

https://arxiv.org/abs/1603.01547