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

Was this helpful?

  1. 2019
  2. 03

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

PreviousApproximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetNextContextual Word Representations: A Contextual Introduction

Last updated 5 years ago

Was this helpful?

论文地址: 项目地址:

要点

本文的想法挺奇特, 学习两个单词的表示, 即一个向量来表示 (word_x, word_y) 这样的组合. 方法上也稍有不同, 一般的 word embeddings, 利用的是 target word 和 context 两者间的关系; 本文可以说有两个 target words, 但事实上它们又被认为是一体的, 考虑的是 (word_x, word_y) 和 context 的关系 (就不说是三角关系了吧).

用 R(x, y) 作为 (x, y) 这个组合的表示. 本文中, 如下公式来计算, 其中粗正体的 x 和 y 是 L2 normalized 后的词向量, 上标 4 表示 4 层 MLP. (不限于文章的这种表示方法)

而 context 则用了一个单层 BiLSTM, 最后对 hidden states 用 attention pooling 得到一维的向量:

得到 R(x, y) 和 C(c) 之后, 就要强化单词对与真上下文之间的联系, 还是用了 negative sampling. 不过使用了两种 negative sampling 的变种:

  1. Bivariate Negative Sampling: 只篡改 context 作为负样本;

  2. Multivariate Negative Sampling: 可同时篡改 x, y, 或 c, 任何一方被修改了都被认为是负样本.

文中用到了一项名为Typed Sampling的技术. 采样 x 或 y 的负样本时, 除了从一开始就生成的覆盖整个 Vocab 的unigram distribution 的中采样, 还从对应单词的 top 100 个近邻 (用 cosine similarity 度量距离) 采样. 这和 Airbnb 的基于同一 market 的采样思路相同, 能强化特定类别单词间的关系.

本文剩下的工作讨论了如何将习得的 pair2vec, 即 R(x, y) 作为特征加入模型中. 为了不破坏 encoder 中的 word embeddings, 文章将 pair2vec 加到了 encoder 之上的层中.

从第一个公式可以看出, R(x, y) 和 R(y, x) 是不对称的. 文章就用如下公式为两个序列中所有的单词对生成了关系表示 ([;] 表示 concatenation):

简洁起见, 省略 encoder 的计算过程, 将以上单词对的关系加入模型可以用如下公式描述 (alpha_{i,j} 是单词 a_i 和 b_j 计算得到的注意力系数):

上述公式针对不同的模型会有所改变, 不变的是, 都是以 concate 的方式将 r 注入到模型中.

从实验结果来看, pair2vec 的帮助很显著. 以下是 SQuAD 和 MultiNLI 的结果:

pair2vec_result.png
https://arxiv.org/abs/1810.08854
https://github.com/mandarjoshi90/pair2vec
pair2vec_Rxy.png
pair2vec_Cc.png
pair2vec_eq4.png
pair2vec_eq910.png