文本检索及匹配论文阅读笔记汇总（不定期更新）

文档检索

文档检索主要考虑relevance matching，其最明显的特点是query和document长度差别比较大。

关于relevance matching和semantic matching的区别，DRMM这篇论文有比较详细的论述，大家不太了解的可以看下原论文和我之前的阅读笔记。

DRMM

A Deep Relevance Matching Model for Ad-hoc Retrieval

K-NRM && Conv-KNRM

End-to-End Neural Ad-hoc Ranking with Kernel Pooling
Convolutional Neural Networks for Soft-Matching N-Grams in
Ad-hoc Search

PACRR && Co-PACRR

PACRR: A Position-Aware Neural IR Model for Relevance Matching
Co-PACRR:A Context-Aware Neural IR Model for Ad-hoc Retrieval

Enhanced DRMM

Deep Relevance Ranking Using Enhanced Document-Query Interactions

文本匹配

文本匹配更关注semantic matching问题，考虑句子对的全局匹配关系。通常两段文本长度相近。

Simaese Lstm

Siamese Recurrent Architectures for Learning Sentence Similarity

MatchPyramid

Text Matching as Image Recognition

DAM(必读)

A Decomposable Attention Model for Natural Language Inference

BiMPM

Bilateral Multi-Perspective Matching for Natural Language Sentences

DIIN

Natural Language Inference Over Interaction Space(DIIN)

ESIM(必读)

Enhanced LSTM for Natural Language Inference

DRCN

Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information