Neural Models for Information Retrieval
Bhaskar Mitra, Nick Craswell
(Submitted on 3 May 2017)
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ machine learning techniques over hand-crafted IR features. By contrast, neural models learn representations of language from raw text that can bridge the gap between query and document vocabulary. Unlike classical IR models, these new machine learning based approaches are data-hungry, requiring large scale training data before they can be deployed. This tutorial introduces basic concepts and intuitions behind neural IR models, and places them in the context of traditional retrieval models. We begin by introducing fundamental concepts of IR and different neural and non-neural approaches to learning vector representations of text. We then review shallow neural IR methods that employ pre-trained neural term embeddings without learning the IR task end-to-end. We introduce deep neural networks next, discussing popular deep architectures. Finally, we review the current DNN models for information retrieval. We conclude with a discussion on potential future directions for neural IR.
文献紹介:SemEval-2012 Task 1: English Lexical SimplificationTomoyuki Kajiwara
Lucia Specia, Sujay Kumar Jauhar, Rada Mihalcea. SemEval-2012 Task 1: English Lexical Simplification. In Proceedings of the 6th International Workshop on Semantic Evaluation (SemEval-2012), pp.347-355, 2012.
文献紹介:SemEval-2012 Task 1: English Lexical SimplificationTomoyuki Kajiwara
Lucia Specia, Sujay Kumar Jauhar, Rada Mihalcea. SemEval-2012 Task 1: English Lexical Simplification. In Proceedings of the 6th International Workshop on Semantic Evaluation (SemEval-2012), pp.347-355, 2012.
EMNLP 2015 読み会 @ 小町研 "Morphological Analysis for Unsegmented Languages using ...Yuki Tomo
首都大学東京 情報通信システム学域 小町研究室に行われた EMNLP 2015 読み会で "Morphological Analysis for Unsegmented Languages using Recurrent Neural Network Language Model" を紹介した際の資料です。
This document discusses contributing to Chainer and increasing its user base. It introduces Keisuke Umezawa as a Chainer Evangelist and outlines the mission of the Chainer User Group to expand the number of contributors, users, researchers, and those interested in deep learning and Chainer. It addresses common concerns about contributing such as not knowing what to do, lacking skills, and being afraid of reviews. Suggestions are provided like following the contribution guide, starting with labeled easier issues, and receiving helpful comments. The overall goal is to encourage more people to contribute to Chainer.
47. Dual Embedding Space
Model (DESM)
• クエリ、ドキュメントを、それぞれに含まれる単
語の平均で表現する
• ただし、クエリの単語とドキュメントの単語は別
空間で表現されている
• 典型的な例として、Word2vecの2つの行列がIN,
OUTに使用される
47
IN OUT
49. Word Mover’s Distance
(WMD) に基づいた手法
• 基本的なアイデア
• 文書A, B間の距離 =
A, Bの単語同士を対応付けることでAをBに変換するとき、対
応付けのコストが最も低い場合のコストの総和
• 単語xを単語yに対応付けるコスト =
x, yの分散表現ベクトルの距離
49
[1] Kusner, Matt J., et al. “From word embeddings to document distances.”
Proceedings of the 32nd International Conference on Machine Learning
(ICML 2015). 2015.
69. Neural Document Ranking Model(2)
Siamese network
• Deep Semantic Similarity Model (DSSM)
• 短いクエリとドキュメントを対象
• 入力はBoTrigraghs
• Learning deep structured semantic models for
web search using clickthrough data
• クリックしたかどうかを教師データにするい
つものあれ
69
[2] Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry Heck. 2013. Learning deep structured semantic models for web search using
clickthrough data. In Proc. CIKM. ACM, 2333–2338.