2016

Adaptability of Neural Networks on Varying Granularity IR Tasks

Cohen, Daniel, Ai, Qingyao, Croft, W. Bruce

Understand

Recent work in Information Retrieval (IR) using Deep Learning models has yielded state of the art results on a variety of IR tasks.

  • Deep neural networks (DNN) are capable of learning ideal representations of data during the training process, removing the need for independently extracting features.
  • However, the structures of these DNNs are often tailored to perform on specific datasets.
  • In addition, IR tasks deal with text at varying levels of granularity from single factoids to documents containing thousands of words.

Built on

  • Learning to rank answers on large online qa collections

    M. Surdeanu, M. Ciaramita, and H. Zaragoza · 2008

    Earlier work this paper cites.

  • Statistical language models for information retrieval

    C. Zhai · 2008

    Earlier work this paper cites.

  • Learning deep structured semantic models for web search using clickthrough data

    P.-S. Huang, X. He, J. Gao, L. Deng, A. Acero, and L. Heck · 2013

    Earlier work this paper cites.

  • Distributed representations of sentences and documents

    Original

    Q. V. Le and T. Mikolov · 2014

    Earlier work this paper cites.

  • Semantic modelling with long-short-term memory for information retrieval

    Original

    H. Palangi, L. Deng, Y. Shen, J. Gao, X. He, J. Chen, X. Song, and R. Ward · 2014

    Earlier work this paper cites.

Similar

  • A latent semantic model with convolutional-pooling structure for information retrieval

    Y. Shen, X. He, J. Gao, L. Deng, and G. Mesnil · 2014

    Cited alongside, same era.

  • Applying Deep Learning to Answer Selection: A Study and An Open Task

    M. Feng, B. Xiang, M. R. Glass, L. Wang, and B. Zhou · 2015

    Cited alongside, same era.

  • Convolutional neural network architectures for matching natural language sentences

    Original

    B. Hu, Z. Lu, H. Li, and Q. Chen · 2015

    Cited alongside, same era.

  • Learning to rank short text pairs with convolutional deep neural networks

    A. Severyn and A. Moschitti · 2015

    Cited alongside, same era.

  • Lstm-based deep learning models for non-factoid answer selection

    Original

    M. Tan, B. Xiang, and B. Zhou · 2015

    Cited alongside, same era.

  • A recurrent neural network based answer ranking model for web question answering

    D. Wang and E. Nyberg

    Cited in the paper.

  • A recurrent neural network based answer ranking model for web question answering

    D. Wang and E. Nyberg

    Cited in the paper.

Then

  • Monolingual and cross-lingual information retrieval models based on (bilingual) word embeddings

    I. Vulić and M.-F. Moens · 2015

    Later among the works it cites.

  • ABCNN: attention-based convolutional neural network for modeling sentence pairs

    Original

    W. Yin, H. Schütze, B. Xiang, and B. Zhou · 2015

    Later among the works it cites.

  • Attentive pooling networks

    Original

    C. N. dos Santos, M. Tan, B. Xiang, and B. Zhou · 2016

    Closest in time.

  • Deep sentence embedding using long short-term memory networks: Analysis and application to information retrieval

    H. Palangi, L. Deng, Y. Shen, J. Gao, X. He, J. Chen, X. Song, and R. K. Ward · 2016

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…