We had 27 submissions (excluding three incomplete submissions). Every paper was reviewed by at least two members of the program committee and finally 19 submission were accepted (acceptance rate of 73%). Among the accepted papers, there were a few popular themes. 8 papers were related to learning and applications of word embeddings. 10 papers focused on applications of deep neural networks for different IR tasks. The accepted papers also covered a broad range of tasks, including question/answering, proactive IR, knowledge-based IR, conversational models and text-to-image, but document ranking was a popular choice with 7 papers using it as the evaluation task. The word cloud summary (generated using http://www.wordle.net (opens in new tab)) of the abstracts of the accepted papers highlights additional themes across all the submissions.
Geographically, the accepted papers (based on the first author) ranged from 9 countries and 3 continents (FR: 4, IN: 4, CN: 2, DK: 2, UK: 2, US: 2, AT: 1, FI: 1 and IT: 1). Based on the first author’s affiliation, 2 of the accepted papers came from the industry and the rest from academia.
The full list of accepted papers is below:
An empirical study on large scale text classification with skip-gram embeddings (opens in new tab)
Georgios Balikas and Massih-Reza Amini
Deep Feature Fusion Network for Answer Quality Prediction in Community Question Answering (opens in new tab)
Sai Praneeth Suggu, Kushwanth N. Goutham T, Manoj K. Chinnakotla and Manish Shrivastava
Selective Term Proximity Scoring Via BP-ANN (opens in new tab)
Ju Yang, Rebecca Stones, Gang Wang and Xiaoguang Liu
Adaptability of Neural Networks on Varying Granularity IR Tasks (opens in new tab)
Daniel Cohen, Qingyao Ai and W. Bruce Croft
Emulating Human Conversations using Convolutional Neural Network-based IR (opens in new tab)
Abhay Prakash, Chris Brockett and Puneet Agrawal
A Study of MatchPyramid Models on Ad-hoc Retrieval (opens in new tab)
Liang Pang, Yanyan Lan, Jiafeng Guo, Jun Xu and Xueqi Cheng
Learning text representation using recurrent convolutional neural network with highway layers (opens in new tab)
Ying Wen, Weinan Zhang, Rui Luo and Jun Wang
Toward Word Embedding for Personalized Information Retrieval (opens in new tab)
Nawal Ould Amer, Philippe Mulhem and Mathias Géry
Toward a Deep Neural Approach for Knowledge-Based IR (opens in new tab)
Gia-Hung Nguyen, Lynda Tamine, Laure Soulier and Nathalie Bricon-Souf
Query Expansion with Locally-Trained Word Embeddings (opens in new tab)
Fernando Diaz, Bhaskar Mitra and Nick Craswell
LSTM-Based Predictions for Proactive Information Retrieval (opens in new tab)
Petri Luukkonen, Markus Koskela and Patrik Floréen
Picture It In Your Mind: Generating High Level Visual Representations From Textual Descriptions (opens in new tab)
Fabio Carrara, Andrea Esuli, Tiziano Fagni, Fabrizio Falchi and Alejandro Moreo Fernández
Uncertainty in Neural Network Word Embedding Exploration of Potential Threshold (opens in new tab)
Navid Rekabsaz, Mihai Lupu and Allan Hanbury
Deep Learning Relevance: Creating Relevant Information (as Opposed to Retrieving it) (opens in new tab)
Christina Lioma, Birger Larsen, Casper Petersen and Jakob Grue Simonsen
Learning Dynamic Classes of Events using Stacked Multilayer Perceptron Networks (opens in new tab)
Nattiya Kanhabua, Huamin Ren and Thomas B. Moeslund
Representing Documents and Queries as Sets of Word Embedded Vectors for Information Retrieval (opens in new tab)
Debasis Ganguly, Dwaipayan Roy, Mandar Mitra and Gareth Jones
Using Word Embeddings for Automatic Query Expansion (opens in new tab)
Dwaipayan Roy, Debjyoti Paul and Mandar Mitra
Modelling User Preferences using Word Embeddings for Context-Aware Venue Recommendation (opens in new tab)
Jarana Manotumruksa, Craig Macdonald and Iadh Ounis
Using Word Embeddings in Twitter Election Classification (opens in new tab)
Xiao Yang, Craig Macdonald and Iadh Ounis