Neu-IR 2017 will take place on Friday August 11, 2017. It is a full day workshop with the following preliminary schedule:
Morning session I (9:00 – 10:30)
(Chair: Bhaskar Mitra)
- 09:00–09:15: Welcome and opening announcements
- 09:15–10:00: Keynote by Yelong Shen (35+10 mins)
- Title: Deep Neural Networks for IR – from Web Search to Reading Comprehension
- Abstract: In this talk, I start with a brief overview of deep learning for information retrieval tasks. I will present dssm model and its extensions to model the relevance between two text strings (query and document). Then I will describe recently developed deep learning technologies “ReasoNet” for machine reading comprehension. In the last section, I will discuss our on-going work of symbolic neural nets which could be a better natural language model.
- Bio: Yelong Shen is a Senior Research and Software Development Engineer in the Deep Learning Technology Center of Microsoft Research, Redmond. In 2013, he worked as an research intern in DLTC team where he developed and implemented Convolutional-DSSM model, which is broadly applied to IR and recommendation tasks. He obtained his PhD from Kent State University in May 2015. More recently, he and colleagues developed ReasoNet for machine reading comprehension tasks. His main research interest includes reinforcement learning and natural language understanding.
- 10:00–10.30: General track paper presentations (12 + 3 mins each)
- RE-PACRR: A Context and Density-Aware Neural Information Retrieval Model – Kai Hui, Andrew Yates, Klaus Berberich and Gerard de Melo
- Microblog Retrieval for Post-Disaster Relief: Applying and Comparing Neural IR Models – Prannay Khosla, Moumita Basu, Kripabandhu Ghosh and Saptarshi Ghosh
Coffee break (10:30 – 10:50)
Morning session II (10:50 – 12:10)
(Chair: Nick Craswell)
- 10:50–11:40: TREC talks (8 + 2 mins each)
- Complex Answers Retrieval – Laura Dietz
- Real-Time Summarization – Jimmy Lin
- Tasks – Emine Yilmaz
- Dynamic Domain – Grace Hui Yang
- Open Search – Krisztian Balog
- 11:40–12:10: Special track paper presentations (12 + 3 mins each)
- Semantic Entity Retrieval Toolkit – Christophe Van Gysel, Maarten de Rijke and Evangelos Kanoulas
- An Approach for Weakly-Supervised Deep Information Retrieval – Sean MacAvaney, Kai Hui and Andrew Yates
Lunch (12:10 – 14:00)
Afternoon I (14:00 – 15:30)
(Chair: Jiafeng Guo)
- 14:00–14:30: General track paper presentations (12 + 3 mins each)
- Thread Reconstruction in Conversational Data using Neural Coherence Models. Dat Tien Nguyen, Shafiq Joty, Basma El Amel Boussaha and Maarten de Rijke
- Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation. Liu Yang, Hamed Zamani, Yongfeng Zhang, Jiafeng Guo and Bruce Croft
- 14:30–15:30: Poster session (60 mins)
Coffee break (15:30 – 15:50)
Afternoon II (15:50 – 17:20)
(Chair: Maarten de Rijke)
- 15:50–16:50: Panel discussion (60 mins)
- Fernando Diaz
- Claudia Hauff
- Jian-Yun Nie
- 16:50–17:20: Wrap-up discussion and closing (30 mins)
