2017

Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering

Wang, Shuohang, Yu, Mo, Jiang, Jing et al.

Understand

A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers.

Existing methods usually extract answers from single passages independently.
But some questions require a combination of evidence from across different sources to answer correctly.
In this paper, we propose two models which make use of multiple passages to generate their answers.

Built on

Baseball: an automatic question-answerer
Bert F Green Jr, Alice K Wolf, Carol Chomsky, and Kenneth Laughery · 1961
Earlier work this paper cites.
Long short-term memory
Sepp Hochreiter and Jürgen Schmidhuber · 1997
Earlier work this paper cites.
The trec-8 question answering track report
Ellen M. Voorhees · 1999
Earlier work this paper cites.
Scaling question answering to the web
Cody Kwok, Oren Etzioni, and Daniel S Weld · 2001
Earlier work this paper cites.
Discriminative reranking for machine translation
Libin Shen, Anoop Sarkar, and Franz Josef Och · 2004
Earlier work this paper cites.
Discriminative reranking for natural language parsing
Michael Collins and Terry Koo · 2005
Earlier work this paper cites.
Forest reranking: Discriminative parsing with non-local features
Liang Huang · 2008
Earlier work this paper cites.
The probabilistic relevance framework: Bm25 and beyond
Stephen Robertson, Hugo Zaragoza, et al · 2009
Earlier work this paper cites.
Building watson: An overview of the deepqa project
David Ferrucci, Eric Brown, Jennifer Chu-Carroll, James Fan, David Gondek, Aditya A Kalyanpur, Adam Lally, J William Murdock, Eric Nyberg, John Prager, et al · 2010
Earlier work this paper cites.
Semantic parsing on freebase from question-answer pairs
Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang · 2013
Earlier work this paper cites.
GloVe: Global vectors for word representation
Jeffrey Pennington, Richard Socher, and Christopher D Manning · 2014
Earlier work this paper cites.
More accurate question answering on freebase
Hannah Bast and Elmar Haussmann · 2015
Earlier work this paper cites.

Similar

Modeling of the question answering task in the yodaqa system
Petr Baudiš and Jan Šedivỳ · 2015
Cited alongside, same era.
Large-scale simple question answering with memory networks
Antoine Bordes, Nicolas Usunier, Sumit Chopra, and Jason Weston · 2015
Cited alongside, same era.
Teaching machines to read and comprehend
Karl Moritz Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom · 2015
Cited alongside, same era.
Adam: A method for stochastic optimization
Diederik Kingma and Jimmy Ba · 2015
Cited alongside, same era.
Semantic parsing via staged query graph generation: Question answering with knowledge base
Wen-tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao · 2015
Cited alongside, same era.
Recurrent neural network grammars
Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, and Noah A Smith · 2016
Cited alongside, same era.
Text understanding with the attention sum reader network
Rudolf Kadlec, Martin Schmid, Ondrej Bajgar, and Jan Kleindienst · 2016
Cited alongside, same era.
A decomposable attention model for natural language inference
Ankur P Parikh, Oscar Täckström, Dipanjan Das, and Jakob Uszkoreit · 2016
Cited alongside, same era.
SQuAD: 100,000+ questions for machine comprehension of text
Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang · 2016
Cited alongside, same era.
Natural language comprehension with the epireader
Adam Trischler, Zheng Ye, Xingdi Yuan, and Kaheer Suleman · 2016
Cited alongside, same era.
Learning natural language inference with LSTM
Shuohang Wang and Jing Jiang · 2016
Cited alongside, same era.
Question answering on freebase via relation extraction and textual evidence
Kun Xu, Siva Reddy, Yansong Feng, Songfang Huang, and Dongyan Zhao · 2016
Cited alongside, same era.

Then

Ask the right questions: Active question reformulation with reinforcement learning
Original
Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Andrea Gesmundo, Neil Houlsby, Wojciech Gajewski, and Wei Wang · 2017
Closest in time.
Reading Wikipedia to answer open-domain questions
Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes · 2017
Closest in time.
Attention-over-attention neural networks for reading comprehension
Yiming Cui, Zhipeng Chen, Si Wei, Shijin Wang, Ting Liu, and Guoping Hu · 2017
Closest in time.
SearchQA: A new q&a dataset augmented with context from a search engine
Original
Matthew Dunn, Levent Sagun, Mike Higgins, Ugur Guney, Volkan Cirik, and Kyunghyun Cho · 2017
Closest in time.
Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension
Mandar Joshi, Eunsol Choi, Daniel S. Weld, and Luke Zettlemoyer · 2017
Closest in time.
Deriving neural architectures from sequence and graph kernels
Tao Lei, Wengong Jin, Regina Barzilay, and Tommi Jaakkola · 2017
Closest in time.
Bidirectional attention flow for machine comprehension
Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh Hajishirzi · 2017
Closest in time.
S-net: From answer extraction to answer generation for machine reading comprehension
Original
Chuanqi Tan, Furu Wei, Nan Yang, Weifeng Lv, and Ming Zhou · 2017
Closest in time.
Machine comprehension using match-LSTM and answer pointer
Shuohang Wang and Jing Jiang · 2017
Closest in time.
R3: Reinforced reader-ranker for open-domain question answering
Original
Shuohang Wang, Mo Yu, Xiaoxiao Guo, Zhiguo Wang, Tim Klinger, Wei Zhang, Shiyu Chang, Gerald Tesauro, Bowen Zhou, and Jing Jiang · 2017
Closest in time.
Improved neural relation detection for knowledge base question answering
Original
Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cicero dos Santos, Bing Xiang, and Bowen Zhou · 2017
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…

Reading the bibliography…