2022

TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases

Shu, Yiheng, Yu, Zhiwei, Li, Yuhan et al.

Understand

Pre-trained language models (PLMs) have shown their effectiveness in multiple scenarios.

However, KBQA remains challenging, especially regarding coverage and generalization settings.
This is due to two main factors: i) understanding the semantics of both questions and relevant knowledge from the KB; ii) generating executable logical forms with both semantic and syntactic correctness.
In this paper, we present a new KBQA model, TIARA, which addresses those issues by applying multi-grained retrieval to help the PLM focus on the most relevant KB contexts, viz., entities, exemplary logical forms, and schema items.

Built on

Freebase: a collaboratively created graph database for structuring human knowledge
Kurt D. Bollacker, Colin Evans, Praveen K. Paritosh, Tim Sturge, and Jamie Taylor. 2008 · 2008
Earlier work this paper cites.
Unik-QA: Unified representations of structured and unstructured knowledge for open-domain question answering
Original
Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, and Scott Yih. 2020 · 2012
Earlier work this paper cites.
Facc1: Freebase annotation of clueweb corpora, version 1 (release date 2013-06-26, format version 1, correction level 0)
Evgeniy Gabrilovich, Michael Ringgaard, and Amarnag Subramanya. 2013 · 2013
Earlier work this paper cites.
Semantic parsing via staged query graph generation: Question answering with knowledge base
Wen-tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao. 2015 · 2015
Earlier work this paper cites.
The value of semantic parse labeling for knowledge base question answering
Wen-tau Yih, Matthew Richardson, Christopher Meek, Ming-Wei Chang, and Jina Suh. 2016 · 2016
Earlier work this paper cites.
Neural symbolic machines: Learning semantic parsers on freebase with weak supervision
Chen Liang, Jonathan Berant, Quoc V. Le, Kenneth D. Forbus, and Ni Lao. 2017 · 2017
Earlier work this paper cites.
Open domain question answering using early fusion of knowledge bases and text
Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, and William W. Cohen. 2018 · 2018
Earlier work this paper cites.
Learning to answer complex questions over knowledge bases with query composition
Nikita Bhutani, Xinyi Zheng, and H. V. Jagadish. 2019 · 2019
Earlier work this paper cites.
Uhop: An unrestricted-hop relation extraction framework for knowledge-based question answering
Zi-Yuan Chen, Chih-Hung Chang, Yi-Pei Chen, Jijnasa Nayak, and Lun-Wei Ku. 2019 · 2019
Earlier work this paper cites.
BERT: pre-training of deep bidirectional transformers for language understanding
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019 · 2019
Earlier work this paper cites.
Knowledge base question answering with topic units
Yunshi Lan, Shuohang Wang, and Jing Jiang. 2019 · 2019
Earlier work this paper cites.
Pytorch: An imperative style, high-performance deep learning library
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019 · 2019
Earlier work this paper cites.
Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text
Haitian Sun, Tania Bedrax-Weiss, and William W. Cohen. 2019 · 2019
Earlier work this paper cites.
Language models are few-shot learners
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020 · 2020
Earlier work this paper cites.
Measuring compositional generalization: A comprehensive method on realistic data
Daniel Keysers, Nathanael Schärli, Nathan Scales, Hylke Buisman, Daniel Furrer, Sergii Kashubin, Nikola Momchev, Danila Sinopalnikov, Lukasz Stafiniak, Tibor Tihon, Dmitry Tsarkov, Xiao Wang, Marc van Zee, and Olivier Bousquet. 2020 · 2020
Earlier work this paper cites.

Similar

Query graph generation for answering multi-hop complex questions from knowledge bases
Yunshi Lan and Jing Jiang. 2020 · 2020
Cited alongside, same era.
Efficient one-pass end-to-end entity linking for questions
Belinda Z. Li, Sewon Min, Srinivasan Iyer, Yashar Mehdad, and Wen-tau Yih. 2020 · 2020
Cited alongside, same era.
Exploring the limits of transfer learning with a unified text-to-text transformer
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020 · 2020
Cited alongside, same era.
Improving multi-hop question answering over knowledge graphs using knowledge base embeddings
Apoorv Saxena, Aditay Tripathi, and Partha P. Talukdar. 2020 · 2020
Cited alongside, same era.
Neural mention detection
Juntao Yu, Bernd Bohnet, and Massimo Poesio. 2020 · 2020
Cited alongside, same era.
ReTraCk: A flexible and efficient framework for knowledge base question answering
Shuang Chen, Qian Liu, Zhiwei Yu, Chin-Yew Lin, Jian-Guang Lou, and Feng Jiang. 2021 · 2021
Cited alongside, same era.
Case-based reasoning for natural language queries over knowledge bases
Rajarshi Das, Manzil Zaheer, Dung Thai, Ameya Godbole, Ethan Perez, Jay Yoon Lee, Lizhen Tan, Lazaros Polymenakos, and Andrew McCallum. 2021 · 2021
Cited alongside, same era.
Spanner: Named entity re-/recognition as span prediction
Jinlan Fu, Xuanjing Huang, and Pengfei Liu. 2021 · 2021
Cited alongside, same era.
Beyond I.I.D.: three levels of generalization for question answering on knowledge bases
Yu Gu, Sue Kase, Michelle Vanni, Brian M. Sadler, Percy Liang, Xifeng Yan, and Yu Su. 2021 · 2021
Cited alongside, same era.
Improving multi-hop knowledge base question answering by learning intermediate supervision signals
Gaole He, Yunshi Lan, Jing Jiang, Wayne Xin Zhao, and Ji-Rong Wen. 2021 · 2021
Cited alongside, same era.
EDG-based question decomposition for complex question answering over knowledge bases
Xixin Hu, Yiheng Shu, Xiang Huang, and Yuzhong Qu. 2021 · 2021
Cited alongside, same era.
BoningKnife: Joint entity mention detection and typing for nested NER via prior boundary knowledge
Original
Huiqiang Jiang, Guoxin Wang, Weile Chen, Chengxi Zhang, and Börje F. Karlsson. 2021 · 2021
Cited alongside, same era.

Then

Transfernet: An effective and transparent framework for multi-hop question answering over relation graph
Jiaxin Shi, Shulin Cao, Lei Hou, Juanzi Li, and Hanwang Zhang. 2021 · 2021
Later among the works it cites.
Constrained language models yield few-shot semantic parsers
Richard Shin, Christopher H. Lin, Sam Thomson, Charles Chen, Subhro Roy, Emmanouil Antonios Platanios, Adam Pauls, Dan Klein, Jason Eisner, and Benjamin Van Durme. 2021 · 2021
Later among the works it cites.
Large-scale relation learning for question answering over knowledge bases with pre-trained language models
Yuanmeng Yan, Rumei Li, Sirui Wang, Hongzhi Zhang, Zan Daoguang, Fuzheng Zhang, Wei Wu, and Weiran Xu. 2021 · 2021
Later among the works it cites.
KQA pro: A dataset with explicit compositional programs for complex question answering over knowledge base
Shulin Cao, Jiaxin Shi, Liangming Pan, Lunyiu Nie, Yutong Xiang, Lei Hou, Juanzi Li, Bin He, and Hanwang Zhang. 2022a · 2022
Closest in time.
Program transfer for answering complex questions over knowledge bases
Shulin Cao, Jiaxin Shi, Zijun Yao, Xin Lv, Jifan Yu, Lei Hou, Juanzi Li, Zhiyuan Liu, and Jinghui Xiao. 2022b · 2022
Closest in time.
Arcaneqa: Dynamic program induction and contextualized encoding for knowledge base question answering
Original
Yu Gu and Yu Su. 2022 · 2022
Closest in time.
Logical form generation via multi-task learning for complex question answering over knowledge bases
Xixin Hu, Xuan Wu, Yiheng Shu, and Yuzhong Qu. 2022 · 2022
Closest in time.
MRKL systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
Original
Ehud Karpas, Omri Abend, Yonatan Belinkov, Barak Lenz, Opher Lieber, Nir Ratner, Yoav Shoham, Hofit Bata, Yoav Levine, Kevin Leyton-Brown, Dor Muhlgay, Noam Rozen, Erez Schwartz, Gal Shachaf, Shai Shalev-Shwartz, Amnon Shashua, and Moshe Tennenholtz. 2022 · 2022
Closest in time.
Synchromesh: Reliable code generation from pre-trained language models
Original
Gabriel Poesia, Oleksandr Polozov, Vu Le, Ashish Tiwari, Gustavo Soares, Christopher Meek, and Sumit Gulwani. 2022 · 2022
Closest in time.
Nearest neighbor zero-shot inference
Original
Weijia Shi, Julian Michael, Suchin Gururangan, and Luke Zettlemoyer. 2022 · 2022
Closest in time.
Chain of thought prompting elicits reasoning in large language models
Original
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed H. Chi, Quoc Le, and Denny Zhou. 2022 · 2022
Closest in time.
Unifiedskg: Unifying and multi-tasking structured knowledge grounding with text-to-text language models
Original
Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir R. Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, and Tao Yu. 2022 · 2022
Closest in time.
Rng-kbqa: Generation augmented iterative ranking for knowledge base question answering
Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, and Caiming Xiong. 2021 · 2022
Closest in time.
S 2 {}^{\mbox{2}} ql: Retrieval augmented zero-shot question answering over knowledge graph
Daoguang Zan, Wang Sirui, Zhang Hongzhi, Yan Yuanmeng, Wu Wei, Guan Bei, and Wang Yongji. 2022 · 2022
Closest in time.
Subgraph retrieval enhanced model for multi-hop knowledge base question answering
Jing Zhang, Xiaokang Zhang, Jifan Yu, Jian Tang, Jie Tang, Cuiping Li, and Hong Chen. 2022 · 2022
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…