Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games

Feng, Yufei; Yu, Mo; Xiong, Wenhan; Guo, Xiaoxiao; Huang, Junjie; Chang, Shiyu; Campbell, Murray; Greenspan, Michael; Zhu, Xiaodan

doi:10.21428/594757db.ce391ef3

Cited by 3 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is mainly due to the following four reasons: 1) Tools not open-source, like Sherpa-ai [63] 2) Missing repositories: is the case of tools that have not yet released their codes after the paper publication: Chiron [65], FedHealth [66], FAE [67], GENO [68], FedTGan [69] and IPLS [71]. 3) Coherent but not suitable: is the case of LEAF [45], FL-Bench [70], and PyFed [57], which are positioned for benchmarking purposes and, therefore, might lack essential features for conducting more extensive research activities. FedGraphNN [46] is a sub-project of the more significant initiative called FedML [40] already included in this survey.…”

Section: Easy Integration With Other Toolsmentioning

confidence: 99%

FeLebrities: a user-centric assessment of Federated Learning frameworks

Riviera¹,

Galazzo²,

Menegaz³

2023

Preprint

View full text Add to dashboard Cite

<p>Federated Learning (FL) is a new paradigm aiming to solve the data access problem. It is gaining an increasing interest in a variety of research fields, including the Biomedical and Financial environments, where lots of valuable data sources are available but not often directly accessible due to the regulations that protect sensitive information. FL provides a solution by moving the focus from sharing data to sharing models. The FL paradigm involves different entities (institutions) holding proprietary datasets, contributing with each other to train a global Artificial Intelligence (AI) model using their own locally available data. Although several studies propose ways to distribute the computation or aggregate results, fewer efforts have been made on how to implement it. With the ambition of helping accelerate the exploitation of FL frameworks, this paper proposes a survey of public tools that are currently available for building FL pipelines, an objective ranking based on the current state of user preferences, and the assessment of the growing trend of the tool’s popularity over a six months time window. Finally, a ranking of the maturity of the tools is derived based on keyaspects to consider when building an FL pipeline. </p>

show abstract

Section: Easy Integration With Other Toolsmentioning

confidence: 99%

FeLebrities: a user-centric assessment of Federated Learning frameworks

Riviera¹,

Galazzo²,

Menegaz³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…2) Missing repositories: is the case of tools that have not yet released their codes after the paper publication: Chiron [72], FedHealth [73], FAE [74], GENO [75], FedTGan [76] and IPLS [78]. 3) Coherent but not suitable: is the case of LEAF [52], FL-Bench [77], and PyFed [64], which are positioned for benchmarking purposes and, therefore, might lack essential features for conducting more extensive research activities. FedGraphNN [53] is a sub-project of the more significant initiative called FedML [48] already included in this survey.…”

Section: A Evaluation Metricsmentioning

confidence: 99%

FeLebrities: A User-Centric Assessment of Federated Learning Frameworks

Riviera,

Galazzo,

Menegaz

2023

IEEE Access

View full text Add to dashboard Cite

Federated Learning (FL) is a new paradigm aiming to solve the data access problem. It provides a solution by moving the focus from sharing data to sharing models. The FL paradigm involves different entities (institutions) holding proprietary datasets, contributing with each other to train a global Artificial Intelligence (AI) model using their own locally available data. Although several studies propose ways to distribute the computation or aggregate results, fewer efforts have been made on how to implement FL pipelines. With the ambition of helping accelerate the exploitation of FL frameworks, this paper proposes a survey of public tools that are currently available for building FL pipelines, an objective ranking based on the current state of user preferences, and the assessment of the growing trend of the tool's popularity over a one year time window, with measurements performed every six months. These measurements include objective metrics, like the number of "Watch," "Star" and "Follow" available from software repositories as well as thirteen custom metrics grouped into three main categories: Usability, Portability, and Flexibility. Finally, a ranking of the maturity of the tools is derived based on key aspects to consider when building a FL pipeline.INDEX TERMS Federated Learning tools, Distributed systems, AI at scale.

show abstract

“…Graph-based models (De Cao et al, 2018;Fang et al, 2019;Ding et al, 2019) utilize graph structure and graph neural network to model the connections among sentences or entities for multi-hop QA. There are works adopting chain-like reasoning to solve multi-hop textual QA (Chen et al, 2019a;Asai et al, 2019;Feng et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Reasoning over Hybrid Chain for Table-and-Text Open Domain QA

Zhong¹,

Huang²,

Liu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Tabular and textual question answering requires systems to perform reasoning over heterogeneous information, considering table structure, and the connections among table and text. In this paper, we propose a ChAincentric Reasoning and Pre-training framework (CARP). CARP utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering.We also propose a novel chain-centric pretraining method, to enhance the pre-trained model in identifying the cross-modality reasoning process and alleviating the data sparsity problem. This method constructs the large-scale reasoning corpus by synthesizing pseudo heterogeneous reasoning paths from Wikipedia and generating corresponding questions. We evaluate our system on OTT-QA, a large-scale table-and-text open-domain question answering benchmark, and our system achieves the state-of-the-art performance. Further analyses illustrate that the explicit hybrid chain offers substantial performance improvement and interpretablity of the intermediate reasoning process, and the chain-centric pretraining boosts the performance on the chain extraction.

show abstract

Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games

Cited by 3 publications

References 21 publications

FeLebrities: a user-centric assessment of Federated Learning frameworks

FeLebrities: a user-centric assessment of Federated Learning frameworks

FeLebrities: A User-Centric Assessment of Federated Learning Frameworks

Reasoning over Hybrid Chain for Table-and-Text Open Domain QA

Contact Info

Product

Resources

About