Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning

Yichen Jiang, Mohit Bansal


Abstract
Multi-hop QA requires a model to connect multiple pieces of evidence scattered in a long context to answer the question. The recently proposed HotpotQA (Yang et al., 2018) dataset is comprised of questions embodying four different multi-hop reasoning paradigms (two bridge entity setups, checking multiple properties, and comparing two entities), making it challenging for a single neural network to handle all four. In this work, we present an interpretable, controller-based Self-Assembling Neural Modular Network (Hu et al., 2017, 2018) for multi-hop reasoning, where we design four novel modules (Find, Relocate, Compare, NoOp) to perform unique types of language reasoning. Based on a question, our layout controller RNN dynamically infers a series of reasoning modules to construct the entire network. Empirically, we show that our dynamic, multi-hop modular network achieves significant improvements over the static, single-hop baseline (on both regular and adversarial evaluation). We further demonstrate the interpretability of our model via three analyses. First, the controller can softly decompose the multi-hop question into multiple single-hop sub-questions to promote compositional reasoning behavior of the main network. Second, the controller can predict layouts that conform to the layouts designed by human experts. Finally, the intermediate module can infer the entity that connects two distantly-located supporting facts by addressing the sub-question from the controller.
Anthology ID:
D19-1455
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4474–4484
Language:
URL:
https://aclanthology.org/D19-1455
DOI:
10.18653/v1/D19-1455
Bibkey:
Cite (ACL):
Yichen Jiang and Mohit Bansal. 2019. Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4474–4484, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning (Jiang & Bansal, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/D19-1455.pdf
Code
 jiangycTarheel/NMN-MultiHopQA
Data
HotpotQASQuAD