1 code implementation • NAACL (DLG4NLP) 2022 • Zhenyun Deng, Yonghua Zhu, Qianqian Qi, Michael Witbrock, Patricia Riddle
Current graph-neural-network-based (GNN-based) approaches to multi-hop questions integrate clues from scattered paragraphs in an entity graph, achieving implicit reasoning by synchronous update of graph node representations using information from neighbours; this is poorly suited for explaining how clues are passed through the graph in hops.
no code implementations • 31 May 2024 • Qianqian Qi, David J. Hessen, Peter G. M. van der Heijden
Popular word embedding methods such as GloVe and Word2Vec are related to the factorization of the pointwise mutual information (PMI) matrix.
no code implementations • 14 Mar 2023 • Qianqian Qi, David J. Hessen, Peter G. M. van der Heijden
The elements of the raw document-term matrix are weighted, and the weighting exponent of singular values is adjusted to improve the performance of LSA.
no code implementations • COLING 2022 • Zhenyun Deng, Yonghua Zhu, Yang Chen, Qianqian Qi, Michael Witbrock, Patricia Riddle
In this paper, we propose the Prompt-based Conservation Learning (PCL) framework for multi-hop QA, which acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop QA tasks, mitigating forgetting.
no code implementations • 19 Nov 2021 • Lin Ni, Qiming Bao, Xiaoxuan Li, Qianqian Qi, Paul Denny, Jim Warren, Michael Witbrock, Jiamou Liu
We propose DeepQR, a novel neural-network model for AQQR that is trained using multiple-choice-question (MCQ) datasets collected from PeerWise, a widely-used learnersourcing platform.
no code implementations • 25 Jul 2021 • Qianqian Qi, David J. Hessen, Tejaswini Deoskar, Peter G. M. van der Heijden
In this article, we present a theoretical analysis and comparison of the two techniques in the context of document-term matrices.