Huihui Zhang


pdf bib
Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering
Weiwen Xu | Huihui Zhang | Deng Cai | Wai Lam
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Exploiting Reasoning Chains for Multi-hop Science Question Answering
Weiwen Xu | Yang Deng | Huihui Zhang | Deng Cai | Wai Lam
Findings of the Association for Computational Linguistics: EMNLP 2021

We propose a novel Chain Guided Retriever-reader (CGR) framework to model the reasoning chain for multi-hop Science Question Answering. Our framework is capable of performing explainable reasoning without the need of any corpus-specific annotations, such as the ground-truth reasoning chain, or human-annotated entity mentions. Specifically, we first generate reasoning chains from a semantic graph constructed by Abstract Meaning Representation of retrieved evidence facts. A Chain-aware loss, concerning both local and global chain information, is also designed to enable the generated chains to serve as distant supervision signals for training the retriever, where reinforcement learning is also adopted to maximize the utility of the reasoning chains. Our framework allows the retriever to capture step-by-step clues of the entire reasoning process, which is not only shown to be effective on two challenging multi-hop Science QA tasks, namely OpenBookQA and ARC-Challenge, but also favors explainability.


pdf bib
BERTatDE at SemEval-2020 Task 6: Extracting Term-definition Pairs in Free Text Using Pre-trained Model
Huihui Zhang | Feiliang Ren
Proceedings of the Fourteenth Workshop on Semantic Evaluation

Definition extraction is an important task in Nature Language Processing, and it is used to identify the terms and definitions related to terms. The task contains sentence classification task (i.e., classify whether it contains definition) and sequence labeling task (i.e., find the boundary of terms and definitions). The paper describes our system BERTatDE1 in sentence classification task (subtask 1) and sequence labeling task (subtask 2) in the definition extraction (SemEval-2020 Task 6). We use BERT to solve the multi-domain problems including the uncertainty of term boundary that is, different areas have different ways to definite the domain related terms. We use BERT, BiLSTM and attention in subtask 1 and our best result achieved 79.71% in F1 and the eighteenth place in subtask 1. For the subtask 2, we use BERT, BiLSTM and CRF to sequence labeling, and achieve 40.73% in Macro-averaged F1.

pdf bib
Knowledge Graph Embedding with Atrous Convolution and Residual Learning
Feiliang Ren | Juchen Li | Huihui Zhang | Shilei Liu | Bochao Li | Ruicheng Ming | Yujia Bai
Proceedings of the 28th International Conference on Computational Linguistics

Knowledge graph embedding is an important task and it will benefit lots of downstream applications. Currently, deep neural networks based methods achieve state-of-the-art performance. However, most of these existing methods are very complex and need much time for training and inference. To address this issue, we propose a simple but effective atrous convolution based knowledge graph embedding method. Compared with existing state-of-the-art methods, our method has following main characteristics. First, it effectively increases feature interactions by using atrous convolutions. Second, to address the original information forgotten issue and vanishing/exploding gradient issue, it uses the residual learning method. Third, it has simpler structure but much higher parameter efficiency. We evaluate our method on six benchmark datasets with different evaluation metrics. Extensive experiments show that our model is very effective. On these diverse datasets, it achieves better results than the compared state-of-the-art methods on most of evaluation metrics. The source codes of our model could be found at