Yonghong Yan


Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable
Ruiliu Fu | Han Wang | Xuejun Zhang | Jun Zhou | Yonghong Yan
Findings of the Association for Computational Linguistics: EMNLP 2021

Multi-hop QA requires the machine to answer complex questions through finding multiple clues and reasoning, and provide explanatory evidence to demonstrate the machine’s reasoning process. We propose Relation Extractor-Reader and Comparator (RERC), a three-stage framework based on complex question decomposition. The Relation Extractor decomposes the complex question, and then the Reader answers the sub-questions in turn, and finally the Comparator performs numerical comparison and summarizes all to get the final answer, where the entire process itself constitutes a complete reasoning evidence path. In the 2WikiMultiHopQA dataset, our RERC model has achieved the state-of-the-art performance, with a winning joint F1 score of 53.58 on the leaderboard. All indicators of our RERC are close to human performance, with only 1.95 behind the human level in F1 score of support fact. At the same time, the evidence path provided by our RERC framework has excellent readability and faithfulness.


Discriminating between Similar Languages on Imbalanced Conversational Texts
Junqing He | Xian Huang | Xuemin Zhao | Yan Zhang | Yonghong Yan
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

HCCL at SemEval-2018 Task 8: An End-to-End System for Sequence Labeling from Cybersecurity Reports
Mingming Fu | Xuemin Zhao | Yonghong Yan
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper describes HCCL team systems that participated in SemEval 2018 Task 8: SecureNLP (Semantic Extraction from cybersecurity reports using NLP). To solve the problem, our team applied a neural network architecture that benefits from both word and character level representaions automatically, by using combination of Bi-directional LSTM, CNN and CRF (Ma and Hovy, 2016). Our system is truly end-to-end, requiring no feature engineering or data preprocessing, and we ranked 4th in the subtask 1, 7th in the subtask2 and 3rd in the SubTask2-relaxed.


HCCL at SemEval-2017 Task 2: Combining Multilingual Word Embeddings and Transliteration Model for Semantic Similarity
Junqing He | Long Wu | Xuemin Zhao | Yonghong Yan
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

In this paper, we introduce an approach to combining word embeddings and machine translation for multilingual semantic word similarity, the task2 of SemEval-2017. Thanks to the unsupervised transliteration model, our cross-lingual word embeddings encounter decreased sums of OOVs. Our results are produced using only monolingual Wikipedia corpora and a limited amount of sentence-aligned data. Although relatively little resources are utilized, our system ranked 3rd in the monolingual subtask and can be the 6th in the cross-lingual subtask.


Distributional Representations of Words for Short Text Classification
Chenglong Ma | Weiqun Xu | Peijia Li | Yonghong Yan
Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing

IOA: Improving SVM Based Sentiment Classification Through Post Processing
Peijia Li | Weiqun Xu | Chenglong Ma | Jia Sun | Yonghong Yan
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

A Shallow Discourse Parsing System Based On Maximum Entropy Model
Jia Sun | Peijia Li | Weiqun Xu | Yonghong Yan
Proceedings of the Nineteenth Conference on Computational Natural Language Learning - Shared Task


Markovian Discriminative Modeling for Dialog State Tracking
Hang Ren | Weiqun Xu | Yonghong Yan
Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)


Dialog State Tracking using Conditional Random Fields
Hang Ren | Weiqun Xu | Yan Zhang | Yonghong Yan
Proceedings of the SIGDIAL 2013 Conference


Semantic class induction and its application for a Chinese voice search system
Yali Li | Weiqun Xu | Yonghong Yan
CIPS-SIGHAN Joint Conference on Chinese Language Processing