Yue Hu


pdf bib
IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation
Yuqiang Xie | Luxi Xing | Wei Peng | Yue Hu
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

This paper introduces our systems for all three subtasks of SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning. To help our model better represent and understand abstract concepts in natural language, we well-design many simple and effective approaches adapted to the backbone model (RoBERTa). Specifically, we formalize the subtasks into the multiple-choice question answering format and add special tokens to abstract concepts, then, the final prediction of QA is considered as the result of subtasks. Additionally, we employ many finetuning tricks to improve the performance. Experimental results show that our approach gains significant performance compared with the baseline systems. Our system achieves eighth rank (87.51%) and tenth rank (89.64%) on the official blind test set of subtask 1 and subtask 2 respectively.


pdf bib
Comparison of the effects of attention mechanism on translation tasks of different lengths of ambiguous words
Yue Hu | Jiahao Qin | Zemeiqi Chen | Jingshi Zhou | Xiaojun Zhang
Proceedings of the Second International Workshop of Discourse Processing

In recent years, attention mechanism has been widely used in various neural machine translation tasks based on encoder decoder. This paper focuses on the performance of encoder decoder attention mechanism in word sense disambiguation task with different text length, trying to find out the influence of context marker on attention mechanism in word sense disambiguation task. We hypothesize that attention mechanisms have similar performance when translating texts of different lengths. Our conclusion is that the alignment effect of attention mechanism is magnified in short text translation tasks with ambiguous nouns, while the effect of attention mechanism is far less than expected in long-text tasks, which means that attention mechanism is not the main mechanism for NMT model to feed WSD to integrate context information. This may mean that attention mechanism pays more attention to ambiguous nouns than context markers. The experimental results show that with the increase of text length, the performance of NMT model using attention mechanism will gradually decline.

pdf bib
IIE’s Neural Machine Translation Systems for WMT20
Xiangpeng Wei | Ping Guo | Yunpeng Li | Xingsheng Zhang | Luxi Xing | Yue Hu
Proceedings of the Fifth Conference on Machine Translation

In this paper we introduce the systems IIE submitted for the WMT20 shared task on German-French news translation. Our systems are based on the Transformer architecture with some effective improvements. Multiscale collaborative deep architecture, data selection, back translation, knowledge distillation, domain adaptation, model ensemble and re-ranking are employed and proven effective in our experiments. Our German-to-French system achieved 35.0 BLEU and ranked the second among all anonymous submissions, and our French-to-German system achieved 36.6 BLEU and ranked the fourth in all anonymous submissions.

pdf bib
Bi-directional CognitiveThinking Network for Machine Reading Comprehension
Wei Peng | Yue Hu | Luxi Xing | Yuqiang Xie | Jing Yu | Yajing Sun | Xiangpeng Wei
Proceedings of the 28th International Conference on Computational Linguistics

We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory. It aims to simulate two ways of thinking in the brain to answer questions, including reverse thinking and inertial thinking. To validate the effectiveness of our framework, we design a corresponding Bi-directional Cognitive Thinking Network (BCTN) to encode the passage and generate a question (answer) given an answer (question) and decouple the bi-directional knowledge. The model has the ability to reverse reasoning questions which can assist inertial thinking to generate more accurate answers. Competitive improvement is observed in DuReader dataset, confirming our hypothesis that bi-directional knowledge helps the QA task. The novel framework shows an interesting perspective on machine reading comprehension and cognitive science.

pdf bib
IIE-NLP-NUT at SemEval-2020 Task 4: Guiding PLM with Prompt Template Reconstruction Strategy for ComVE
Luxi Xing | Yuqiang Xie | Yue Hu | Wei Peng
Proceedings of the Fourteenth Workshop on Semantic Evaluation

This paper introduces our systems for the first two subtasks of SemEval Task4: Commonsense Validation and Explanation. To clarify the intention for judgment and inject contrastive information for selection, we propose the input reconstruction strategy with prompt templates. Specifically, we formalize the subtasks into the multiple-choice question answering format and construct the input with the prompt templates, then, the final prediction of question answering is considered as the result of subtasks. Experimental results show that our approaches achieve significant performance compared with the baseline systems. Our approaches secure the third rank on both official test sets of the first two subtasks with an accuracy of 96.4 and an accuracy of 94.3 respectively.

pdf bib
Uncertainty-Aware Semantic Augmentation for Neural Machine Translation
Xiangpeng Wei | Heng Yu | Yue Hu | Rongxiang Weng | Luxi Xing | Weihua Luo
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other. However, the dominant methods for NMT only observe one of them from the parallel corpora for the model training but have to deal with adequate variations under the same meaning at inference. This leads to a discrepancy of the data distribution between the training and the inference phases. To address this problem, we propose uncertainty-aware semantic augmentation, which explicitly captures the universal semantic information among multiple semantically-equivalent source sentences and enhances the hidden representations with this information for better translations. Extensive experiments on various translation tasks reveal that our approach significantly outperforms the strong baselines and the existing methods.

pdf bib
Multiscale Collaborative Deep Models for Neural Machine Translation
Xiangpeng Wei | Heng Yu | Yue Hu | Yue Zhang | Rongxiang Weng | Weihua Luo
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Recent evidence reveals that Neural Machine Translation (NMT) models with deeper neural networks can be more effective but are difficult to train. In this paper, we present a MultiScale Collaborative (MSC) framework to ease the training of NMT models that are substantially deeper than those used previously. We explicitly boost the gradient back-propagation from top to bottom levels by introducing a block-scale collaboration mechanism into deep NMT models. Then, instead of forcing the whole encoder stack directly learns a desired representation, we let each encoder block learns a fine-grained representation and enhance it by encoding spatial dependencies using a context-scale collaboration. We provide empirical evidence showing that the MSC nets are easy to optimize and can obtain improvements of translation quality from considerably increased depth. On IWSLT translation tasks with three translation directions, our extremely deep models (with 72-layer encoders) surpass strong baselines by +2.2~+3.1 BLEU points. In addition, our deep MSC achieves a BLEU score of 30.56 on WMT14 English-to-German task that significantly outperforms state-of-the-art deep NMT models. We have included the source code in supplementary materials.

pdf bib
基于Graph Transformer的知识库问题生成(Question Generation from Knowledge Base with Graph Transformer)
Yue Hu (胡月) | Guangyou Zhou (周光有)
Proceedings of the 19th Chinese National Conference on Computational Linguistics

知识库问答依靠知识库推断答案需大量带标注信息的问答对,但构建大规模且精准的数据集不仅代价昂贵,还受领域等因素限制。为缓解数据标注问题,面向知识库的问题生成任务引起了研究者关注,该任务是利用知识库三元组自动生成问题。现有方法仅由一个三元组生成的问题简短且缺乏多样性。为生成信息量丰富且多样化的问题,本文采用Graph Transformer和BERT两个编码层来加强三元组多粒度语义表征以获取背景信息。在SimpleQuestions上的实验结果证明了该方法有效性。


pdf bib
Unsupervised Neural Machine Translation with Future Rewarding
Xiangpeng Wei | Yue Hu | Luxi Xing | Li Gao
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

In this paper, we alleviate the local optimality of back-translation by learning a policy (takes the form of an encoder-decoder and is defined by its parameters) with future rewarding under the reinforcement learning framework, which aims to optimize the global word predictions for unsupervised neural machine translation. To this end, we design a novel reward function to characterize high-quality translations from two aspects: n-gram matching and semantic adequacy. The n-gram matching is defined as an alternative for the discrete BLEU metric, and the semantic adequacy is used to measure the adequacy of conveying the meaning of the source sentence to the target. During training, our model strives for earning higher rewards by learning to produce grammatically more accurate and semantically more adequate translations. Besides, a variational inference network (VIN) is proposed to constrain the corresponding sentences in two languages have the same or similar latent semantic code. On the widely used WMT’14 English-French, WMT’16 English-German and NIST Chinese-to-English benchmarks, our models respectively obtain 27.59/27.15, 19.65/23.42 and 22.40 BLEU points without using any labeled data, demonstrating consistent improvements over previous unsupervised NMT models.


pdf bib
BrailleSUM: A News Summarization System for the Blind and Visually Impaired People
Xiaojun Wan | Yue Hu
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)


pdf bib
Automatic Generation of Related Work Sections in Scientific Papers: An Optimization Approach
Yue Hu | Xiaojun Wan
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Word Clustering Based on Un-LP Algorithm
Jiguang Liang | Xiaofei Zhou | Yue Hu | Li Guo | Shuo Bai
Proceedings of the First AHA!-Workshop on Information Discovery in Text