2024
pdf
bib
abs
“In-Dialogues We Learn”: Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
Chuanqi Cheng
|
Quan Tu
|
Wei Wu
|
Shuo Shang
|
Cunli Mao
|
Zhengtao Yu
|
Rui Yan
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas. However, most existing approaches rely on pre-defined personal profiles, which are not only time-consuming and labor-intensive to create but also lack flexibility. We propose In-Dialogue Learning (IDL), a fine-tuning framework that enhances the ability of pre-trained large language models to leverage dialogue history to characterize persona for personalized dialogue generation tasks without pre-defined profiles. Our experiments on three datasets demonstrate that IDL brings substantial improvements, with BLEU and ROUGE scores increasing by up to 200% and 247%, respectively. Additionally, the results of human evaluations further validate the efficacy of our proposed method.
pdf
bib
abs
Representation Alignment and Adversarial Networks for Cross-lingual Dependency Parsing
Ying Li
|
Jianjian Liu
|
Zhengtao Yu
|
Shengxiang Gao
|
Yuxin Huang
|
Cunli Mao
Findings of the Association for Computational Linguistics: EMNLP 2024
With the strong representational capabilities of pre-trained language models, dependency parsing in resource-rich languages has seen significant advancements. However, the parsing accuracy drops sharply when the model is transferred to low-resource language due to distribution shifts. To alleviate this issue, we propose a representation alignment and adversarial model to filter out useful knowledge from rich-resource language and ignore useless ones. Our proposed model consists of two components, i.e., an alignment network in the input layer for selecting useful language-specific features and an adversarial network in the encoder layer for augmenting the language-invariant contextualized features. Experiments on the benchmark datasets show that our proposed model outperforms RoBERTa-enhanced strong baseline models by 1.37 LAS and 1.34 UAS. Detailed analysis shows that both alignment and adversarial networks are equally important in alleviating the distribution shifts problem and can complement each other. In addition, the comparative experiments demonstrate that both the alignment and adversarial networks can substantially facilitate extracting and utilizing relevant target language features, thereby increasing the adaptation capability of our proposed model.
2023
pdf
bib
abs
Non-parallel Accent Transfer based on Fine-grained Controllable Accent Modelling
Linqin Wang
|
Zhengtao Yu
|
Yuanzhang Yang
|
Shengxiang Gao
|
Cunli Mao
|
Yuxin Huang
Findings of the Association for Computational Linguistics: EMNLP 2023
Existing accent transfer works rely on parallel data or speech recognition models. This paper focuses on the practical application of accent transfer and aims to implement accent transfer using non-parallel datasets. The study has encountered the challenge of speech representation disentanglement and modeling accents. In our accent modeling transfer framework, we manage to solve these problems by two proposed methods. First, we learn the suprasegmental information associated with tone to finely model the accents in terms of tone and rhythm. Second, we propose to use mutual information learning to disentangle the accent features and control the accent of the generated speech during the inference time. Experiments show that the proposed framework attains superior performance to the baseline models in terms of accentedness and audio quality.
pdf
bib
abs
融合多粒度特征的缅甸语文本图像识别方法(Burmese Language Recognition Method Fused with Multi-Granularity Features)
Enyu He (何恩宇)
|
Rui Chen (陈蕊)
|
Cunli Mao (毛存礼)
|
Yuxin Huang (黄于欣)
|
Shengxaing Gao (高盛祥)
|
Zhengtao Yu (余正涛)
Proceedings of the 22nd Chinese National Conference on Computational Linguistics
“缅甸语属于东南亚低资源语言,缅甸语文本图像识别对开展缅甸语机器翻译等任务具有重要意义。由于缅甸语属于典型的字符组合型语言,一个感受野内存在多个字符嵌套,现有缅甸语识别方法主要是从字符粒度进行识别,在解码时会出现某些字符未能正确识别而导致局部乱码。考虑到缅甸语存在特殊的字符组合规则,本文提出了一种融合多粒度特征的缅甸语文本图像识别方法,将较细粒度的字符粒度和较粗粒度的字符簇粒度进行序列建模,然后将两种粒度特征序列进行融合后利用解码器进行解码。实验结果表明,该方法能够有效缓解识别结果乱码的现象,并且在人工构建的数据集上相比“VGG16+BiLSTM+Transformer”的基线模型识别准确率提高2.4%,达到97.35%。 "
pdf
bib
abs
相似音节增强的越汉跨语言实体消歧方法(Similar syllable enhanced cross-lingual entity disambiguation for Vietnamese-Chinese)
Yujuan Li (李裕娟)
|
Ran Song (宋燃)
|
Cunli Mao (毛存礼)
|
Yuxin Huang (黄于欣)
|
Shengxiang Gao (高盛祥)
|
Shan Lu (陆杉)
Proceedings of the 22nd Chinese National Conference on Computational Linguistics
“跨语言实体消歧是在源语言句子中找到目标语言相对应的实体,对跨语言自然语言处理任务有重要支撑。现有跨语言实体消歧方法在资源丰富的语言上能得到较好的效果,但在资源稀缺的语种上效果不佳,其中越南语-汉语就是一对典型的低资源语言;另一方面,汉语和越南语是非同源语言存在较大差异,跨语言表征困难;因此现有的方法很难适用于越南语-汉语的实体消歧。事实上,汉语和越南语具有相似的音节特点,能够增强越-汉跨语言的实体表示。为更好的融合音节特征,我们提出相似音节增强的越汉跨语言实体消歧方法,缓解了越南语-汉语数据稀缺和语言差异导致性能不佳。实验表明,所提出方法优于现有的实体消歧方法,在R@1指标下提升了5.63%。”
2022
pdf
bib
abs
融入音素特征的英-泰-老多语言神经机器翻译方法(English-Thai-Lao multilingual neural machine translation fused with phonemic features)
Zheng Shen (沈政)
|
Cunli Mao (毛存礼)
|
Zhengtao Yu (余正涛)
|
Shengxiang Gao (高盛祥)
|
Linqin Wang (王琳钦)
|
Yuxin Huang (黄于欣)
Proceedings of the 21st Chinese National Conference on Computational Linguistics
“多语言神经机器翻译是提升低资源语言翻译质量的有效手段。由于不同语言之间字符差异较大,现有方法难以得到统一的词表征形式。泰语和老挝语属于具有音素相似性的低资源语言,考虑到利用语言相似性能够拉近语义距离,提出一种融入音素特征的多语言词表征学习方法:(1)设计音素特征表示模块和泰老文本表示模块,基于交叉注意力机制得到融合音素特征后的泰老文本表示,拉近泰老之间的语义距离;(2)在微调阶段,基于参数分化得到不同语言对特定的训练参数,缓解联合训练造成模型过度泛化的问题。实验结果表明在ALT数据集上,提出方法在泰-英和老-英两个翻译方向上,相比基线模型提升0.97和0.99个BLEU值。”
pdf
bib
abs
融合双重注意力机制的缅甸语图像文本识别方法(Burmese image text recognition method with dual attention mechanism)
Fengxiao Wang (王奉孝)
|
Cunli Mao (毛存礼)
|
Zhengtao Yu (余正涛)
|
Shengxiang Gao (高盛祥)
|
Huang Yuxin (黄于欣)
|
Fuhao Liu (刘福浩)
Proceedings of the 21st Chinese National Conference on Computational Linguistics
“由于缅甸语字符具有独特的语言编码结构以及字符组合规则,现有图像文本识别方法在缅甸语图像识别任务中无法充分关注文字边缘的特征,会导致缅甸语字符上下标丢失的问题。因此,本文基于Transformer框架的图像文本识别方法做出改进,提出一种融合通道和空间注意力机制的视觉关注模块,旨在捕获像素级成对关系和通道依赖关系,降低缅甸语图像中噪声干扰从而获得语义更完整的特征图。此外,在解码过程中,将基于多头注意力的解码单元组合为解码器,用于将特征序列转化为缅甸语文字。实验结果表明,该方法在自构的缅甸语图像文本识别数据集上相比Transformer识别准确率提高0.5%,达到95.3%。”
2021
pdf
bib
abs
基于模型不确定性约束的半监督汉缅神经机器翻译(Semi-Supervised Chinese-Myanmar Neural Machine Translation based Model-Uncertainty)
Linqin Wang (王琳钦)
|
Zhengtao Yu (余正涛)
|
Cunli Mao (毛存礼)
|
Chengxiang Gao (高盛祥)
|
Zhibo Man (满志博)
|
Zhenhan Wang (王振晗)
Proceedings of the 20th Chinese National Conference on Computational Linguistics
基于回译的半监督神经机器翻译方法在低资源神经机器翻译取得了明显的效果,然而,由于汉缅双语资源稀缺、结构差异较大,传统基于Transformer的回译方法中编码端的Self-attention机制不能有效区别回译中产生的伪平行数据的噪声对句子编码的影响,致使译文出现漏译,多译,错译等问题。为此,该文提出基于模型不确定性为约束的半监督汉缅神经机器翻译方法,在Transformer网络中利用基于变分推断的蒙特卡洛Dropout构建模型不确定性注意力机制,获取到能够区分噪声数据的句子向量表征,在此基础上与Self-attention机制得到的句子编码向量进行融合,以此得到句子有效编码表征。实验证明,本文方法相比传统基于Transformer的回译方法在汉语-缅甸语和缅甸语-汉语两个翻译方向BLEU值分别提升了4.01和1.88个点,充分验证了该方法在汉缅神经翻译任务的有效性。
pdf
bib
abs
融合多层语义特征图的缅甸语图像文本识别方法(Burmese Image Text Recognition Method Fused with Multi-layer Semantic Feature Maps)
Fuhao Liu (刘福浩)
|
Cunli Mao (毛存礼)
|
Zhengtao Yu (余正涛)
|
Chengxiang Gao (高盛祥)
|
Linqin Wang (王琳钦)
|
Xuyang Xie (谢旭阳)
Proceedings of the 20th Chinese National Conference on Computational Linguistics
由于缅甸语存在特殊的字符组合结构,在图像文本识别研究方面存在较大的困难,直接利用现有的图像文本识别方法识别缅甸语图片存在字符缺失和复杂背景下识别效果不佳的问题。因此,本文提出一种融合多层语义特征图的缅甸语图像文本识别方法,利用深度卷积网络获得多层图像特征并对其融合获取多层语义信息,缓解缅甸语图像中由于字符嵌套导致特征丢失的问题。另外,在训练阶段采用MIX UP的策略进行网络参数优化,提高模型的泛化能力,降低模型在测试阶段对训练样本产生的依赖。实验结果表明,提出方法相比基线模型准确率提升了2.2%。
pdf
bib
abs
融合多粒度特征的低资源语言词性标记和依存分析联合模型(A Joint Model with Multi-Granularity Features of Low-resource Language POS Tagging and Dependency Parsing)
Sha Lu (陆杉)
|
Cunli Mao (毛存礼)
|
Zhengtao Yu (余正涛)
|
Chengxiang Gao (高盛祥)
|
Yuxin Huang (黄于欣)
|
Zhenhan Wang (王振晗)
Proceedings of the 20th Chinese National Conference on Computational Linguistics
研究低资源语言的词性标记和依存分析对推动低资源自然语言处理任务有着重要的作用。针对低资源语言词嵌入表示,已有工作并没有充分利用字符、子词层面信息编码,导致模型无法利用不同粒度的特征,对此,提出融合多粒度特征的词嵌入表示,利用不同的语言模型分别获得字符、子词以及词语层面的语义信息,将三种粒度的词嵌入进行拼接,达到丰富语义信息的目的,缓解由于标注数据稀缺导致的依存分析模型性能不佳的问题。进一步将词性标记和依存分析模型进行联合训练,使模型之间能相互共享知识,降低词性标记错误在依存分析任务上的线性传递。以泰语、越南语为研究对象,在宾州树库数据集上,提出方法相比于基线模型的UAS、LAS、POS均有明显提升。
2020
pdf
bib
abs
基于多语言联合训练的汉-英-缅神经机器翻译方法(Chinese-English-Burmese Neural Machine Translation Method Based on Multilingual Joint Training)
Zhibo Man (满志博)
|
Cunli Mao (毛存礼)
|
Zhengtao Yu (余正涛)
|
Xunyu Li (李训宇)
|
Shengxiang Gao (高盛祥)
|
Junguo Zhu (朱俊国)
Proceedings of the 19th Chinese National Conference on Computational Linguistics
多语言神经机器翻译是解决低资源神经机器翻译的有效方法,现有方法通常依靠共享词表的方式解决英语、法语以及德语相似语言之间的多语言翻译问题。缅甸语属于一种典型的低资源语言,汉语、英语以及缅甸语之间的语言结构差异性较大,为了缓解由于差异性引起的共享词表大小受限制的问题,提出一种基于多语言联合训练的汉英缅神经机器翻译方法。在Transformer框架下将丰富的汉英平行语料与汉缅、英缅的语料进行联合训练,模型训练过程中分别在编码端和解码端将汉英缅映射在同一语义空间降低汉英缅语言结构差异性对共享词表的影响,通过共享汉英语料训练参数来弥补汉缅数据缺失的问题。实验表明在一对多、多对多的翻译场景下,提出方法相比基线模型的汉-英、英-缅以及汉-缅的BLEU值有明显的提升。