To acquire non-ferrous metals related news from different countries’internet,we proposed a cross-lingual non-ferrous metals related news recognition method based on CNN with a limited bilingual dictionary.Firstly,con...To acquire non-ferrous metals related news from different countries’internet,we proposed a cross-lingual non-ferrous metals related news recognition method based on CNN with a limited bilingual dictionary.Firstly,considering the lack of related language resources of non-ferrous metals,we use a limited bilingual dictionary and CCA to learn cross-lingual word vector and to represent news in different languages uniformly.Then,to improve the effect of recognition,we use a variant of the CNN to learn recognition features and construct the recognition model.The experimental results show that our proposed method acquires better results.展开更多
Joint learning of words and entities is advantageous to various NLP tasks, while most of the works focus on single language setting. Cross-lingual representations learning receives high attention recently, but is stil...Joint learning of words and entities is advantageous to various NLP tasks, while most of the works focus on single language setting. Cross-lingual representations learning receives high attention recently, but is still restricted by the availability of parallel data. In this paper, a method is proposed to jointly embed texts and entities on comparable data. In addition to evaluate on public semantic textual similarity datasets, a task (cross-lingual text extraction) was proposed to assess the similarities between texts and contribute to this dataset. It shows that the proposed method outperforms cross-lingual representations methods using parallel data on cross-lingual tasks, and achieves competitive results on mono-lingual tasks.展开更多
Cross-lingual summarization(CLS)is the task of generating a summary in a target language from a document in a source language.Recently,end-to-end CLS models have achieved impressive results using large-scale,high-qual...Cross-lingual summarization(CLS)is the task of generating a summary in a target language from a document in a source language.Recently,end-to-end CLS models have achieved impressive results using large-scale,high-quality datasets typically constructed by translating monolingual summary corpora into CLS corpora.However,due to the limited performance of low-resource language translation models,translation noise can seriously degrade the performance of these models.In this paper,we propose a fine-grained reinforcement learning approach to address low-resource CLS based on noisy data.We introduce the source language summary as a gold signal to alleviate the impact of the translated noisy target summary.Specifically,we design a reinforcement reward by calculating the word correlation and word missing degree between the source language summary and the generated target language summary,and combine it with cross-entropy loss to optimize the CLS model.To validate the performance of our proposed model,we construct Chinese-Vietnamese and Vietnamese-Chinese CLS datasets.Experimental results show that our proposed model outperforms the baselines in terms of both the ROUGE score and BERTScore.展开更多
Neural networks have been widely used for English name tagging and have delivered state-of-the-art results. However, for low resource languages, due to the limited resources and lack of training data, taggers tend to ...Neural networks have been widely used for English name tagging and have delivered state-of-the-art results. However, for low resource languages, due to the limited resources and lack of training data, taggers tend to have lower performance, in comparison to the English language. In this paper, we tackle this challenging issue by incorporating multi-level cross-lingual knowledge as attention into a neural architecture, which guides low resource name tagging to achieve a better performance. Specifically, we regard entity type distribution as language independent and use bilingual lexicons to bridge cross-lingual semantic mapping. Then, we jointly apply word-level cross-lingual mutual influence and entity-type level monolingual word distributions to enhance low resource name tagging. Experiments on three languages demonstrate the effectiveness of this neural architecture： for Chinese,Uzbek, and Turkish, we are able to yield significant improvements in name tagging over all previous baselines.展开更多
This paper proposes a novel Chinese-English Cross-Lingual Information Retrieval (CECLIR) model PME, in which bilingual dictionary and comparable corpora are used to translate the query terms. The Proximity and mutua...This paper proposes a novel Chinese-English Cross-Lingual Information Retrieval (CECLIR) model PME, in which bilingual dictionary and comparable corpora are used to translate the query terms. The Proximity and mutual information of the term-pairs in the Chinese and English comparable corpora are employed not only to resolve the translation ambiguities but also to perform the query expansion so as to deal with the out-of-vocabulary issues in the CECLIR. The evaluation results show that the query precision of PME algorithm is about 84.4% of the monolingual information retrieval.展开更多
随着互联网信息的发展,如何有效地表示不同语言所含的信息已成为自然语言处理(Natural Language Processing,NLP)领域的一项重要任务.然而,很多传统的机器学习模型依赖在高资源语言中进行训练,无法迁移到低资源语言中使用.为了解决这一...随着互联网信息的发展,如何有效地表示不同语言所含的信息已成为自然语言处理(Natural Language Processing,NLP)领域的一项重要任务.然而,很多传统的机器学习模型依赖在高资源语言中进行训练,无法迁移到低资源语言中使用.为了解决这一问题,结合迁移学习和深度学习模型,提出一种多语言双向编码器表征量(Multi-lingual Bidirectional Encoder Representations from Transformers,M-BERT)的迁移学习方法.该方法利用M-BERT作为特征提取器,在源语言领域和目标语言领域之间进行特征转换,减小不同语言领域之间的差异,从而提高目标任务在不同领域之间的泛化能力.首先,在构建BERT模型的基础上,通过数据收集处理、训练设置、参数估计和模型训练等预训练操作完成M-BERT模型的构建,并在目标任务上进行微调.然后,利用迁移学习实现M-BERT模型在跨语言文本分析方面的应用.最后,在从英语到法语和德语的跨语言迁移实验中,证明了本文模型具有较高的性能质量和较小的计算量,并在联合训练方案中达到了96.2%的准确率.研究结果表明,该文模型实现了跨语言数据迁移,且验证了其在跨语言NLP领域的有效性和创新性.展开更多
跨语言文本主题发现是跨语言文本挖掘领域的重要研究方向,对跨语言文本分析和组织各种文本数据具有较高的应用价值。基于Bagging和跨语言词嵌入改进LDA主题模型,提出跨语言文本主题发现方法BCL-LDA(Bagging,Cross-lingual word embeddin...跨语言文本主题发现是跨语言文本挖掘领域的重要研究方向,对跨语言文本分析和组织各种文本数据具有较高的应用价值。基于Bagging和跨语言词嵌入改进LDA主题模型,提出跨语言文本主题发现方法BCL-LDA(Bagging,Cross-lingual word embedding with LDA),从多语言文本中挖掘关键信息。该方法首先将Bagging集成学习思想与LDA主题模型结合生成混合语言子主题集;然后利用跨语言词嵌入和K-means算法对混合子主题进行聚类分组;最后使用TF-IDF算法对主题词进行过滤排序。汉语-德语、汉语-法语主题发现实验表明,该方法在主题连贯性和多样性方面均表现优异,能够提取出语义更加相关且主题更加连贯多样的双语主题。展开更多
基金The Major Technologies R&D Special Program of Anhui,China(Grant No.16030901060)The National Natural Science Foundation of China(Grant No.61502010)+1 种基金The Natural Science Foundation of Anhui Province(Grant No.1608085QF146)The Natural Science Foundation of China(Grant No.61806004).
文摘To acquire non-ferrous metals related news from different countries’internet,we proposed a cross-lingual non-ferrous metals related news recognition method based on CNN with a limited bilingual dictionary.Firstly,considering the lack of related language resources of non-ferrous metals,we use a limited bilingual dictionary and CCA to learn cross-lingual word vector and to represent news in different languages uniformly.Then,to improve the effect of recognition,we use a variant of the CNN to learn recognition features and construct the recognition model.The experimental results show that our proposed method acquires better results.
文摘Joint learning of words and entities is advantageous to various NLP tasks, while most of the works focus on single language setting. Cross-lingual representations learning receives high attention recently, but is still restricted by the availability of parallel data. In this paper, a method is proposed to jointly embed texts and entities on comparable data. In addition to evaluate on public semantic textual similarity datasets, a task (cross-lingual text extraction) was proposed to assess the similarities between texts and contribute to this dataset. It shows that the proposed method outperforms cross-lingual representations methods using parallel data on cross-lingual tasks, and achieves competitive results on mono-lingual tasks.
基金Project supported by the National Natural Science Foundation of China(Nos.U21B2027,62266027,61972186,62241604)the Yunnan Provincial Major Science and Technology Special Plan Projects,China(Nos.202302AD080003,202103AA080015,and 202202AD080003)+1 种基金the General Projects of Basic Research in Yunnan Province,China(Nos.202301AT070471 and 202301AT070393)the Kunming University of Science and Technology“Double First-Class”Joint Project,China(No.202201BE070001-021)。
文摘Cross-lingual summarization(CLS)is the task of generating a summary in a target language from a document in a source language.Recently,end-to-end CLS models have achieved impressive results using large-scale,high-quality datasets typically constructed by translating monolingual summary corpora into CLS corpora.However,due to the limited performance of low-resource language translation models,translation noise can seriously degrade the performance of these models.In this paper,we propose a fine-grained reinforcement learning approach to address low-resource CLS based on noisy data.We introduce the source language summary as a gold signal to alleviate the impact of the translated noisy target summary.Specifically,we design a reinforcement reward by calculating the word correlation and word missing degree between the source language summary and the generated target language summary,and combine it with cross-entropy loss to optimize the CLS model.To validate the performance of our proposed model,we construct Chinese-Vietnamese and Vietnamese-Chinese CLS datasets.Experimental results show that our proposed model outperforms the baselines in terms of both the ROUGE score and BERTScore.
基金supported by the National High-Tech Development(863)Program of China(No.2015AA015407)the National Natural Science Foundation of China(Nos.61632011 and 61370164)
文摘Neural networks have been widely used for English name tagging and have delivered state-of-the-art results. However, for low resource languages, due to the limited resources and lack of training data, taggers tend to have lower performance, in comparison to the English language. In this paper, we tackle this challenging issue by incorporating multi-level cross-lingual knowledge as attention into a neural architecture, which guides low resource name tagging to achieve a better performance. Specifically, we regard entity type distribution as language independent and use bilingual lexicons to bridge cross-lingual semantic mapping. Then, we jointly apply word-level cross-lingual mutual influence and entity-type level monolingual word distributions to enhance low resource name tagging. Experiments on three languages demonstrate the effectiveness of this neural architecture： for Chinese,Uzbek, and Turkish, we are able to yield significant improvements in name tagging over all previous baselines.
基金the National Natural Science Foundation of China (No.69983009).Received November 26, 1999 revised November 1, 2000.
文摘This paper proposes a novel Chinese-English Cross-Lingual Information Retrieval (CECLIR) model PME, in which bilingual dictionary and comparable corpora are used to translate the query terms. The Proximity and mutual information of the term-pairs in the Chinese and English comparable corpora are employed not only to resolve the translation ambiguities but also to perform the query expansion so as to deal with the out-of-vocabulary issues in the CECLIR. The evaluation results show that the query precision of PME algorithm is about 84.4% of the monolingual information retrieval.
文摘随着互联网信息的发展,如何有效地表示不同语言所含的信息已成为自然语言处理(Natural Language Processing,NLP)领域的一项重要任务.然而,很多传统的机器学习模型依赖在高资源语言中进行训练,无法迁移到低资源语言中使用.为了解决这一问题,结合迁移学习和深度学习模型,提出一种多语言双向编码器表征量(Multi-lingual Bidirectional Encoder Representations from Transformers,M-BERT)的迁移学习方法.该方法利用M-BERT作为特征提取器,在源语言领域和目标语言领域之间进行特征转换,减小不同语言领域之间的差异,从而提高目标任务在不同领域之间的泛化能力.首先,在构建BERT模型的基础上,通过数据收集处理、训练设置、参数估计和模型训练等预训练操作完成M-BERT模型的构建,并在目标任务上进行微调.然后,利用迁移学习实现M-BERT模型在跨语言文本分析方面的应用.最后,在从英语到法语和德语的跨语言迁移实验中,证明了本文模型具有较高的性能质量和较小的计算量,并在联合训练方案中达到了96.2%的准确率.研究结果表明,该文模型实现了跨语言数据迁移,且验证了其在跨语言NLP领域的有效性和创新性.
文摘跨语言文本主题发现是跨语言文本挖掘领域的重要研究方向,对跨语言文本分析和组织各种文本数据具有较高的应用价值。基于Bagging和跨语言词嵌入改进LDA主题模型,提出跨语言文本主题发现方法BCL-LDA(Bagging,Cross-lingual word embedding with LDA),从多语言文本中挖掘关键信息。该方法首先将Bagging集成学习思想与LDA主题模型结合生成混合语言子主题集;然后利用跨语言词嵌入和K-means算法对混合子主题进行聚类分组;最后使用TF-IDF算法对主题词进行过滤排序。汉语-德语、汉语-法语主题发现实验表明,该方法在主题连贯性和多样性方面均表现优异,能够提取出语义更加相关且主题更加连贯多样的双语主题。
