Semi-Markov conditional random fields(Semi-CRFs)have been successfully utilized in many segmentation problems,including Chinese word segmentation(CWS).The advantage of Semi-CRF lies in its inherent ability to exploit ...Semi-Markov conditional random fields(Semi-CRFs)have been successfully utilized in many segmentation problems,including Chinese word segmentation(CWS).The advantage of Semi-CRF lies in its inherent ability to exploit properties of segments instead of individual elements of sequences.Despite its theoretical advantage,Semi-CRF is still not the best choice for CWS because its computation complexity is quadratic to the sentenced length.In this paper,we propose a simple yet effective framework to help Semi-CRF achieve comparable performance with CRF-based models under similar computation complexity.Specifically,we first adopt a bi-directional long short-term memory(BiLSTM)on character level to model the context information,and then use simple but effective fusion layer to represent the segment information.Besides,to model arbitrarily long segments within linear time complexity,we also propose a new model named Semi-CRF-Relay.The direct modeling of segments makes the combination with word features easy and the CWS performance can be enhanced merely by adding publicly available pre-trained word embeddings.Experiments on four popular CWS datasets show the effectiveness of our proposed methods.The source codes and pre-trained embeddings of this paper are available on https://github.com/fastnlp/fastNLP/.展开更多
In this paper a novel word-segmentation algorithm is presented todelimit words in Chinese natural language queries in NChiql system, a Chinese natural language query interface to databases. Although there are sizable ...In this paper a novel word-segmentation algorithm is presented todelimit words in Chinese natural language queries in NChiql system, a Chinese natural language query interface to databases. Although there are sizable literatureson Chinese segmentation, they cannot satisfy particular requirements in this system. The novel word-segmentation algorithm is based on the database semantics,namely Semantic Conceptual Model (SCM) for specific domain knowledge. Basedon SCM, the segmenter labels the database semantics to words directly, which easesthe disambiguation and translation (from natural language to database query) inNChiql.展开更多
Chinese word segmentation plays an important role in search engine,artificial intelligence,machine translation and so on.There are currently three main word segmentation algorithms:dictionary-based word segmentation a...Chinese word segmentation plays an important role in search engine,artificial intelligence,machine translation and so on.There are currently three main word segmentation algorithms:dictionary-based word segmentation algorithms,statistics-based word segmentation algorithms,and understandingbased word segmentation algorithms.However,few people combine these three methods or two of them.Therefore,a Chinese word segmentation model is proposed based on a combination of statistical word segmentation algorithm and understanding-based word segmentation algorithm.It combines Hidden Markov Model(HMM)word segmentation and Bi-LSTM word segmentation to improve accuracy.The main method is to make lexical statistics on the results of the two participles,and to choose the best results based on the statistical results,and then to combine them into the final word segmentation results.This combined word segmentation model is applied to perform experiments on the MSRA corpus provided by Bakeoff.Experiments show that the accuracy of word segmentation results is 12.52%higher than that of traditional HMM model and 0.19%higher than that of BI-LSTM model.展开更多
The previously proposed syllable-synchronous network search (SSNS) algorithm plays a very important role in the word decoding of the continuous Chinese speech recognition and achieves satisfying performance. Several r...The previously proposed syllable-synchronous network search (SSNS) algorithm plays a very important role in the word decoding of the continuous Chinese speech recognition and achieves satisfying performance. Several related key factors that may affect the overall word decoding effect are carefully studied in this paper, including the perfecting of the vocabulary, the big-discount Turing re-estimating of the N-Gram probabilities, and the managing of the searching path buffers. Based on these discussions, corresponding approaches to improving the SSNS algorithm are proposed. Compared with the previous version of SSNS algorithm, the new version decreases the Chinese character error rate (CCER) in the word decoding by 42.1% across a database consisting of a large number of testing sentences (syllable strings).展开更多
As a powerful sequence labeling model, conditional random fields (CRFs) have had successful applications in many natural language processing (NLP) tasks. However, the high complexity of CRFs training only allows a...As a powerful sequence labeling model, conditional random fields (CRFs) have had successful applications in many natural language processing (NLP) tasks. However, the high complexity of CRFs training only allows a very small tag (or label) set, because the training becomes intractable as the tag set enlarges. This paper proposes an improved decomposed training and joint decoding algorithm for CRF learning. Instead of training a single CRF model for all tags, it trains a binary sub-CRF independently for each tag. An optimal tag sequence is then produced by a joint decoding algorithm based on the probabilistic output of all sub-CRFs involved. To test its effectiveness, we apply this approach to tackling Chinese word segmentation (CWS) as a sequence labeling problem. Our evaluation shows that it can reduce the computational cost of this language processing task by 40-50% without any significant performance loss on various large-scale data sets.展开更多
The resolution of overlapping ambiguity strings(OAS)is studied based on the maximum entropy model.There are two model outputs,where either the first two characters form a word or the last two characters form a word.Th...The resolution of overlapping ambiguity strings(OAS)is studied based on the maximum entropy model.There are two model outputs,where either the first two characters form a word or the last two characters form a word.The features of the model include one word in con-text of OAS,the current OAS and word probability relation of two kinds of segmentation results.OAS in training text is found by the combination of the FMM and BMM segmen-tation method.After feature tagging they are used to train the maximum entropy model.The People Daily corpus of January 1998 is used in training and testing.Experimental results show a closed test precision of 98.64%and an open test precision of 95.01%.The open test precision is 3.76%better compared with that of the precision of common word probability method.展开更多
Trained on a large corpus,pretrained models(PTMs)can capture different levels of concepts in context and hence generate universal language representations,which greatly benefit downstream natural language processing(N...Trained on a large corpus,pretrained models(PTMs)can capture different levels of concepts in context and hence generate universal language representations,which greatly benefit downstream natural language processing(NLP)tasks.In recent years,PTMs have been widely used in most NLP applications,especially for high-resource languages,such as English and Chinese.However,scarce resources have discouraged the progress of PTMs for low-resource languages.Transformer-based PTMs for the Khmer language are presented in this work for the first time.We evaluate our models on two downstream tasks:Part-of-speech tagging and news categorization.The dataset for the latter task is self-constructed.Experiments demonstrate the effectiveness of the Khmer models.In addition,we find that the current Khmer word segmentation technology does not aid performance improvement.We aim to release our models and datasets to the community in hopes of facilitating the future development of Khmer NLP applications.展开更多
基金supported by the National Natural Science Foundation of China under Grant Nos.61751201 arid 61672162the Shanghai Municipal Science and Technology Major Project under Grant Nos.2018SHZDZX01 and ZJLab.
文摘Semi-Markov conditional random fields(Semi-CRFs)have been successfully utilized in many segmentation problems,including Chinese word segmentation(CWS).The advantage of Semi-CRF lies in its inherent ability to exploit properties of segments instead of individual elements of sequences.Despite its theoretical advantage,Semi-CRF is still not the best choice for CWS because its computation complexity is quadratic to the sentenced length.In this paper,we propose a simple yet effective framework to help Semi-CRF achieve comparable performance with CRF-based models under similar computation complexity.Specifically,we first adopt a bi-directional long short-term memory(BiLSTM)on character level to model the context information,and then use simple but effective fusion layer to represent the segment information.Besides,to model arbitrarily long segments within linear time complexity,we also propose a new model named Semi-CRF-Relay.The direct modeling of segments makes the combination with word features easy and the CWS performance can be enhanced merely by adding publicly available pre-trained word embeddings.Experiments on four popular CWS datasets show the effectiveness of our proposed methods.The source codes and pre-trained embeddings of this paper are available on https://github.com/fastnlp/fastNLP/.
文摘In this paper a novel word-segmentation algorithm is presented todelimit words in Chinese natural language queries in NChiql system, a Chinese natural language query interface to databases. Although there are sizable literatureson Chinese segmentation, they cannot satisfy particular requirements in this system. The novel word-segmentation algorithm is based on the database semantics,namely Semantic Conceptual Model (SCM) for specific domain knowledge. Basedon SCM, the segmenter labels the database semantics to words directly, which easesthe disambiguation and translation (from natural language to database query) inNChiql.
基金a National Nature Science Fund Project(61661051)Key Laboratory of Education Information of Nationalities Ministry of Education+2 种基金Yunnan Key Laboratory of Smart EducationProgram for innovative research team (in Scienceand Technology) in University of Yunnan ProvinceKunming Key Laboratory of EducationInformation.
文摘Chinese word segmentation plays an important role in search engine,artificial intelligence,machine translation and so on.There are currently three main word segmentation algorithms:dictionary-based word segmentation algorithms,statistics-based word segmentation algorithms,and understandingbased word segmentation algorithms.However,few people combine these three methods or two of them.Therefore,a Chinese word segmentation model is proposed based on a combination of statistical word segmentation algorithm and understanding-based word segmentation algorithm.It combines Hidden Markov Model(HMM)word segmentation and Bi-LSTM word segmentation to improve accuracy.The main method is to make lexical statistics on the results of the two participles,and to choose the best results based on the statistical results,and then to combine them into the final word segmentation results.This combined word segmentation model is applied to perform experiments on the MSRA corpus provided by Bakeoff.Experiments show that the accuracy of word segmentation results is 12.52%higher than that of traditional HMM model and 0.19%higher than that of BI-LSTM model.
文摘The previously proposed syllable-synchronous network search (SSNS) algorithm plays a very important role in the word decoding of the continuous Chinese speech recognition and achieves satisfying performance. Several related key factors that may affect the overall word decoding effect are carefully studied in this paper, including the perfecting of the vocabulary, the big-discount Turing re-estimating of the N-Gram probabilities, and the managing of the searching path buffers. Based on these discussions, corresponding approaches to improving the SSNS algorithm are proposed. Compared with the previous version of SSNS algorithm, the new version decreases the Chinese character error rate (CCER) in the word decoding by 42.1% across a database consisting of a large number of testing sentences (syllable strings).
基金the Research Grants Council of Hong Kong S.A.R.,China,through the CERG under Grant No.9040861(CityU 1318/03H)City University of Hong Kong through the Strategic Research under Grant No.7002037.
文摘As a powerful sequence labeling model, conditional random fields (CRFs) have had successful applications in many natural language processing (NLP) tasks. However, the high complexity of CRFs training only allows a very small tag (or label) set, because the training becomes intractable as the tag set enlarges. This paper proposes an improved decomposed training and joint decoding algorithm for CRF learning. Instead of training a single CRF model for all tags, it trains a binary sub-CRF independently for each tag. An optimal tag sequence is then produced by a joint decoding algorithm based on the probabilistic output of all sub-CRFs involved. To test its effectiveness, we apply this approach to tackling Chinese word segmentation (CWS) as a sequence labeling problem. Our evaluation shows that it can reduce the computational cost of this language processing task by 40-50% without any significant performance loss on various large-scale data sets.
文摘The resolution of overlapping ambiguity strings(OAS)is studied based on the maximum entropy model.There are two model outputs,where either the first two characters form a word or the last two characters form a word.The features of the model include one word in con-text of OAS,the current OAS and word probability relation of two kinds of segmentation results.OAS in training text is found by the combination of the FMM and BMM segmen-tation method.After feature tagging they are used to train the maximum entropy model.The People Daily corpus of January 1998 is used in training and testing.Experimental results show a closed test precision of 98.64%and an open test precision of 95.01%.The open test precision is 3.76%better compared with that of the precision of common word probability method.
基金supported by the Major Projects of Guangdong Education Department for Foundation Research and Applied Research(No.2017KZDXM031)Guangzhou Science and Technology Plan Project(No.202009010021)。
文摘Trained on a large corpus,pretrained models(PTMs)can capture different levels of concepts in context and hence generate universal language representations,which greatly benefit downstream natural language processing(NLP)tasks.In recent years,PTMs have been widely used in most NLP applications,especially for high-resource languages,such as English and Chinese.However,scarce resources have discouraged the progress of PTMs for low-resource languages.Transformer-based PTMs for the Khmer language are presented in this work for the first time.We evaluate our models on two downstream tasks:Part-of-speech tagging and news categorization.The dataset for the latter task is self-constructed.Experiments demonstrate the effectiveness of the Khmer models.In addition,we find that the current Khmer word segmentation technology does not aid performance improvement.We aim to release our models and datasets to the community in hopes of facilitating the future development of Khmer NLP applications.