Head-driven statistical models for natural language parsing are the most representative lexicalized syntactic parsing models, but they only utilize semantic dependency between words, and do not incorporate other seman...Head-driven statistical models for natural language parsing are the most representative lexicalized syntactic parsing models, but they only utilize semantic dependency between words, and do not incorporate other semantic information such as semantic collocation and semantic category. Some improvements on this distinctive parser are presented. Firstly, "valency" is an essential semantic feature of words. Once the valency of word is determined, the collocation of the word is clear, and the sentence structure can be directly derived. Thus, a syntactic parsing model combining valence structure with semantic dependency is purposed on the base of head-driven statistical syntactic parsing models. Secondly, semantic role labeling(SRL) is very necessary for deep natural language processing. An integrated parsing approach is proposed to integrate semantic parsing into the syntactic parsing process. Experiments are conducted for the refined statistical parser. The results show that 87.12% precision and 85.04% recall are obtained, and F measure is improved by 5.68% compared with the head-driven parsing model introduced by Collins.展开更多
方面情感三元组抽取(ASTE)是方面情感分析中一项极具挑战性的子任务,目的是提取所给句子中的方面项、观点项和对应的情感极性。现有的面向ASTE任务的模型分为流水线模型和端到端模型。针对流水线模型易受到错误传播的影响,且大部分现有...方面情感三元组抽取(ASTE)是方面情感分析中一项极具挑战性的子任务,目的是提取所给句子中的方面项、观点项和对应的情感极性。现有的面向ASTE任务的模型分为流水线模型和端到端模型。针对流水线模型易受到错误传播的影响,且大部分现有端到端模型忽略了句子中丰富的句法信息问题,提出一种语义和句法增强的双通道方面情感三元组抽取模型(SSED-ASTE)。首先,使用BERT(Bidirectional Encoder Representation from Transformers)编码器对上下文编码;其次,使用双向长短期记忆(Bi-LSTM)网络捕捉上下文语义依赖关系;再次,通过2个并行的图卷积网络(GCN)分别使用自注意力机制和依存句法分析提取语义特征和句法特征并融合;最后,使用网格标记方案(GTS)抽取三元组。在4个公开数据集上进行实验分析,与GTS-BERT模型相比,所提模型的F1值分别提升了0.29、1.50、2.93和0.78个百分点。实验结果表明,所提模型可以有效利用句子中隐含的语义信息和句法信息,实现较准确的三元组抽取。展开更多
句子的语义处理是自然语言处理的重要难题与挑战。抽象语义表示(Abstract meaning representation,AMR)是近几年国际上新兴的句子级语义表示方法,突破了传统的句法树结构的限制,将一个句子语义抽象为一个单根有向无环图,很好地解决了论...句子的语义处理是自然语言处理的重要难题与挑战。抽象语义表示(Abstract meaning representation,AMR)是近几年国际上新兴的句子级语义表示方法,突破了传统的句法树结构的限制,将一个句子语义抽象为一个单根有向无环图,很好地解决了论元共享问题,成为语言资源建设和句子语义解析的研究热点。本文从AMR概念与规范、解析算法和应用等方面对AMR相关研究进行系统的梳理,特别对AMR的各种解析算法进行了比较深入的分析和比较,指出了现有算法存在的问题和不足,同时介绍了中文AMR的开发进展,最后展望了AMR未来的研究方向。展开更多
为基于真实语料进行句法分析,构建了大规模的短语结构树库和依存结构树库,并尝试在两种结构的树库之间进行转换.讨论了宾州中文树库(Penn Chinese Treebank,CTB)中短语结构树库和依存结构树库的关系,并基于现代中文依存文法制定了中心...为基于真实语料进行句法分析,构建了大规模的短语结构树库和依存结构树库,并尝试在两种结构的树库之间进行转换.讨论了宾州中文树库(Penn Chinese Treebank,CTB)中短语结构树库和依存结构树库的关系,并基于现代中文依存文法制定了中心子节点过滤表,依据该表将短语结构的CTB转换为依存结构树库.在CTB中随机抽取200句语料,转换正确率达到了99.50%.基于该转换得到的依存结构树库可以进一步进行中文依存关系解析的研究.展开更多
基金Project(61262035) supported by the National Natural Science Foundation of ChinaProjects(GJJ12271,GJJ12742) supported by the Science and Technology Foundation of Education Department of Jiangxi Province,ChinaProject(20122BAB201033) supported by the Natural Science Foundation of Jiangxi Province,China
文摘Head-driven statistical models for natural language parsing are the most representative lexicalized syntactic parsing models, but they only utilize semantic dependency between words, and do not incorporate other semantic information such as semantic collocation and semantic category. Some improvements on this distinctive parser are presented. Firstly, "valency" is an essential semantic feature of words. Once the valency of word is determined, the collocation of the word is clear, and the sentence structure can be directly derived. Thus, a syntactic parsing model combining valence structure with semantic dependency is purposed on the base of head-driven statistical syntactic parsing models. Secondly, semantic role labeling(SRL) is very necessary for deep natural language processing. An integrated parsing approach is proposed to integrate semantic parsing into the syntactic parsing process. Experiments are conducted for the refined statistical parser. The results show that 87.12% precision and 85.04% recall are obtained, and F measure is improved by 5.68% compared with the head-driven parsing model introduced by Collins.
文摘方面情感三元组抽取(ASTE)是方面情感分析中一项极具挑战性的子任务,目的是提取所给句子中的方面项、观点项和对应的情感极性。现有的面向ASTE任务的模型分为流水线模型和端到端模型。针对流水线模型易受到错误传播的影响,且大部分现有端到端模型忽略了句子中丰富的句法信息问题,提出一种语义和句法增强的双通道方面情感三元组抽取模型(SSED-ASTE)。首先,使用BERT(Bidirectional Encoder Representation from Transformers)编码器对上下文编码;其次,使用双向长短期记忆(Bi-LSTM)网络捕捉上下文语义依赖关系;再次,通过2个并行的图卷积网络(GCN)分别使用自注意力机制和依存句法分析提取语义特征和句法特征并融合;最后,使用网格标记方案(GTS)抽取三元组。在4个公开数据集上进行实验分析,与GTS-BERT模型相比,所提模型的F1值分别提升了0.29、1.50、2.93和0.78个百分点。实验结果表明,所提模型可以有效利用句子中隐含的语义信息和句法信息,实现较准确的三元组抽取。
文摘句子的语义处理是自然语言处理的重要难题与挑战。抽象语义表示(Abstract meaning representation,AMR)是近几年国际上新兴的句子级语义表示方法,突破了传统的句法树结构的限制,将一个句子语义抽象为一个单根有向无环图,很好地解决了论元共享问题,成为语言资源建设和句子语义解析的研究热点。本文从AMR概念与规范、解析算法和应用等方面对AMR相关研究进行系统的梳理,特别对AMR的各种解析算法进行了比较深入的分析和比较,指出了现有算法存在的问题和不足,同时介绍了中文AMR的开发进展,最后展望了AMR未来的研究方向。
文摘为基于真实语料进行句法分析,构建了大规模的短语结构树库和依存结构树库,并尝试在两种结构的树库之间进行转换.讨论了宾州中文树库(Penn Chinese Treebank,CTB)中短语结构树库和依存结构树库的关系,并基于现代中文依存文法制定了中心子节点过滤表,依据该表将短语结构的CTB转换为依存结构树库.在CTB中随机抽取200句语料,转换正确率达到了99.50%.基于该转换得到的依存结构树库可以进一步进行中文依存关系解析的研究.
