All human languages have words that can mean different things in different contexts, such words with multiple meanings are potentially “ambiguous”. The process of “deciding which of several meanings of a term is in...All human languages have words that can mean different things in different contexts, such words with multiple meanings are potentially “ambiguous”. The process of “deciding which of several meanings of a term is intended in a given context” is known as “word sense disambiguation (WSD)”. This paper presents a method of WSD that assigns a target word the sense that is most related to the senses of its neighbor words. We explore the use of measures of relatedness between word senses based on a novel hybrid approach. First, we investigate how to “literally” and “regularly” express a “concept”. We apply set algebra to WordNet’s synsets cooperating with WordNet’s word ontology. In this way we establish regular rules for constructing various representations (lexical notations) of a concept using Boolean operators and word forms in various synset(s) defined in WordNet. Then we establish a formal mechanism for quantifying and estimating the semantic relatedness between concepts—we facilitate “concept distribution statistics” to determine the degree of semantic relatedness between two lexically expressed con- cepts. The experimental results showed good performance on Semcor, a subset of Brown corpus. We observe that measures of semantic relatedness are useful sources of information for WSD.展开更多
Word Sense Disambiguation (WSD) is to decide the sense of an ambiguous word on particular context. Most of current studies on WSD only use several ambiguous words as test samples, thus leads to some limitation in prac...Word Sense Disambiguation (WSD) is to decide the sense of an ambiguous word on particular context. Most of current studies on WSD only use several ambiguous words as test samples, thus leads to some limitation in practical application. In this paper, we perform WSD study based on large scale real-world corpus using two unsupervised learning algorithms based on ±n-improved Bayesian model and Dependency Grammar (DG)-improved Bayesian model. ±n-improved classifiers reduce the window size of context of ambiguous words with close-distance feature extraction method, and decrease the jamming of useless features, thus obviously improve the accuracy, reaching 83.18% (in open test). DG-improved classifier can more effectively conquer the noise effect existing in Naive-Bayesian classifier. Experimental results show that this approach does better on Chinese WSD, and the open test achieved an accuracy of 86.27%.展开更多
The natural language processing has a set of phases that evolves from lexical text analysis to the pragmatic one in which the author’s intentions are shown. The ambiguity problem appears in all of these tasks. Previo...The natural language processing has a set of phases that evolves from lexical text analysis to the pragmatic one in which the author’s intentions are shown. The ambiguity problem appears in all of these tasks. Previous works tries to do word sense disambiguation, the process of assign a sense to a word inside a specific context, creating algorithms under a supervised or unsupervised approach, which means that those algorithms use or not an external lexical resource. This paper presents an approximated approach that combines not supervised algorithms by the use of a classifiers set, the result will be a learning algorithm based on unsupervised methods for word sense disambiguation process. It begins with an introduction to word sense disambiguation concepts and then analyzes some unsupervised algorithms in order to extract the best of them, and combines them under a supervised approach making use of some classifiers.展开更多
Entity linking refers to linking a string in a text to corresponding entities in a knowledge base through candidate entity generation and candidate entity ranking.It is of great significance to some NLP(natural langua...Entity linking refers to linking a string in a text to corresponding entities in a knowledge base through candidate entity generation and candidate entity ranking.It is of great significance to some NLP(natural language processing)tasks,such as question answering.Unlike English entity linking,Chinese entity linking requires more consideration due to the lack of spacing and capitalization in text sequences and the ambiguity of characters and words,which is more evident in certain scenarios.In Chinese domains,such as industry,the generated candidate entities are usually composed of long strings and are heavily nested.In addition,the meanings of the words that make up industrial entities are sometimes ambiguous.Their semantic space is a subspace of the general word embedding space,and thus each entity word needs to get its exact meanings.Therefore,we propose two schemes to achieve better Chinese entity linking.First,we implement an ngram based candidate entity generation method to increase the recall rate and reduce the nesting noise.Then,we enhance the corresponding candidate entity ranking mechanism by introducing sense embedding.Considering the contradiction between the ambiguity of word vectors and the single sense of the industrial domain,we design a sense embedding model based on graph clustering,which adopts an unsupervised approach for word sense induction and learns sense representation in conjunction with context.We test the embedding quality of our approach on classical datasets and demonstrate its disambiguation ability in general scenarios.We confirm that our method can better learn candidate entities’fundamental laws in the industrial domain and achieve better performance on entity linking through experiments.展开更多
提出了一种对数模型 (logarithm model,简称 L M) ,构造了一个词义自动消歧系统 LM-WSD(word sensedisambiguation based on logarithm model) .在词义自动消歧实验中 ,构造了 4种计算模型进行词义消歧 ,根据 4个计算模型的消歧结果 ,...提出了一种对数模型 (logarithm model,简称 L M) ,构造了一个词义自动消歧系统 LM-WSD(word sensedisambiguation based on logarithm model) .在词义自动消歧实验中 ,构造了 4种计算模型进行词义消歧 ,根据 4个计算模型的消歧结果 ,分析了高频率词义、指示词、特定领域、固定搭配和固定用法信息对名词和动词词义消歧的影响 .目前 ,该词义自动消歧系统 L M-WSD已经应用于基于词层的英汉机器翻译系统 (汽车配件专业领域 )中 ,有效地提高了翻译性能 .展开更多
文摘All human languages have words that can mean different things in different contexts, such words with multiple meanings are potentially “ambiguous”. The process of “deciding which of several meanings of a term is intended in a given context” is known as “word sense disambiguation (WSD)”. This paper presents a method of WSD that assigns a target word the sense that is most related to the senses of its neighbor words. We explore the use of measures of relatedness between word senses based on a novel hybrid approach. First, we investigate how to “literally” and “regularly” express a “concept”. We apply set algebra to WordNet’s synsets cooperating with WordNet’s word ontology. In this way we establish regular rules for constructing various representations (lexical notations) of a concept using Boolean operators and word forms in various synset(s) defined in WordNet. Then we establish a formal mechanism for quantifying and estimating the semantic relatedness between concepts—we facilitate “concept distribution statistics” to determine the degree of semantic relatedness between two lexically expressed con- cepts. The experimental results showed good performance on Semcor, a subset of Brown corpus. We observe that measures of semantic relatedness are useful sources of information for WSD.
基金Supported by the National Natural Science Foundation of China (No.60435020).
文摘Word Sense Disambiguation (WSD) is to decide the sense of an ambiguous word on particular context. Most of current studies on WSD only use several ambiguous words as test samples, thus leads to some limitation in practical application. In this paper, we perform WSD study based on large scale real-world corpus using two unsupervised learning algorithms based on ±n-improved Bayesian model and Dependency Grammar (DG)-improved Bayesian model. ±n-improved classifiers reduce the window size of context of ambiguous words with close-distance feature extraction method, and decrease the jamming of useless features, thus obviously improve the accuracy, reaching 83.18% (in open test). DG-improved classifier can more effectively conquer the noise effect existing in Naive-Bayesian classifier. Experimental results show that this approach does better on Chinese WSD, and the open test achieved an accuracy of 86.27%.
文摘The natural language processing has a set of phases that evolves from lexical text analysis to the pragmatic one in which the author’s intentions are shown. The ambiguity problem appears in all of these tasks. Previous works tries to do word sense disambiguation, the process of assign a sense to a word inside a specific context, creating algorithms under a supervised or unsupervised approach, which means that those algorithms use or not an external lexical resource. This paper presents an approximated approach that combines not supervised algorithms by the use of a classifiers set, the result will be a learning algorithm based on unsupervised methods for word sense disambiguation process. It begins with an introduction to word sense disambiguation concepts and then analyzes some unsupervised algorithms in order to extract the best of them, and combines them under a supervised approach making use of some classifiers.
基金supported by the National Natural Science Foundation of China under Grant Nos.61932004 and 62072205.
文摘Entity linking refers to linking a string in a text to corresponding entities in a knowledge base through candidate entity generation and candidate entity ranking.It is of great significance to some NLP(natural language processing)tasks,such as question answering.Unlike English entity linking,Chinese entity linking requires more consideration due to the lack of spacing and capitalization in text sequences and the ambiguity of characters and words,which is more evident in certain scenarios.In Chinese domains,such as industry,the generated candidate entities are usually composed of long strings and are heavily nested.In addition,the meanings of the words that make up industrial entities are sometimes ambiguous.Their semantic space is a subspace of the general word embedding space,and thus each entity word needs to get its exact meanings.Therefore,we propose two schemes to achieve better Chinese entity linking.First,we implement an ngram based candidate entity generation method to increase the recall rate and reduce the nesting noise.Then,we enhance the corresponding candidate entity ranking mechanism by introducing sense embedding.Considering the contradiction between the ambiguity of word vectors and the single sense of the industrial domain,we design a sense embedding model based on graph clustering,which adopts an unsupervised approach for word sense induction and learns sense representation in conjunction with context.We test the embedding quality of our approach on classical datasets and demonstrate its disambiguation ability in general scenarios.We confirm that our method can better learn candidate entities’fundamental laws in the industrial domain and achieve better performance on entity linking through experiments.
