Knowledge of noun phrase anaphoricity might be profitably exploited in coreference resolution to bypass the resolution of non-anaphoric noun phrases. However, it is surprising to notice that recent attempts to incorpo...Knowledge of noun phrase anaphoricity might be profitably exploited in coreference resolution to bypass the resolution of non-anaphoric noun phrases. However, it is surprising to notice that recent attempts to incorporate automatically acquired anaphoricity information into coreferenee resolution systems have been far from expectation. This paper proposes a global learning method in determining the anaphoricity of noun phrases via a label propagation algorithm to improve learning-based coreference resolution. In order to eliminate the huge computational burden in the label propagation algorithm, we employ the weighted support vectors as the critical instances in the training texts. In addition, two kinds of kernels, i.e instances to represent all the anaphoricity-labeled NP , the feature-based RBF （Radial Basis Function） kernel and the convolution tree kernel with approximate matching, are explored to compute the anaphoricity similarity between two noun phrases. Experiments on the ACE2003 corpus demonstrate the great effectiveness of our method in anaphoricity determination of noun phrases and its application in learning-based coreference resolution.展开更多
This paper proposes a tree kernel method of semantic relation detection and classification （RDC） between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree ke...This paper proposes a tree kernel method of semantic relation detection and classification （RDC） between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree kernel is presented to better capture the inherent structural information in a parse tree by enabling the standard convolution tree kernel with context-sensitiveness and approximate matching of sub-trees. Second, an enriched parse tree structure is proposed to well derive necessary structural information, e.g., proper latent annotations, from a parse tree. Evaluation on the ACE RDC corpora shows that both the new tree kernel and the enriched parse tree structure contribute significantly to RDC and our tree kernel method much outperforms the state-of-the-art ones.展开更多
State-of-the-arts studies on sentiment classification are typically domain-dependent and domain-restricted. In this paper, we aim to reduce domain dependency and improve overall performance simultaneously by proposing...State-of-the-arts studies on sentiment classification are typically domain-dependent and domain-restricted. In this paper, we aim to reduce domain dependency and improve overall performance simultaneously by proposing an efficient multi-domain sentiment classification algorithm. Our method employs the approach of multiple classifier combination. In this approach, we first train single domain classifiers separately with domain specific data, and then combine the classifiers for the final decision. Our experiments show that this approach performs much better than both single domain classification approach （using the training data individually） and mixed domain classification approach （simply combining all the training data）. In particular, classifier combination with weighted sum rule obtains an average error reduction of 27.6% over single domain classification.展开更多
基金Supported by the National Natural Science Foundation of China under Grant Nos.60873150,90920004 and 61003153
文摘Knowledge of noun phrase anaphoricity might be profitably exploited in coreference resolution to bypass the resolution of non-anaphoric noun phrases. However, it is surprising to notice that recent attempts to incorporate automatically acquired anaphoricity information into coreferenee resolution systems have been far from expectation. This paper proposes a global learning method in determining the anaphoricity of noun phrases via a label propagation algorithm to improve learning-based coreference resolution. In order to eliminate the huge computational burden in the label propagation algorithm, we employ the weighted support vectors as the critical instances in the training texts. In addition, two kinds of kernels, i.e instances to represent all the anaphoricity-labeled NP , the feature-based RBF （Radial Basis Function） kernel and the convolution tree kernel with approximate matching, are explored to compute the anaphoricity similarity between two noun phrases. Experiments on the ACE2003 corpus demonstrate the great effectiveness of our method in anaphoricity determination of noun phrases and its application in learning-based coreference resolution.
基金Supported by the National Natural Science Foundation of China under Grant Nos.60873150,60970056 and 90920004
文摘This paper proposes a tree kernel method of semantic relation detection and classification （RDC） between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree kernel is presented to better capture the inherent structural information in a parse tree by enabling the standard convolution tree kernel with context-sensitiveness and approximate matching of sub-trees. Second, an enriched parse tree structure is proposed to well derive necessary structural information, e.g., proper latent annotations, from a parse tree. Evaluation on the ACE RDC corpora shows that both the new tree kernel and the enriched parse tree structure contribute significantly to RDC and our tree kernel method much outperforms the state-of-the-art ones.
基金Supported by the National Natural Science Foundation of China under Grant No.61003155Start-Up Grant for Newly Appointed Professors under Grant No.1-BBZM in The Hong Kong Polytechnic University
文摘State-of-the-arts studies on sentiment classification are typically domain-dependent and domain-restricted. In this paper, we aim to reduce domain dependency and improve overall performance simultaneously by proposing an efficient multi-domain sentiment classification algorithm. Our method employs the approach of multiple classifier combination. In this approach, we first train single domain classifiers separately with domain specific data, and then combine the classifiers for the final decision. Our experiments show that this approach performs much better than both single domain classification approach （using the training data individually） and mixed domain classification approach （simply combining all the training data）. In particular, classifier combination with weighted sum rule obtains an average error reduction of 27.6% over single domain classification.
