Junsheng Zhou

Learn More
Most existing systems solved the phrase chunking task with the sequence labeling approaches, in which the chunk candidates cannot be treated as a whole during parsing process so that the chunk-level features cannot be exploited in a natural way. In this paper, we formulate phrase chunking as a joint segmentation and labeling task. We propose an efficient(More)
Most previous work treats the solution for pronouns and noun phrases either in two separate processes or in a single process. We argue that resolving them in two processes may result in the loss of potential useful information for each process. However, resolving them in a single process is also problematic. These two types of mentions have very different(More)
Chinese named entity recognition is one of the difficult and challenging tasks of NLP. In this paper, we present a Chinese named entity recognition system using a multi-phase model. First, we segment the text with a character-level CRF model. Then we apply three word-level CRF models to the labeling person names, location names and organization names in the(More)
Spectral Graph Transducer(SGT) is one of the superior graph-based transductive learning methods for classification. As for the Spectral Graph Transducer algorithm , a good graph representation for data to be processed is very important. In this paper, we try to incorporate Latent Semantic Indexing(LSI) into SGT for text classification. Firstly, we exploit(More)
We propose a novel reranking method to extend a deterministic neural dependency parser. Different to conventional k-best reranking, the proposed model integrates search and learning by utilizing a dynamic action revising process, using the rerank-ing model to guide modification for the base outputs and to rerank the candidates. The dynamic reranking model(More)
To alleviate the error propagation in the traditional pipelined models for Abstract Meaning Representation (AMR) parsing, we formulate AMR parsing as a joint task that performs the two subtasks: concept identification and relation identification simultaneously. To this end, we first develop a novel component-wise beam search algorithm for relation(More)
Discriminative structured prediction models have been widely used in many natural language processing tasks, but it is challenging to apply the method to semantic parsing. In this paper, by introducing hybrid tree as a latent structure variable to close the gap between the input sentences and output representations, we formulate semantic parsing as a(More)
Chinese event descriptive clause splitting is the task of splitting a complex Chinese sentence into several clauses. In this paper, we present a discriminative approach for Chinese event descriptive clause splitting task. By formulating the Chinese clause splitting task as a sequence labeling problem, we apply the structured SVMs model to Chinese clause(More)