BACKGROUND: Relation extraction is a fundamental technology in biomedical text mining. Most of the previous studies on relation extraction from biomedical literature have focused on specific or predefined types of relations, which inherently limits the types of the extracted relations. With the aim of fully leveraging the knowledge described in the literature, we address much broader types of semantic relations using a single extraction framework. RESULTS: Our system, which we name PASMED, extracts diverse types of binary relations from biomedical literature using deep syntactic patterns. Our experimental results demonstrate that it achieves a level of recall considerably higher than the state of the art, while maintaining reasonable precision. We have then applied PASMED to the whole MEDLINE corpus and extracted more than 137 million semantic relations. The extracted relations provide a quantitative understanding of what kinds of semantic relations are actually described in MEDLINE and can be ultimately extracted by (possibly type-specific) relation extraction systems. CONCLUSION: PASMED extracts a large number of relations that have previously been missed by existing text mining systems. The entire collection of the relations extracted from MEDLINE is publicly available in machine-readable form, so that it can serve as a potential knowledge base for high-level text-mining applications.

In this paper, we present a recursive neural network (RNN) model that works on a syntactic tree.Our model differs from previous RNN models in that the model allows for an explicit weighting of important phrases for the target task.We also propose to average parameters in training.Our experimental results on semantic relation classification show that both phrase categories and task-specific weighting significantly improve the prediction accuracy of the model.We also show that averaging the model parameters is effective in stabilizing the learning and improves generalization capacity.The proposed model marks scores competitive with state-of-the-art RNN-based models.

We review the design of the concurrent logic language GHC, the basis of the kernel language for the Parallel Inference Machine being developed in the Japanese Fifth Generation Computer Systems project, and the design of the parallel language KL1, the actual kernel language being implemented and used. The key idea in the design of these languages is the separation of concurrency and parallelism. Clarification of concepts of this kind seems to play an important role in bridging the gap between parallel inference systems and knowledge information processing in a coherent manner. In particular, design of a new kernel language has always encouraged us to re-examine and reorganise various existing notions related to programming and to invent new ones.

This paper describes a High-speed Prolog Machine (HIM) architecture and its hardware structure, which are developed as a product of Fifth Generation Computer System (FGCS} project in Japan.HIM realizes high performance and provides a practical programming environment.A major HIM feature is a large memory capacity and specialized hardware for unification and stack operations.HIM has a compiler-oriented architecture with high-level stack-control instructions.Furthermore, the HIM architecture provides side-effect operations, nonlocal-exit control and multiprocess support primitives, which are effective to develop system programs.The performance is estimated at 280 KLIPS (Kilo Logical Inferences Per Second) in executing a deterministic "concatenate" Prolog program.The HIM processor is implemented with high-speed CCML {Current Mode Logic) chips and with I00 nanosecond machine cycle.