Sentence examples for relation recognition from inspiring English sources

Hamamoto et al. [14] proposed a relation recognition method by using hidden Markov models (HMMs).

The factors that influence the deduction of relation recognition are sense of events, markers, event ordering, and knowledge-based reasoning.

This paper attempts to solve the technical issues for "(1) object and relation recognition" and "(2) situation interpretation".

Then we design a multi-task neural network model to incorporate our BiSynData to benefit implicit discourse relation recognition.

Although SynData has been proven useful for implicit discourse relation recognition, it also has the meaning shift problem and the domain problem.

Summarizing the factors that affect the deduction of relation recognition, other than senses of two events, three main aspects are primary considerations: markers, event ordering, and knowledge-based reasoning.

The project is a combination of Java libraries for relation keyword recognition, negation recognition, candidate PPI pair identification, pattern matching and PPI information extraction.

We believe that LSOE performance can be enhanced by refining the lexical-syntactic patterns used in the relation identification, improving the recognition of the arguments of a relation, and using parse trees.

Figure 13 presents the relation of recognition rate versus occlusion for all the analysed objects.

We analyzed the concept generation process by comparing it with the linguistic interpretation process, from the viewpoints of thought types (property mapping, blending, and thematic relation) and recognition types (commonalities and alignable and nonalignable differences).

The algorithm locates the presence of any negation keyword in the parsed sentence through pattern matching, similar to relation keyword recognition.