2017/12/07 by Xiao Han, Han Xiao, Xiao, Han +4 · 1 citation
Computer Science · #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Stochastic Gradient Optimization Techniques #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.1712.02555
This is the draft submitting to ICML 2018. You could expect the final version, which is more perfect
openalex publication_date 2017/12/07 · arxiv created 2018/05/17 · arxiv updated 2018/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Neural architecture is a purely numeric framework, which fits the data as a continuous function. However, lacking of logic flow (e.g. if, for, while), traditional algorithms (e.g. Hungarian algorithm, A^* searching, decision tress algorithm) could not be embedded into this paradigm, which limits the theories and applications. In this paper, we reform the calculus graph as a dynamic process, which is guided by logic flow. Within our novel methodology, traditional algorithms could empower numerical neural network. Specifically, regarding the subject of sentence matching, we reformulate this issue as the form of task-assignment, which is solved by Hungarian algorithm. First, our model applies BiLSTM to parse the sentences. Then Hungarian layer aligns the matching positions. Last, we transform the matching results for soft-max regression by another BiLSTM. Extensive experiments show that our model outperforms other state-of-the-art baselines substantially.