Rigorous Systems Research Group (RSRG) Seminar

In this talk, I will present a general framework for sequence modeling by exploring the segmental structures of the sequences. We first observe that segmental structure is a common pattern in many types of sequences, e.g., phrases in human languages. We then design a probabilistic model that is able to consider all valid segmentations for a sequence. We describe an efficient and exact dynamic programming algorithm for forward and backward computations. Due to the generality, it can be used as a loss function in many sequence tasks. We demonstrate our approach on text segmentation, speech recognition and machine translation. In addition to quantitative results, we also show that our approach can discover meaningful segments in their respective application contexts. (Joint work with Po-Sen Huang, Dengyong Zhou, Yining Wang, Sitao Huang, Abdelrahman Mohamed, Li Deng.)