Our proposed model closes the performance gap between non-autoregressive and autoregressive approaches on ASPEC Ja-En dataset with 8.6x faster decoding. Our experiments show that the lowerbound can be greatly increased by running the inference algorithm, resulting in significantly improved translation quality. During inference, the length of translation automatically adapts itself. In contrast to existing approaches, we use a deterministic inference algorithm to find the target sequence that maximizes the lowerbound to the log-probability. Inspired by recent refinement-based approaches, we propose LaNMT, a latent-variable non-autoregressive model with continuous latent variables and deterministic inference procedure. Our method outperforms the baseline model by a 1.77 SARI score on the English dataset, and raises the proportion of the low level (HSK level 1-3) words in Chinese definitions by 3.87%.Īlthough neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency.
We demonstrate that the framework can generate relevant, simple definitions for the target words through automatic and manual evaluations on English and Chinese datasets.
By jointly training these components, the framework can generate both complex and simple definitions simultaneously. We disentangle the complexity factors from the text by carefully designing a parameter sharing scheme between two decoders. We explore this task and propose a multitasking framework SimpDefiner that only requires a standard dictionary with complex definitions and a corpus containing arbitrary simple texts. A significant challenge of this task is the lack of learner's dictionaries in many languages, and therefore the lack of data for supervised training. We propose a novel task of Simple Definition Generation (SDG) to help language learners and low literacy readers. This task has attracted much attention in recent years. The definition generation task can help language learners by providing explanations for unfamiliar words.