29 citations · 47 across the 11 of their papers we have counts for
11 papers
Not All Irregularity Is Equal: Causally Isolating a Rare Failure Mode in Japanese Morphological Inflection
Wen Zhang
Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors clustered in rare morphologi…
When Irregularity Helps: A Subclass Analysis of Inductive Bias in Neural Morphology
Wen Zhang
Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors concentrated in rare morphol…
Mind Your Moras: Orthography-Aware Error Analysis of Neural Japanese Morphological Generation
Wen Zhang
We present an orthography-aware error analysis of Japanese past-tense morphological inflection, treating hiragana not merely as a transcriptional medium, but as a representational…
Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation
Wuwei Huang, Renren Jin, Wen Zhang +3
Recent studies on end-to-end speech translation(ST) have facilitated the exploration of multilingual end-to-end ST and end-to-end simultaneous ST. In this paper, we investigate end…
Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation
Mengge Liu, Wen Zhang, Xiang Li +4
Simultaneous machine translation (SimulMT) models start translation before the end of the source sentence, making the translation monotonically aligned with the source sentence. Ho…
Modeling Fluency and Faithfulness for Diverse Neural Machine Translation
Yang Feng, Wanying Xie, Shuhao Gu +4
Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the pro…
Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation
Yong Shan, Yang Feng, Jinchao Zhang +2
Generally, Neural Machine Translation models generate target words in a left-to-right (L2R) manner and fail to exploit any future (right) semantics information, which usually produ…
Bridging the Gap between Training and Inference for Neural Machine Translation
Wen Zhang, Yang Feng, Fandong Meng +2
Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the…
Speeding Up Neural Machine Translation Decoding by Cube Pruning
Wen Zhang, Liang Huang, Yang Feng +2
Although neural machine translation has achieved promising results, it suffers from slow translation speed. The direct consequence is that a trade-off has to be made between transl…
Refining Source Representations with Relation Networks for Neural Machine Translation
Wen Zhang, Jiawei Hu, Yang Feng +1
Although neural machine translation with the encoder-decoder framework has achieved great success recently, it still suffers drawbacks of forgetting distant information, which is a…
Refining Source Representations with Relation Networks for Neural Machine Translation
Wen Zhang, Jiawei Hu, Yang Feng +1
Although neural machine translation (NMT) with the encoder-decoder framework has achieved great success in recent times, it still suffers from some drawbacks: RNNs tend to forget o…