不确定输入的神经格-序列模型
Neural Lattice-to-Sequence Models for Uncertain Inputs
摘要:
对神经序列到序列模型的输入通常由上游系统确定,例如词分段器、词性标注器或语音识别器。这些上游模型可能容易出错。通过词格表示输入,可以通过以紧凑的形式捕获替代序列及其后验概率来明确这种不确定性。在这项工作中,我们扩展了TreeLSTM(Tai等人,2015)转换成LatticeLSTM,它能够使用单词格,并且可以用作注意编码器-解码器模型中的编码器。我们通过扩展TreeLSTM的子和和遗忘门并将偏置项引入注意力机制,将格后验分数集成到这个架构中。我们用语音翻译网格进行了实验,并报告了在基线上的一致改进,这些基线翻译了1-最佳假设或没有后验分数的网格。
英文摘要:
The input to a neural sequence-to-sequence model is often determined by an up-stream system, e.g. a word segmenter, part of speech tagger, or speech recognizer. These up-stream models are potentially error-prone. Representing inputs through word lattices allows making this uncertainty explicit by capturing alternative sequences and their posterior probabilities in a compact form. In this work, we extend the TreeLSTM (Tai et al., 2015) into a LatticeLSTM that is able to consume word lattices, and can be used as encoder in an attentional encoder-decoder model. We integrate lattice posterior scores into this architecture by extending the TreeLSTM's child-sum and forget gates and introducing a bias term into the attention mechanism. We experiment with speech translation lattices and report consistent improvements over baselines that translate either the 1-best hypothesis or the lattice without posterior scores.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。