Abstract
Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently. However, during training time, typically only one reference is considered for each example, even though there are often multiple references available, e.g., 4 references in NIST MT evaluations, and 5 references in image captioning data. We first investigate several different ways of utilizing multiple human references during training. But more importantly, we then propose an algorithm to generate exponentially many pseudo-references by first compressing existing human references into lattices and then traversing them to generate new pseudo-references. These approaches lead to substantial improvements over strong baselines in both machine translation (+1.5 BLEU) and image captioning (+3.1 BLEU / +11.7 CIDEr).
Highlights
Neural text generation has attracted much attention in recent years thanks to its impressive generation accuracy and wide applicability
In machine translation (MT), even though the training sets are usually with single reference, the evaluation sets often come with multiple references
We investigate three different methods for multi-reference training on both MT and image captioning tasks (Section 2)
Summary
Neural text generation has attracted much attention in recent years thanks to its impressive generation accuracy and wide applicability. There are many recent efforts in improving the generation accuracy, e.g., ConvS2S (Gehring et al, 2017) and Transformer (Vaswani et al, 2017) All these efforts are limited to training with a single reference even when multiple references are available. C 2018 Association for Computational Linguistics rithm to compress all existing human references into a lattice by merging similar words across different references (see examples in Fig. 1); this can be viewed as a modern, neural version of paraphrasing with multiple-sequence alignment (Barzilay and Lee, 2003, 2002). We propose a novel neural network-based multiple sequence alignment model to compress the existing references into lattices. By traversing these lattices, we generate exponentially many new pseudoreferences (Section 3). We report substantial improvements over strong baselines in both MT (+1.5 BLEU) and image captioning (+3.1 BLEU / +11.7 CIDEr) by training on the newly generated pseudo-references (Section 4)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.