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)

Read more

Summary

Introduction

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)

Using Multiple References
Pseudo-References Generation
Indonesia reiterates opposition to garrisoning foreign armies
Naive Idea
Indonesia reiterates opposition to foreign troops in Indonesia
Two elephants try to fit through a small entry
Measuring Word Similarity in Context
Iterative Pairwise Word Alignment using Dynamic Programming
Traverse Lattice and Pseudo-References Selection by BLEU
Machine Translation
Image Captioning
Case Study
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call