Leveraging additional unlabeled data to boost model performance is common practice in machine learning and natural language processing. For generation tasks, if there is overlap between the additional data and the target text evaluation data, then training on the additional data is training on answers of the test set. This leads to overly-inflated scores with the additional data compared to real-world testing scenarios and problems when comparing models. We study the AMR dataset and Gigaword, which is popularly used for improving AMR-to-text generators, and find significant overlap between Gigaword and a subset of the AMR dataset. We propose methods for excluding parts of Gigaword to remove this overlap, and show that our approach leads to a more realistic evaluation of the task of AMR-to-text generation. Going forward, we give simple best-practice recommendations for leveraging additional data in AMR-to-text generation.

Recent advances in deep learning have shown promises in solving complex combinatorial optimization problems, such as sorting variable-sized sequences. In this work, we take a step further and tackle the problem of ordering the elements of sequences that come with graph structures. Our solution adopts an encoder-decoder framework, in which the encoder is a graph neural network that learns the representation for each element, and the decoder predicts the ordering of each local neighborhood of the graph in turn. We apply our framework to multilingual surface realization, which is the task of ordering and completing sentences with their dependency parses given but without the ordering of words. Experiments show that our approach is much better for this task than prior works that do not consider graph structures. We participated in 2019 Surface Realization Shared Task (SR’19), and we ranked second out of 14 teams while outperforming those teams below by a large margin.

We consider neural language generation under a novel problem setting: generating the words of a sentence according to the order of their first appearance in its lexicalized PCFG parse tree, in a depth-first, left-to-right manner. Unlike previous tree-based language generation methods, our approach is both (i) top-down and (ii) explicitly generating syntactic structure at the same time. In addition, our method combines neural model with symbolic approach: word choice at each step is constrained by its predicted syntactic function. We applied our model to the task of dialog response generation, and found it significantly improves over sequence-to-sequence baseline, in terms of diversity and relevance. We also investigated the effect of lexicalization on language generation, and found that lexicalization schemes that give priority to content words have certain advantages over those focusing on dependency relations.

Neural models have become one of the most important approaches to dialog response generation. However, they still tend to generate the most common and generic responses in the corpus all the time. To address this problem, we designed an iterative training process and ensemble method based on boosting. We combined our method with different training and decoding paradigms as the base model, including mutual-information-based decoding and reward-augmented maximum likelihood learning. Empirical results show that our approach can significantly improve the diversity and relevance of the responses generated by all base models, backed by objective measurements and human evaluation.

Data augmentation seeks to manipulate the available data for training to improve the generalization ability of models. We investigate two data augmentation proxies, permutation and flipping, for neural dialog response selection task on various models over multiple datasets, including both Chinese and English languages. Different from standard data augmentation techniques, our method combines the original and synthesized data for prediction. Empirical results show that our approach can gain 1 to 3 recall-at-1 points over baseline models in both full-scale and small-scale settings.