In this work, we study how the large-scale pretrain-finetune framework changes the behavior of a neural language generator. We focus on the transformer encoder-decoder model for the open-domain dialogue response generation task. We find that after standard fine-tuning, the model forgets important language generation skills acquired during large-scale pre-training. We demonstrate the forgetting phenomenon through a detailed behavior analysis from the perspectives of context sensitivity and knowledge transfer. Adopting the concept of data mixing, we propose an intuitive fine-tuning strategy named "mix-review". We find that mix-review effectively regularize the fine-tuning process, and the forgetting problem is largely alleviated. Finally, we discuss interesting behavior of the resulting dialogue model and its implications.
This paper describes Facebook AI's submission to the WAT 2019 Myanmar-English translation task. Our baseline systems are BPE-based transformer models. We explore methods to leverage monolingual data to improve generalization, including self-training, back-translation and their combination. We further improve results by using noisy channel re-ranking and ensembling. We demonstrate that these techniques can significantly improve not only a system trained with additional monolingual data, but even the baseline system trained exclusively on the provided small parallel dataset. Our system ranks first in both directions according to human evaluation and BLEU, with a gain of over 8 BLEU points above the second best system.
While we live in an increasingly interconnected world, different places still exhibit strikingly different cultures and many events we experience in our every day life pertain only to the specific place we live in. As a result, people often talk about different things in different parts of the world. In this work we study the effect of local context in machine translation and postulate that particularly in low resource settings this causes the domains of the source and target language to greatly mismatch, as the two languages are often spoken in further apart regions of the world with more distinctive cultural traits and unrelated local events. In this work we first propose a controlled setting to carefully analyze the source-target domain mismatch, and its dependence on the amount of parallel and monolingual data. Second, we test both a model trained with back-translation and one trained with self-training. The latter leverages in-domain source monolingual data but uses potentially incorrect target references. We found that these two approaches are often complementary to each other. For instance, on a low-resource Nepali-English dataset the combined approach improves upon the baseline using just parallel data by 2.5 BLEU points, and by 0.6 BLEU point when compared to back-translation.
Back-translation is a widely used data augmentation technique which leverages target monolingual data. However, its effectiveness has been challenged since automatic metrics such as BLEU only show significant improvements for test examples where the source itself is a translation, or translationese. This is believed to be due to translationese inputs better matching the back-translated training data. In this work, we show that this conjecture is not empirically supported and that back-translation improves translation quality of both naturally occurring text as well as translationese according to professional human translators. We provide empirical evidence to support the view that back-translation is preferred by humans because it produces more fluent outputs. BLEU cannot capture human preferences because references are translationese when source sentences are natural text. We recommend complementing BLEU with a language model score to measure fluency.
Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we will show, hyperparameter choices have significant impact on the final results. We present a replication study of BERT pretraining (Devlin et al., 2019) that carefully measures the impact of many key hyperparameters and training data size. We find that BERT was significantly undertrained, and can match or exceed the performance of every model published after it. Our best model achieves state-of-the-art results on GLUE, RACE and SQuAD. These results highlight the importance of previously overlooked design choices, and raise questions about the source of recently reported improvements. We release our models and code.
This paper describes Facebook FAIR's submission to the WMT19 shared news translation task. We participate in two language pairs and four language directions, English <-> German and English <-> Russian. Following our submission from last year, our baseline systems are large BPE-based transformer models trained with the Fairseq sequence modeling toolkit which rely on sampled back-translations. This year we experiment with different bitext data filtering schemes, as well as with adding filtered back-translated data. We also ensemble and fine-tune our models on domain-specific data, then decode using noisy channel model reranking. Our submissions are ranked first in all four directions of the human evaluation campaign. On En->De, our system significantly outperforms other systems as well as human translations. This system improves upon our WMT'18 submission by 4.5 BLEU points.
Recent advances in generative modeling of text have demonstrated remarkable improvements in terms of fluency and coherency. In this work we investigate to which extent a machine can discriminate real from machine generated text. This is important in itself for automatic detection of computer generated stories, but can also serve as a tool for further improving text generation. We show that learning a dedicated scoring function to discriminate between real and fake text achieves higher precision than employing the likelihood of a generative model. The scoring functions generalize to other generators than those used for training as long as these generators have comparable model complexity and are trained on similar datasets.
fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and supports distributed training across multiple GPUs and machines. We also support fast mixed-precision training and inference on modern GPUs. A demo video can be found at https://www.youtube.com/watch?v=OtgDdWtHvto
Mixture models trained via EM are among the simplest, most widely used and well understood latent variable models in the machine learning literature. Surprisingly, these models have been hardly explored in text generation applications such as machine translation. In principle, they provide a latent variable to control generation and produce a diverse set of hypotheses. In practice, however, mixture models are prone to degeneracies---often only one component gets trained or the latent variable is simply ignored. We find that disabling dropout noise in responsibility computation is critical to successful training. In addition, the design choices of parameterization, prior distribution, hard versus soft EM and online versus offline assignment can dramatically affect model performance. We develop an evaluation protocol to assess both quality and diversity of generations against multiple references, and provide an extensive empirical study of several mixture model variants. Our analysis shows that certain types of mixture models are more robust and offer the best trade-off between translation quality and diversity compared to variational models and diverse decoding approaches.
The vast majority of language pairs in the world are low-resource because they have little, if any, parallel data available. Unfortunately, machine translation (MT) systems do not currently work well in this setting. Besides the technical challenges of learning with limited supervision, there is also another challenge: it is very difficult to evaluate methods trained on low resource language pairs because there are very few freely and publicly available benchmarks. In this work, we take sentences from Wikipedia pages and introduce new evaluation datasets in two very low resource language pairs, Nepali-English and Sinhala-English. These are languages with very different morphology and syntax, for which little out-of-domain parallel data is available and for which relatively large amounts of monolingual data are freely available. We describe our process to collect and cross-check the quality of translations, and we report baseline performance using several learning settings: fully supervised, weakly supervised, semi-supervised, and fully unsupervised. Our experiments demonstrate that current state-of-the-art methods perform rather poorly on this benchmark, posing a challenge to the research community working on low resource MT. Data and code to reproduce our experiments are available at https://github.com/facebookresearch/flores.