There has been recent success in pre-training on monolingual data and fine-tuning on Machine Translation (MT), but it remains unclear how to best leverage a pre-trained model for a given MT task. This paper investigates the benefits and drawbacks of freezing parameters, and adding new ones, when fine-tuning a pre-trained model on MT. We focus on 1) Fine-tuning a model trained only on English monolingual data, BART. 2) Fine-tuning a model trained on monolingual data from 25 languages, mBART. For BART we get the best performance by freezing most of the model parameters, and adding extra positional embeddings. For mBART we match or outperform the performance of naive fine-tuning for most language pairs with the encoder, and most of the decoder, frozen. The encoder-decoder attention parameters are most important to fine-tune. When constraining ourselves to an out-of-domain training set for Vietnamese to English we see the largest improvements over the fine-tuning baseline.

Models pretrained with self-supervised objectives on large text corpora achieve state-of-the-art performance on English text summarization tasks. However, these models are typically fine-tuned on hundreds of thousands of data points, an infeasible requirement when applying summarization to new, niche domains. In this work, we introduce a novel and generalizable method, called WikiTransfer, for fine-tuning pretrained models for summarization in an unsupervised, dataset-specific manner. WikiTransfer fine-tunes pretrained models on pseudo-summaries, produced from generic Wikipedia data, which contain characteristics of the target dataset, such as the length and level of abstraction of the desired summaries. WikiTransfer models achieve state-of-the-art, zero-shot abstractive summarization performance on the CNN-DailyMail dataset and demonstrate the effectiveness of our approach on three additional diverse datasets. These models are more robust to noisy data and also achieve better or comparable few-shot performance using 10 and 100 training examples when compared to few-shot transfer from other summarization datasets. To further boost performance, we employ data augmentation via round-trip translation as well as introduce a regularization term for improved few-shot transfer. To understand the role of dataset aspects in transfer performance and the quality of the resulting output summaries, we further study the effect of the components of our unsupervised fine-tuning data and analyze few-shot performance using both automatic and human evaluation.

Semantic parsing using sequence-to-sequence models allows parsing of deeper representations compared to traditional word tagging based models. In spite of these advantages, widespread adoption of these models for real-time conversational use cases has been stymied by higher compute requirements and thus higher latency. In this work, we propose a non-autoregressive approach to predict semantic parse trees with an efficient seq2seq model architecture. By combining non-autoregressive prediction with convolutional neural networks, we achieve significant latency gains and parameter size reduction compared to traditional RNN models. Our novel architecture achieves up to an 81% reduction in latency on TOP dataset and retains competitive performance to non-pretrained models on three different semantic parsing datasets.

Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. Extractive summarization systems, though interpretable, suffer from redundancy and possible lack of coherence. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework that generates concise abstractive summaries that can be traced back to an extractive summary. Our framework can be applied to any evidence-based text generation problem and can accommodate various pretrained models in its simple architecture. We use the Information Bottleneck principle to jointly train the extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documents (Jing and McKeown, 2000), our framework first extracts a pre-defined amount of evidence spans and then generates a summary using only the evidence. Using automatic and human evaluations, we show that the generated summaries are better than strong extractive and extractive-abstractive baselines.

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between languages hinders the model from performing uniformly across language pairs. In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. We further show how to practically optimize this objective for large translation corpora using an iterated best response scheme, which is both effective and incurs negligible additional computational cost compared to standard empirical risk minimization. We perform extensive experiments on three sets of languages from two datasets and show that our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.

This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks. We present mBART—a sequence-to-sequence denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective (Lewis et al., 2019). mBART is the first method for pre-training a complete sequence-to-sequence model by denoising full texts in multiple languages, whereas previous approaches have focused only on the encoder, decoder, or reconstructing parts of the text. Pre-training a complete model allows it to be directly fine-tuned for supervised (both sentence-level and document-level) and unsupervised machine translation, with no task- specific modifications. We demonstrate that adding mBART initialization produces performance gains in all but the highest-resource settings, including up to 12 BLEU points for low resource MT and over 5 BLEU points for many document-level and unsupervised models. We also show that it enables transfer to language pairs with no bi-text or that were not in the pre-training corpus, and present extensive analysis of which factors contribute the most to effective pre-training.1

Retrieve-and-edit seq2seq methods typically retrieve an output from the training set and learn a model to edit it to produce the final output. We propose to extend this framework with a simple and effective post-generation ranking approach. Our framework (i) retrieves several potentially relevant outputs for each input, (ii) edits each candidate independently, and (iii) re-ranks the edited candidates to select the final output. We use a standard editing model with simple task-specific re-ranking approaches, and we show empirically that this approach outperforms existing, significantly more complex methodologies. Experiments on two machine translation (MT) datasets show new state-of-art results. We also achieve near state-of-art performance on the Gigaword summarization dataset, where our analyses show that there is significant room for performance improvement with better candidate output selection in future work.

We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard Tranformer-based neural machine translation architecture which, despite its simplicity, can be seen as generalizing BERT (due to the bidirectional encoder), GPT (with the left-to-right decoder), and other recent pretraining schemes. We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token. BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa on GLUE and SQuAD, and achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 3.5 ROUGE. BART also provides a 1.1 BLEU increase over a back-translation system for machine translation, with only target language pretraining. We also replicate other pretraining schemes within the BART framework, to understand their effect on end-task performance.

Given a rough, word-by-word gloss of a source language sentence, target language natives can uncover the latent, fully-fluent rendering of the translation. In this work we explore this intuition by breaking translation into a two step process: generating a rough gloss by means of a dictionary and then ‘translating’ the resulting pseudo-translation, or ‘Translationese’ into a fully fluent translation. We build our Translationese decoder once from a mish-mash of parallel data that has the target language in common and then can build dictionaries on demand using unsupervised techniques, resulting in rapidly generated unsupervised neural MT systems for many source languages. We apply this process to 14 test languages, obtaining better or comparable translation results on high-resource languages than previously published unsupervised MT studies, and obtaining good quality results for low-resource languages that have never been used in an unsupervised MT scenario.

Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation. This approach allows for efficient iterative decoding, where we first predict all of the target words non-autoregressively, and then repeatedly mask out and regenerate the subset of words that the model is least confident about. By applying this strategy for a constant number of iterations, our model improves state-of-the-art performance levels for non-autoregressive and parallel decoding translation models by over 4 BLEU on average. It is also able to reach within about 1 BLEU point of a typical left-to-right transformer model, while decoding significantly faster.

Contemporary machine translation systems achieve greater coverage by applying subword models such as BPE and character-level CNNs, but these methods are highly sensitive to orthographical variations such as spelling mistakes. We show how training on a mild amount of random synthetic noise can dramatically improve robustness to these variations, without diminishing performance on clean text. We focus on translation performance on natural typos, and show that robustness to such noise can be achieved using a balanced diet of simple synthetic noises at training time, without access to the natural noise data or distribution.

We present the first neural poetry translation system. Unlike previous works that often fail to produce any translation for fixed rhyme and rhythm patterns, our system always translates a source text to an English poem. Human evaluation of the translations ranks the quality as acceptable 78.2% of the time.

We present a method for improving word alignments using word similarities. This method is based on encouraging common alignment links between semantically similar words. We use word vectors trained on monolingual data to estimate similarity. Our experiments on translating fifteen languages into English show consistent BLEU score improvements across the languages.

We present a general framework of analyzing existing story corpora to generate controllable and creative new stories. The proposed framework needs little manual annotation to achieve controllable story generation. It creates a new interface for humans to interact with computers to generate personalized stories. We apply the framework to build recurrent neural network (RNN)-based generation models to control story ending valence and storyline. Experiments show that our methods successfully achieve the control and enhance the coherence of stories through introducing storylines. with additional control factors, the generation model gets lower perplexity, and yields more coherent stories that are faithful to the control factors according to human evaluation.