In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better understand the existing methods for learning cross-lingual representations. More importantly, inspired by the framework, we propose a new pre-training task based on contrastive learning. Specifically, we regard a bilingual sentence pair as two views of the same meaning and encourage their encoded representations to be more similar than the negative examples. By leveraging both monolingual and parallel corpora, we jointly train the pretext tasks to improve the cross-lingual transferability of pre-trained models. Experimental results on several benchmarks show that our approach achieves considerably better performance. The code and pre-trained models are available at https://aka.ms/infoxlm.

Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. Specifically, we use example consistency regularization to penalize the prediction sensitivity to four types of data augmentations, i.e., subword sampling, Gaussian noise, code-switch substitution, and machine translation. In addition, we employ model consistency to regularize the models trained with two augmented versions of the same training set. Experimental results on the XTREME benchmark show that our method significantly improves cross-lingual fine-tuning across various tasks, including text classification, question answering, and sequence labeling.

The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task. Specifically, the model first self-label word alignments for parallel sentences. Then we randomly mask tokens in a bitext pair. Given a masked token, the model uses a pointer network to predict the aligned token in the other language. We alternately perform the above two steps in an expectation-maximization manner. Experimental results show that our method improves cross-lingual transferability on various datasets, especially on the token-level tasks, such as question answering, and structured prediction. Moreover, the model can serve as a pretrained word aligner, which achieves reasonably low error rate on the alignment benchmarks. The code and pretrained parameters are available at github.com/CZWin32768/XLM-Align.

Previous work mainly focuses on improving cross-lingual transfer for NLU tasks with a multilingual pretrained encoder (MPE), or improving the performance on supervised machine translation with BERT. However, it is under-explored that whether the MPE can help to facilitate the cross-lingual transferability of NMT model. In this paper, we focus on a zero-shot cross-lingual transfer task in NMT. In this task, the NMT model is trained with parallel dataset of only one language pair and an off-the-shelf MPE, then it is directly tested on zero-shot language pairs. We propose SixT, a simple yet effective model for this task. SixT leverages the MPE with a two-stage training schedule and gets further improvement with a position disentangled encoder and a capacity-enhanced decoder. Using this method, SixT significantly outperforms mBART, a pretrained multilingual encoder-decoder model explicitly designed for NMT, with an average improvement of 7.1 BLEU on zero-shot any-to-English test sets across 14 source languages. Furthermore, with much less training computation cost and training data, our model achieves better performance on 15 any-to-English test sets than CRISS and m2m-100, two strong multilingual NMT baselines.

Multilingual T5 pretrains a sequence-to-sequence model on massive monolingual texts, which has shown promising results on many cross-lingual tasks. In this paper, we improve multilingual text-to-text transfer Transformer with translation pairs (mT6). Specifically, we explore three cross-lingual text-to-text pre-training tasks, namely, machine translation, translation pair span corruption, and translation span corruption. In addition, we propose a partially non-autoregressive objective for text-to-text pre-training. We evaluate the methods on seven multilingual benchmark datasets, including sentence classification, named entity recognition, question answering, and abstractive summarization. Experimental results show that the proposed mT6 improves cross-lingual transferability over mT5.

Compared to monolingual models, cross-lingual models usually require a more expressive vocabulary to represent all languages adequately. We find that many languages are under-represented in recent cross-lingual language models due to the limited vocabulary capacity. To this end, we propose an algorithm VoCap to determine the desired vocabulary capacity of each language. However, increasing the vocabulary size significantly slows down the pre-training speed. In order to address the issues, we propose k-NN-based target sampling to accelerate the expensive softmax. Our experiments show that the multilingual vocabulary learned with VoCap benefits cross-lingual language model pre-training. Moreover, k-NN-based target sampling mitigates the side-effects of increasing the vocabulary size while achieving comparable performance and faster pre-training speed. The code and the pretrained multilingual vocabularies are available at https://github.com/bozheng-hit/VoCapXLM.

In the area of customer support, understanding customers’ intents is a crucial step. Machine learning plays a vital role in this type of intent classification. In reality, it is typical to collect confirmation from customer support representatives (CSRs) regarding the intent prediction, though it can unnecessarily incur prohibitive cost to ask CSRs to assign existing or new intents to the mis-classified cases. Apart from the confirmed cases with and without intent labels, there can be a number of cases with no human curation. This data composition (Positives + Unlabeled + multiclass Negatives) creates unique challenges for model development. In response to that, we propose a semi-supervised multi-task learning paradigm. In this manuscript, we share our experience in building text-based intent classification models for a customer support service on an E-commerce website. We improve the performance significantly by evolving the model from multiclass classification to semi-supervised multi-task learning by leveraging the negative cases, domain- and task-adaptively pretrained ALBERT on customer contact texts, and a number of un-curated data with no labels. In the evaluation, the final model boosts the average AUC ROC by almost 20 points compared to the baseline finetuned multiclass classification ALBERT model.

This report describes Microsoft’s machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. We participated in all three evaluation tracks including Large Track and two Small Tracks where the former one is unconstrained and the latter two are fully constrained. Our model submissions to the shared task were initialized with DeltaLM, a generic pre-trained multilingual encoder-decoder model, and fine-tuned correspondingly with the vast collected parallel data and allowed data sources according to track settings, together with applying progressive learning and iterative back-translation approaches to further improve the performance. Our final submissions ranked first on three tracks in terms of the automatic evaluation metric.

Multilingual pretrained language models (such as multilingual BERT) have achieved impressive results for cross-lingual transfer. However, due to the constant model capacity, multilingual pre-training usually lags behind the monolingual competitors. In this work, we present two approaches to improve zero-shot cross-lingual classification, by transferring the knowledge from monolingual pretrained models to multilingual ones. Experimental results on two cross-lingual classification benchmarks show that our methods outperform vanilla multilingual fine-tuning.

The recently introduced pre-trained language model BERT advances the state-of-the-art on many NLP tasks through the fine-tuning approach, but few studies investigate how the fine-tuning process improves the model performance on downstream tasks. In this paper, we inspect the learning dynamics of BERT fine-tuning with two indicators. We use JS divergence to detect the change of the attention mode and use SVCCA distance to examine the change to the feature extraction mode during BERT fine-tuning. We conclude that BERT fine-tuning mainly changes the attention mode of the last layers and modifies the feature extraction mode of the intermediate and last layers. Moreover, we analyze the consistency of BERT fine-tuning between different random seeds and different datasets. In summary, we provide a distinctive understanding of the learning dynamics of BERT fine-tuning, which sheds some light on improving the fine-tuning results.

Question Answering (QA) has shown great success thanks to the availability of large-scale datasets and the effectiveness of neural models. Recent research works have attempted to extend these successes to the settings with few or no labeled data available. In this work, we introduce two approaches to improve unsupervised QA. First, we harvest lexically and syntactically divergent questions from Wikipedia to automatically construct a corpus of question-answer pairs (named as RefQA). Second, we take advantage of the QA model to extract more appropriate answers, which iteratively refines data over RefQA. We conduct experiments on SQuAD 1.1, and NewsQA by fine-tuning BERT without access to manually annotated data. Our approach outperforms previous unsupervised approaches by a large margin, and is competitive with early supervised models. We also show the effectiveness of our approach in the few-shot learning setting.

Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to-end. These models rely on representation learning to select content appropriately, structure it coherently, and verbalize it grammatically, treating entities as nothing more than vocabulary tokens. In this work we propose an entity-centric neural architecture for data-to-text generation. Our model creates entity-specific representations which are dynamically updated. Text is generated conditioned on the data input and entity memory representations using hierarchical attention at each time step. We present experiments on the RotoWire benchmark and a (five times larger) new dataset on the baseball domain which we create. Our results show that the proposed model outperforms competitive baselines in automatic and human evaluation.

Machine reading comprehension with unanswerable questions is a challenging task. In this work, we propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question paired with its corresponding paragraph that contains the answer. We introduce a pair-to-sequence model for unanswerable question generation, which effectively captures the interactions between the question and the paragraph. We also present a way to construct training data for our question generation models by leveraging the existing reading comprehension dataset. Experimental results show that the pair-to-sequence model performs consistently better compared with the sequence-to-sequence baseline. We further use the automatically generated unanswerable questions as a means of data augmentation on the SQuAD 2.0 dataset, yielding 1.9 absolute F1 improvement with BERT-base model and 1.7 absolute F1 improvement with BERT-large model.

Named entity recognition (NER) identifies typed entity mentions in raw text. While the task is well-established, there is no universally used tagset: often, datasets are annotated for use in downstream applications and accordingly only cover a small set of entity types relevant to a particular task. For instance, in the biomedical domain, one corpus might annotate genes, another chemicals, and another diseases—despite the texts in each corpus containing references to all three types of entities. In this paper, we propose a deep structured model to integrate these “partially annotated” datasets to jointly identify all entity types appearing in the training corpora. By leveraging multiple datasets, the model can learn robust input representations; by building a joint structured model, it avoids potential conflicts caused by combining several models’ predictions at test time. Experiments show that the proposed model significantly outperforms strong multi-task learning baselines when training on multiple, partially annotated datasets and testing on datasets that contain tags from more than one of the training corpora.

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different tasks. In this paper, we propose to visualize loss landscapes and optimization trajectories of fine-tuning BERT on specific datasets. First, we find that pre-training reaches a good initial point across downstream tasks, which leads to wider optima and easier optimization compared with training from scratch. We also demonstrate that the fine-tuning procedure is robust to overfitting, even though BERT is highly over-parameterized for downstream tasks. Second, the visualization results indicate that fine-tuning BERT tends to generalize better because of the flat and wide optima, and the consistency between the training loss surface and the generalization error surface. Third, the lower layers of BERT are more invariant during fine-tuning, which suggests that the layers that are close to input learn more transferable representations of language.

Most machine reading comprehension (MRC) models separately handle encoding and matching with different network architectures. In contrast, pretrained language models with Transformer layers, such as GPT (Radford et al., 2018) and BERT (Devlin et al., 2018), have achieved competitive performance on MRC. A research question that naturally arises is: apart from the benefits of pre-training, how many performance gain comes from the unified network architecture. In this work, we evaluate and analyze unifying encoding and matching components with Transformer for the MRC task. Experimental results on SQuAD show that the unified model outperforms previous networks that separately treat encoding and matching. We also introduce a metric to inspect whether a Transformer layer tends to perform encoding or matching. The analysis results show that the unified model learns different modeling strategies compared with previous manually-designed models.

Semantic parsing aims at mapping natural language utterances into structured meaning representations. In this work, we propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages. Given an input utterance, we first generate a rough sketch of its meaning, where low-level information (such as variable names and arguments) is glossed over. Then, we fill in missing details by taking into account the natural language input and the sketch itself. Experimental results on four datasets characteristic of different domains and meaning representations show that our approach consistently improves performance, achieving competitive results despite the use of relatively simple decoders.

In this work we focus on confidence modeling for neural semantic parsers which are built upon sequence-to-sequence models. We outline three major causes of uncertainty, and design various metrics to quantify these factors. These metrics are then used to estimate confidence scores that indicate whether model predictions are likely to be correct. Beyond confidence estimation, we identify which parts of the input contribute to uncertain predictions allowing users to interpret their model, and verify or refine its input. Experimental results show that our confidence model significantly outperforms a widely used method that relies on posterior probability, and improves the quality of interpretation compared to simply relying on attention scores.

Question answering (QA) systems are sensitive to the many different ways natural language expresses the same information need. In this paper we turn to paraphrases as a means of capturing this knowledge and present a general framework which learns felicitous paraphrases for various QA tasks. Our method is trained end-to-end using question-answer pairs as a supervision signal. A question and its paraphrases serve as input to a neural scoring model which assigns higher weights to linguistic expressions most likely to yield correct answers. We evaluate our approach on QA over Freebase and answer sentence selection. Experimental results on three datasets show that our framework consistently improves performance, achieving competitive results despite the use of simple QA models.

Automatically generating product reviews is a meaningful, yet not well-studied task in sentiment analysis. Traditional natural language generation methods rely extensively on hand-crafted rules and predefined templates. This paper presents an attention-enhanced attribute-to-sequence model to generate product reviews for given attribute information, such as user, product, and rating. The attribute encoder learns to represent input attributes as vectors. Then, the sequence decoder generates reviews by conditioning its output on these vectors. We also introduce an attention mechanism to jointly generate reviews and align words with input attributes. The proposed model is trained end-to-end to maximize the likelihood of target product reviews given the attributes. We build a publicly available dataset for the review generation task by leveraging the Amazon book reviews and their metadata. Experiments on the dataset show that our approach outperforms baseline methods and the attention mechanism significantly improves the performance of our model.