Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks, but focus on conversational tasks has been rather limited. This is partly due to the high cost of obtaining non-English conversational data, which results in limited coverage. In this work, we introduce for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset that we created by translating the English-only Schema-Guided Dialogue (SGD) dataset (Rastogi et al., 2020) into 105 other languages. XSGD contains about 330k utterances per language. To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts. We also investigate two different classifiers: NLI-based and vanilla classifiers, and test cross-lingual capability enabled by the aligned prompts. We evaluate our model’s cross-lingual generalization capabilities on two conversation tasks: slot-filling and intent classification. Our results demonstrate strong and efficient modeling ability of NLI-based classifiers and the large cross-lingual transfer improvements achieved by our aligned prompts, particularly in few-shot settings. We also conduct studies on large language models (LLMs) such as text-davinci-003 and ChatGPT in both zero- and few-shot settings. While LLMs exhibit impressive performance in English, their cross-lingual capabilities in other languages, particularly low-resource ones, are limited.

Pre-trained multilingual language models show significant performance gains for zero-shot cross-lingual model transfer on a wide range of natural language understanding (NLU) tasks. Previously, for zero-shot cross-lingual evaluation, pre-trained models are only fine-tuned on English data and tested on a variety of target languages. In this paper, we do cross-lingualevaluation on various NLU tasks (sentence classification, sequence labeling, question answering) using prompt-tuning and compare it with fine-tuning. The results show that prompt tuning achieves much better cross-lingual transfer than fine-tuning across datasets, with only 0.1% to 0.3% tuned parameters. Additionally, we demonstrate through the analysis that prompt tuning can have better cross-lingual transfer-ability of representations on downstream tasks with better aligned decision boundaries.

Many tasks in natural language processing involve predicting structured outputs, e.g., sequence labeling, semantic role labeling, parsing, and machine translation. Researchers are increasingly applying deep representation learning to these problems, but the structured component of these approaches is usually quite simplistic. In this work, we propose several high-order energy terms to capture complex dependencies among labels in sequence labeling, including several that consider the entire label sequence. We use neural parameterizations for these energy terms, drawing from convolutional, recurrent, and self-attention networks. We use the framework of learning energy-based inference networks (Tu and Gimpel, 2018) for dealing with the difficulties of training and inference with such models. We empirically demonstrate that this approach achieves substantial improvement using a variety of high-order energy terms on four sequence labeling tasks, while having the same decoding speed as simple, local classifiers. We also find high-order energies to help in noisy data conditions.

Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to their success is generalization from a small amount of counterexamples where the spurious correlations do not hold. When such minority examples are scarce, pre-trained models perform as poorly as models trained from scratch. In the case of extreme minority, we propose to use multi-task learning (MTL) to improve generalization. Our experiments on natural language inference and paraphrase identification show that MTL with the right auxiliary tasks significantly improves performance on challenging examples without hurting the in-distribution performance. Further, we show that the gain from MTL mainly comes from improved generalization from the minority examples. Our results highlight the importance of data diversity for overcoming spurious correlations.1

We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model. In particular, we view our non-autoregressive translation system as an inference network (Tu and Gimpel, 2018) trained to minimize the autoregressive teacher energy. This contrasts with the popular approach of training a non-autoregressive model on a distilled corpus consisting of the beam-searched outputs of such a teacher model. Our approach, which we call ENGINE (ENerGy-based Inference NEtworks), achieves state-of-the-art non-autoregressive results on the IWSLT 2014 DE-EN and WMT 2016 RO-EN datasets, approaching the performance of autoregressive models.

Deep energy-based models are powerful, but pose challenges for learning and inference (Belanger and McCallum, 2016). Tu and Gimpel (2018) developed an efficient framework for energy-based models by training “inference networks” to approximate structured inference instead of using gradient descent. However, their alternating optimization approach suffers from instabilities during training, requiring additional loss terms and careful hyperparameter tuning. In this paper, we contribute several strategies to stabilize and improve this joint training of energy functions and inference networks for structured prediction. We design a compound objective to jointly train both cost-augmented and test-time inference networks along with the energy function. We propose joint parameterizations for the inference networks that encourage them to capture complementary functionality during learning. We empirically validate our strategies on two sequence labeling tasks, showing easier paths to strong performance than prior work, as well as further improvements with global energy terms.

Exact structured inference with neural network scoring functions is computationally challenging but several methods have been proposed for approximating inference. One approach is to perform gradient descent with respect to the output structure directly (Belanger and McCallum, 2016). Another approach, proposed recently, is to train a neural network (an “inference network”) to perform inference (Tu and Gimpel, 2018). In this paper, we compare these two families of inference methods on three sequence labeling datasets. We choose sequence labeling because it permits us to use exact inference as a benchmark in terms of speed, accuracy, and search error. Across datasets, we demonstrate that inference networks achieve a better speed/accuracy/search error trade-off than gradient descent, while also being faster than exact inference at similar accuracy levels. We find further benefit by combining inference networks and gradient descent, using the former to provide a warm start for the latter.

We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimensions, we consider several sentence attributes, including sentiment, length, predicates, frames, and automatically-induced clusters. Our empirical results demonstrate: (1) our framework is accurate in terms of generating outputs that match the target control values; (2) our model yields increased maximum metric scores compared to standard n-best list generation via beam search; (3) controlling generation with semantic frames leads to a stronger combination of diversity and quality than other control variables as measured by automatic metrics. We also conduct a human evaluation to assess the utility of providing multiple suggestions for creative writing, demonstrating promising results for the potential of controllable, diverse generation in a collaborative writing system.

We study the problem of measuring the quality of automatically-generated stories. We focus on the setting in which a few sentences of a story are provided and the task is to generate the next sentence (“continuation”) in the story. We seek to identify what makes a story continuation interesting, relevant, and have high overall quality. We crowdsource annotations along these three criteria for the outputs of story continuation systems, design features, and train models to predict the annotations. Our trained scorer can be used as a rich feature function for story generation, a reward function for systems that use reinforcement learning to learn to generate stories, and as a partial evaluation metric for story generation.

We consider the ROC story cloze task (Mostafazadeh et al., 2016) and present several findings. We develop a model that uses hierarchical recurrent networks with attention to encode the sentences in the story and score candidate endings. By discarding the large training set and only training on the validation set, we achieve an accuracy of 74.7%. Even when we discard the story plots (sentences before the ending) and only train to choose the better of two endings, we can still reach 72.5%. We then analyze this “ending-only” task setting. We estimate human accuracy to be 78% and find several types of clues that lead to this high accuracy, including those related to sentiment, negation, and general ending likelihood regardless of the story context.

We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic category, and semantic role. We explore simple, efficient token embedding models based on standard neural network architectures. We learn token embeddings on a large amount of unannotated text and evaluate them as features for part-of-speech taggers and dependency parsers trained on much smaller amounts of annotated data. We find that predictors endowed with token embeddings consistently outperform baseline predictors across a range of context window and training set sizes.