Large language models (LM) generate remarkably fluent text and can be efficiently adapted across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of safety is imperative for deploying LMs in the real world; to this end, prior work often relies on automatic evaluation of LM toxicity. We critically discuss this approach, evaluate several toxicity mitigation strategies with respect to both automatic and human evaluation, and analyze consequences of toxicity mitigation in terms of model bias and LM quality. We demonstrate that while basic intervention strategies can effectively optimize previously established automatic metrics on the RealToxicityPrompts dataset, this comes at the cost of reduced LM coverage for both texts about, and dialects of, marginalized groups. Additionally, we find that human raters often disagree with high automatic toxicity scores after strong toxicity reduction interventions -- highlighting further the nuances involved in careful evaluation of LM toxicity.

One of the strongest signals for automated matching of ontologies and knowledge graphs are the textual descriptions of the concepts. The methods that are typically applied (such as character- or token-based comparisons) are relatively simple, and therefore do not capture the actual meaning of the texts. With the rise of transformer-based language models, text comparison based on meaning (rather than lexical features) is possible. In this paper, we model the ontology matching task as classification problem and present approaches based on transformer models. We further provide an easy to use implementation in the MELT framework which is suited for ontology and knowledge graph matching. We show that a transformer-based filter helps to choose the correct correspondences given a high-recall alignment and already achieves a good result with simple alignment post-processing methods.

Paraphrase generation is an important task in natural language processing. Previous works focus on sentence-level paraphrase generation, while ignoring document-level paraphrase generation, which is a more challenging and valuable task. In this paper, we explore the task of document-level paraphrase generation for the first time and focus on the inter-sentence diversity by considering sentence rewriting and reordering. We propose CoRPG (Coherence Relationship guided Paraphrase Generation), which leverages graph GRU to encode the coherence relationship graph and get the coherence-aware representation for each sentence, which can be used for re-arranging the multiple (possibly modified) input sentences. We create a pseudo document-level paraphrase dataset for training CoRPG. Automatic evaluation results show CoRPG outperforms several strong baseline models on the BERTScore and diversity scores. Human evaluation also shows our model can generate document paraphrase with more diversity and semantic preservation.

Existing text-to-SQL research only considers complete questions as the input, but lay-users might strive to formulate a complete question. To build a smarter natural language interface to database systems (NLIDB) that also processes incomplete questions, we propose a new task, prefix-to-SQL which takes question prefix from users as the input and predicts the intended SQL. We construct a new benchmark called PAGSAS that contains 124K user question prefixes and the intended SQL for 5 sub-tasks Advising, GeoQuery, Scholar, ATIS, and Spider. Additionally, we propose a new metric SAVE to measure how much effort can be saved by users. Experimental results show that PAGSAS is challenging even for strong baseline models such as T5. As we observe the difficulty of prefix-to-SQL is related to the number of omitted tokens, we incorporate curriculum learning of feeding examples with an increasing number of omitted tokens. This improves scores on various sub-tasks by as much as 9% recall scores on sub-task GeoQuery in PAGSAS.

Sensors are the key to sensing the environment and imparting benefits to smart cities in many aspects, such as providing real-time air quality information throughout an urban area. However, a prerequisite is to obtain fine-grained knowledge of the environment. There is a limit to how many sensors can be installed in the physical world due to non-negligible expenses. In this paper, we propose to infer real-time information of any given location in a city based on historical and current observations from the available sensors (termed spatiotemporal inference). Our approach decouples the modeling of short-term and long-term patterns, relying on two major components. Firstly, unlike previous studies that separated the spatial and temporal relation learning, we introduce a joint spatiotemporal graph attention network that learns the short-term dependencies across both the spatial and temporal dimensions. Secondly, we propose an adaptive graph recurrent network with a time skip for capturing long-term patterns. The adaptive adjacency matrices are learned inductively first as the inputs of a recurrent network to learn dynamic dependencies. Experimental results on four public read-world datasets show that our method reduces state-of-the-art baseline mean absolute errors by 5%~12%.

Integrating outside knowledge for reasoning in visio-linguistic tasks such as visual question answering (VQA) is an open problem. Given that pretrained language models have been shown to include world knowledge, we propose to use a unimodal (text-only) train and inference procedure based on automatic off-the-shelf captioning of images and pretrained language models. Our results on a visual question answering task which requires external knowledge (OK-VQA) show that our text-only model outperforms pretrained multimodal (image-text) models of comparable number of parameters. In contrast, our model is less effective in a standard VQA task (VQA 2.0) confirming that our text-only method is specially effective for tasks requiring external knowledge. In addition, we show that our unimodal model is complementary to multimodal models in both OK-VQA and VQA 2.0, and yield the best result to date in OK-VQA among systems not using external knowledge graphs, and comparable to systems that do use them. Our qualitative analysis on OK-VQA reveals that automatic captions often fail to capture relevant information in the images, which seems to be balanced by the better inference ability of the text-only language models. Our work opens up possibilities to further improve inference in visio-linguistic tasks.

We study practical data characteristics underlying federated learning, where non-i.i.d. data from clients have sparse features, and a certain client's local data normally involves only a small part of the full model, called a submodel. Due to data sparsity, the classical federated averaging (FedAvg) algorithm or its variants will be severely slowed down, because when updating the global model, each client's zero update of the full model excluding its submodel is inaccurately aggregated. Therefore, we propose federated submodel averaging (FedSubAvg), ensuring that the expectation of the global update of each model parameter is equal to the average of the local updates of the clients who involve it. We theoretically proved the convergence rate of FedSubAvg by deriving an upper bound under a new metric called the element-wise gradient norm. In particular, this new metric can characterize the convergence of federated optimization over sparse data, while the conventional metric of squared gradient norm used in FedAvg and its variants cannot. We extensively evaluated FedSubAvg over both public and industrial datasets. The evaluation results demonstrate that FedSubAvg significantly outperforms FedAvg and its variants.

General-purpose language models have demonstrated impressive capabilities, performing on par with state-of-the-art approaches on a range of downstream natural language processing (NLP) tasks and benchmarks when inferring instructions from very few examples. Here, we evaluate the multilingual skills of the GPT and T5 models in conducting multi-class classification on non-English languages without any parameter updates. We show that, given a few English examples as context, pre-trained language models can predict not only English test samples but also non-English ones. Finally, we find the in-context few-shot cross-lingual prediction results of language models are significantly better than random prediction, and they are competitive compared to the existing state-of-the-art cross-lingual models.

As data is generated and stored almost everywhere, learning a model from a data-decentralized setting is a task of interest for many AI-driven service providers. Although federated learning is settled down as the main solution in such situations, there still exists room for improvement in terms of personalization. Training federated learning systems usually focuses on optimizing a global model that is identically deployed to all client devices. However, a single global model is not sufficient for each client to be personalized on their performance as local data assumes to be not identically distributed across clients. We propose a method to address this situation through the lens of ensemble learning based on the construction of a low-loss subspace continuum that generates a high-accuracy ensemble of two endpoints (i.e. global model and local model). We demonstrate that our method achieves consistent gains both in personalized and unseen client evaluation settings through extensive experiments on several standard benchmark datasets.

Time series models with recurrent neural networks (RNNs) can have high accuracy but are unfortunately difficult to interpret as a result of feature-interactions, temporal-interactions, and non-linear transformations. Interpretability is important in domains like healthcare where constructing models that provide insight into the relationships they have learned are required to validate and trust model predictions. We want accurate time series models where users can understand the contribution of individual input features. We present the Interpretable-RNN (I-RNN) that balances model complexity and accuracy by forcing the relationship between variables in the model to be additive. Interactions are restricted between hidden states of the RNN and additively combined at the final step. I-RNN specifically captures the unique characteristics of clinical time series, which are unevenly sampled in time, asynchronously acquired, and have missing data. Importantly, the hidden state activations represent feature coefficients that correlate with the prediction target and can be visualized as risk curves that capture the global relationship between individual input features and the outcome. We evaluate the I-RNN model on the Physionet 2012 Challenge dataset to predict in-hospital mortality, and on a real-world clinical decision support task: predicting hemodynamic interventions in the intensive care unit. I-RNN provides explanations in the form of global and local feature importances comparable to highly intelligible models like decision trees trained on hand-engineered features while significantly outperforming them. I-RNN remains intelligible while providing accuracy comparable to state-of-the-art decay-based and interpolation-based recurrent time series models. The experimental results on real-world clinical datasets refute the myth that there is a tradeoff between accuracy and interpretability.