Robert Sim


2023

pdf bib
Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe
Xiang Yue | Huseyin Inan | Xuechen Li | Girish Kumar | Julia McAnallen | Hoda Shajari | Huan Sun | David Levitan | Robert Sim
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating synthetic versions of such data with a formal privacy guarantee, such as differential privacy (DP), provides a promising path to mitigating these privacy concerns, but previous approaches in this direction have typically failed to produce synthetic data of high quality. In this work, we show that a simple and practical recipe in the text domain is effective: simply fine-tuning a pretrained generative language model with DP enables the model to generate useful synthetic text with strong privacy protection. Through extensive empirical analyses on both benchmark and private customer data, we demonstrate that our method produces synthetic text that is competitive in terms of utility with its non-private counterpart, meanwhile providing strong protection against potential privacy leakages.

2022

pdf bib
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
Fatemehsadat Mireshghallah | Vaishnavi Shrivastava | Milad Shokouhi | Taylor Berg-Kirkpatrick | Robert Sim | Dimitrios Dimitriadis
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Global models are typically trained to be as generalizable as possible. Invariance to the specific user is considered desirable since models are shared across multitudes of users. However, these models are often unable to produce personalized responses for individual users, based on their data. Contrary to widely-used personalization techniques based on few-shot and meta-learning, we propose UserIdentifier, a novel scheme for training a single shared model for all users. Our approach produces personalized responses by prepending a fixed, user-specific non-trainable string (called “user identifier”) to each user’s input text. Unlike prior work, this method doesn’t need any additional model parameters, any extra rounds of personal few-shot learning or any change made to the vocabulary. We empirically study different types of user identifiers (numeric, alphanumeric, and also randomly generated) and demonstrate that, surprisingly, randomly generated user identifiers outperform the prefix-tuning based state-of-the-art approach by up to 13, on a suite of sentiment analysis datasets.

pdf bib
Privacy Leakage in Text Classification A Data Extraction Approach
Adel Elmahdy | Huseyin A. Inan | Robert Sim
Proceedings of the Fourth Workshop on Privacy in Natural Language Processing

Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict the class label as opposed to next-word prediction. This poses an interesting challenge and raises an important question regarding the privacy of training data in text classification settings. Therefore, we study the potential privacy leakage in the text classification domain by investigating the problem of unintended memorization of training data that is not pertinent to the learning task. We propose an algorithm to extract missing tokens of a partial text by exploiting the likelihood of the class label provided by the model. We test the effectiveness of our algorithm by inserting canaries into the training set and attempting to extract tokens in these canaries post-training. In our experiments, we demonstrate that successful extraction is possible to some extent. This can also be used as an auditing strategy to assess any potential unauthorized use of personal data without consent.

2021

pdf bib
Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels
Fatemehsadat Mireshghallah | Huseyin Inan | Marcello Hasegawa | Victor Rühle | Taylor Berg-Kirkpatrick | Robert Sim
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy im- plications when training models on user content such as email correspondence. Differential privacy (DP), a popular choice to train models with privacy guarantees, comes with significant costs in terms of utility degradation and disparate impact on subgroups of users. In this work, we introduce two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy through (1) the use of a discriminator and (2) the inclusion of a novel triplet-loss term. We compare our methods with DP through extensive evaluation. We show the advantages of our regularizers with favorable utility-privacy trade-off, faster training with the ability to tap into existing optimization approaches, and ensuring uniform treatment of under-represented subgroups.

pdf bib
Stereotyping Norwegian Salmon: An Inventory of Pitfalls in Fairness Benchmark Datasets
Su Lin Blodgett | Gilsinia Lopez | Alexandra Olteanu | Robert Sim | Hanna Wallach
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Auditing NLP systems for computational harms like surfacing stereotypes is an elusive goal. Several recent efforts have focused on benchmark datasets consisting of pairs of contrastive sentences, which are often accompanied by metrics that aggregate an NLP system’s behavior on these pairs into measurements of harms. We examine four such benchmarks constructed for two NLP tasks: language modeling and coreference resolution. We apply a measurement modeling lens—originating from the social sciences—to inventory a range of pitfalls that threaten these benchmarks’ validity as measurement models for stereotyping. We find that these benchmarks frequently lack clear articulations of what is being measured, and we highlight a range of ambiguities and unstated assumptions that affect how these benchmarks conceptualize and operationalize stereotyping.

2020

pdf bib
Leveraging Structured Metadata for Improving Question Answering on the Web
Xinya Du | Ahmed Hassan Awadallah | Adam Fourney | Robert Sim | Paul Bennett | Claire Cardie
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

We show that leveraging metadata information from web pages can improve the performance of models for answer passage selection/reranking. We propose a neural passage selection model that leverages metadata information with a fine-grained encoding strategy, which learns the representation for metadata predicates in a hierarchical way. The models are evaluated on the MS MARCO (Nguyen et al., 2016) and Recipe-MARCO datasets. Results show that our models significantly outperform baseline models, which do not incorporate metadata. We also show that the fine-grained encoding’s advantage over other strategies for encoding the metadata.