Age-related stereotypes are pervasive in our society, and yet have been under-studied in the NLP community. Here, we present a method for extracting age-related stereotypes from Twitter data, generating a corpus of 300,000 over-generalizations about four contemporary generations (baby boomers, generation X, millennials, and generation Z), as well as “old” and “young” people more generally. By employing word-association metrics, semi-supervised topic modelling, and density-based clustering, we uncover many common stereotypes as reported in the media and in the psychological literature, as well as some more novel findings. We also observe trends consistent with the existing literature, namely that definitions of “young” and “old” age appear to be context-dependent, stereotypes for different generations vary across different topics (e.g., work versus family life), and some age-based stereotypes are distinct from generational stereotypes. The method easily extends to other social group labels, and therefore can be used in future work to study stereotypes of different social categories. By better understanding how stereotypes are formed and spread, and by tracking emerging stereotypes, we hope to eventually develop mitigating measures against such biased statements.

Robustness of machine learning models on ever-changing real-world data is critical, especially for applications affecting human well-being such as content moderation. New kinds of abusive language continually emerge in online discussions in response to current events (e.g., COVID-19), and the deployed abuse detection systems should be updated regularly to remain accurate. In this paper, we show that general abusive language classifiers tend to be fairly reliable in detecting out-of-domain explicitly abusive utterances but fail to detect new types of more subtle, implicit abuse. Next, we propose an interpretability technique, based on the Testing Concept Activation Vector (TCAV) method from computer vision, to quantify the sensitivity of a trained model to the human-defined concepts of explicit and implicit abusive language, and use that to explain the generalizability of the model on new data, in this case, COVID-related anti-Asian hate speech. Extending this technique, we introduce a novel metric, Degree of Explicitness, for a single instance and show that the new metric is beneficial in suggesting out-of-domain unlabeled examples to effectively enrich the training data with informative, implicitly abusive texts.

Certainty calibration is an important goal on the path to interpretability and trustworthy AI. Particularly in the context of human-in-the-loop systems, high-quality low to mid-range certainty estimates are essential. In the presence of a dominant high-certainty class, for instance the non-entity class in NER problems, existing calibration error measures are completely insensitive to potentially large errors in this certainty region of interest. We introduce a region-balanced calibration error metric that weights all certainty regions equally. When low and mid certainty estimates are taken into account, calibration error is typically larger than previously reported. We introduce a simple extension of temperature scaling, requiring no additional computation, that can reduce both traditional and region-balanced notions of calibration error over existing baselines.

We present a novel feature attribution method for explaining text classifiers, and analyze it in the context of hate speech detection. Although feature attribution models usually provide a single importance score for each token, we instead provide two complementary and theoretically-grounded scores – necessity and sufficiency – resulting in more informative explanations. We propose a transparent method that calculates these values by generating explicit perturbations of the input text, allowing the importance scores themselves to be explainable. We employ our method to explain the predictions of different hate speech detection models on the same set of curated examples from a test suite, and show that different values of necessity and sufficiency for identity terms correspond to different kinds of false positive errors, exposing sources of classifier bias against marginalized groups.

Motivations for methods in explainable artificial intelligence (XAI) often include detecting, quantifying and mitigating bias, and contributing to making machine learning models fairer. However, exactly how an XAI method can help in combating biases is often left unspecified. In this paper, we briefly review trends in explainability and fairness in NLP research, identify the current practices in which explainability methods are applied to detect and mitigate bias, and investigate the barriers preventing XAI methods from being used more widely in tackling fairness issues.

We curated WikiPII, an automatically labeled dataset composed of Wikipedia biography pages, annotated for personal information extraction. Although automatic annotation can lead to a high degree of label noise, it is an inexpensive process and can generate large volumes of annotated documents. We trained a BERT-based NER model with WikiPII and showed that with an adequately large training dataset, the model can significantly decrease the cost of manual information extraction, despite the high level of label noise. In a similar approach, organizations can leverage text mining techniques to create customized annotated datasets from their historical data without sharing the raw data for human annotation. Also, we explore collaborative training of NER models through federated learning when the annotation is noisy. Our results suggest that depending on the level of trust to the ML operator and the volume of the available data, distributed training can be an effective way of training a personal information identifier in a privacy-preserved manner. Research material is available at https://github.com/ratmcu/wikipiifed.

Stereotypical language expresses widely-held beliefs about different social categories. Many stereotypes are overtly negative, while others may appear positive on the surface, but still lead to negative consequences. In this work, we present a computational approach to interpreting stereotypes in text through the Stereotype Content Model (SCM), a comprehensive causal theory from social psychology. The SCM proposes that stereotypes can be understood along two primary dimensions: warmth and competence. We present a method for defining warmth and competence axes in semantic embedding space, and show that the four quadrants defined by this subspace accurately represent the warmth and competence concepts, according to annotated lexicons. We then apply our computational SCM model to textual stereotype data and show that it compares favourably with survey-based studies in the psychological literature. Furthermore, we explore various strategies to counter stereotypical beliefs with anti-stereotypes. It is known that countering stereotypes with anti-stereotypical examples is one of the most effective ways to reduce biased thinking, yet the problem of generating anti-stereotypes has not been previously studied. Thus, a better understanding of how to generate realistic and effective anti-stereotypes can contribute to addressing pressing societal concerns of stereotyping, prejudice, and discrimination.

When comparing entities extracted by a medical entity recognition system with gold standard annotations over a test set, two types of mismatches might occur, label mismatch or span mismatch. Here we focus on span mismatch and show that its severity can vary from a serious error to a fully acceptable entity extraction due to the subjectivity of span annotations. For a domain-specific BERT-based NER system, we showed that 25% of the errors have the same labels and overlapping span with gold standard entities. We collected expert judgement which shows more than 90% of these mismatches are accepted or partially accepted by the user. Using the training set of the NER system, we built a fast and lightweight entity classifier to approximate the user experience of such mismatches through accepting or rejecting them. The decisions made by this classifier are used to calculate a learning-based F-score which is shown to be a better approximation of a forgiving user’s experience than the relaxed F-score. We demonstrated the results of applying the proposed evaluation metric for a variety of deep learning medical entity recognition models trained with two datasets.

NLP research has attained high performances in abusive language detection as a supervised classification task. While in research settings, training and test datasets are usually obtained from similar data samples, in practice systems are often applied on data that are different from the training set in topic and class distributions. Also, the ambiguity in class definitions inherited in this task aggravates the discrepancies between source and target datasets. We explore the topic bias and the task formulation bias in cross-dataset generalization. We show that the benign examples in the Wikipedia Detox dataset are biased towards platform-specific topics. We identify these examples using unsupervised topic modeling and manual inspection of topics’ keywords. Removing these topics increases cross-dataset generalization, without reducing in-domain classification performance. For a robust dataset design, we suggest applying inexpensive unsupervised methods to inspect the collected data and downsize the non-generalizable content before manually annotating for class labels.

Entity recognition is a critical first step to a number of clinical NLP applications, such as entity linking and relation extraction. We present the first attempt to apply state-of-the-art entity recognition approaches on a newly released dataset, MedMentions. This dataset contains over 4000 biomedical abstracts, annotated for UMLS semantic types. In comparison to existing datasets, MedMentions contains a far greater number of entity types, and thus represents a more challenging but realistic scenario in a real-world setting. We explore a number of relevant dimensions, including the use of contextual versus non-contextual word embeddings, general versus domain-specific unsupervised pre-training, and different deep learning architectures. We contrast our results against the well-known i2b2 2010 entity recognition dataset, and propose a new method to combine general and domain-specific information. While producing a state-of-the-art result for the i2b2 2010 task (F1 = 0.90), our results on MedMentions are significantly lower (F1 = 0.63), suggesting there is still plenty of opportunity for improvement on this new data.

Language toxicity identification presents a gray area in the ethical debate surrounding freedom of speech and censorship. Today’s social media landscape is littered with unfiltered content that can be anywhere from slightly abusive to hate inducing. In response, we focused on training a multi-label classifier to detect both the type and level of toxicity in online content. This content is typically colloquial and conversational in style. Its classification therefore requires huge amounts of annotated data due to its variability and inconsistency. We compare standard methods of text classification in this task. A conventional one-vs-rest SVM classifier with character and word level frequency-based representation of text reaches 0.9763 ROC AUC score. We demonstrated that leveraging more advanced technologies such as word embeddings, recurrent neural networks, attention mechanism, stacking of classifiers and semi-supervised training can improve the ROC AUC score of classification to 0.9862. We suggest that in order to choose the right model one has to consider the accuracy of models as well as inference complexity based on the application.