Nithum Thain


2021

pdf
Can We Improve Model Robustness through Secondary Attribute Counterfactuals?
Ananth Balashankar | Xuezhi Wang | Ben Packer | Nithum Thain | Ed Chi | Alex Beutel
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Developing robust NLP models that perform well on many, even small, slices of data is a significant but important challenge, with implications from fairness to general reliability. To this end, recent research has explored how models rely on spurious correlations, and how counterfactual data augmentation (CDA) can mitigate such issues. In this paper we study how and why modeling counterfactuals over multiple attributes can go significantly further in improving model performance. We propose RDI, a context-aware methodology which takes into account the impact of secondary attributes on the model’s predictions and increases sensitivity for secondary attributes over reweighted counterfactually augmented data. By implementing RDI in the context of toxicity detection, we find that accounting for secondary attributes can significantly improve robustness, with improvements in sliced accuracy on the original dataset up to 7% compared to existing robustness methods. We also demonstrate that RDI generalizes to the coreference resolution task and provide guidelines to extend this to other tasks.

2020

pdf
Six Attributes of Unhealthy Conversations
Ilan Price | Jordan Gifford-Moore | Jory Flemming | Saul Musker | Maayan Roichman | Guillaume Sylvain | Nithum Thain | Lucas Dixon | Jeffrey Sorensen
Proceedings of the Fourth Workshop on Online Abuse and Harms

We present a new dataset of approximately 44000 comments labeled by crowdworkers. Each comment is labelled as either ‘healthy’ or ‘unhealthy’, in addition to binary labels for the presence of six potentially ‘unhealthy’ sub-attributes: (1) hostile; (2) antagonistic, insulting, provocative or trolling; (3) dismissive; (4) condescending or patronising; (5) sarcastic; and/or (6) an unfair generalisation. Each label also has an associated confidence score. We argue that there is a need for datasets which enable research based on a broad notion of ‘unhealthy online conversation’. We build this typology to encompass a substantial proportion of the individual comments which contribute to unhealthy online conversation. For some of these attributes, this is the first publicly available dataset of this scale. We explore the quality of the dataset, present some summary statistics and initial models to illustrate the utility of this data, and highlight limitations and directions for further research.

pdf
Toxicity Detection: Does Context Really Matter?
John Pavlopoulos | Jeffrey Sorensen | Lucas Dixon | Nithum Thain | Ion Androutsopoulos
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Moderation is crucial to promoting healthy online discussions. Although several ‘toxicity’ detection datasets and models have been published, most of them ignore the context of the posts, implicitly assuming that comments may be judged independently. We investigate this assumption by focusing on two questions: (a) does context affect the human judgement, and (b) does conditioning on context improve performance of toxicity detection systems? We experiment with Wikipedia conversations, limiting the notion of context to the previous post in the thread and the discussion title. We find that context can both amplify or mitigate the perceived toxicity of posts. Moreover, a small but significant subset of manually labeled posts (5% in one of our experiments) end up having the opposite toxicity labels if the annotators are not provided with context. Surprisingly, we also find no evidence that context actually improves the performance of toxicity classifiers, having tried a range of classifiers and mechanisms to make them context aware. This points to the need for larger datasets of comments annotated in context. We make our code and data publicly available.

2019

pdf
Debiasing Embeddings for Reduced Gender Bias in Text Classification
Flavien Prost | Nithum Thain | Tolga Bolukbasi
Proceedings of the First Workshop on Gender Bias in Natural Language Processing

(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation classification (De-Arteaga et al., 2019). We show that traditional techniques for debiasing embeddings can actually worsen the bias of the downstream classifier by providing a less noisy channel for communicating gender information. With a relatively minor adjustment, however, we show how these same techniques can be used to simultaneously reduce bias and maintain high classification accuracy.

pdf
ConvAI at SemEval-2019 Task 6: Offensive Language Identification and Categorization with Perspective and BERT
John Pavlopoulos | Nithum Thain | Lucas Dixon | Ion Androutsopoulos
Proceedings of the 13th International Workshop on Semantic Evaluation

This paper presents the application of two strong baseline systems for toxicity detection and evaluates their performance in identifying and categorizing offensive language in social media. PERSPECTIVE is an API, that serves multiple machine learning models for the improvement of conversations online, as well as a toxicity detection system, trained on a wide variety of comments from platforms across the Internet. BERT is a recently popular language representation model, fine tuned per task and achieving state of the art performance in multiple NLP tasks. PERSPECTIVE performed better than BERT in detecting toxicity, but BERT was much better in categorizing the offensive type. Both baselines were ranked surprisingly high in the SEMEVAL-2019 OFFENSEVAL competition, PERSPECTIVE in detecting an offensive post (12th) and BERT in categorizing it (11th). The main contribution of this paper is the assessment of two strong baselines for the identification (PERSPECTIVE) and the categorization (BERT) of offensive language with little or no additional training data.

2018

pdf
WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community
Yiqing Hua | Cristian Danescu-Niculescu-Mizil | Dario Taraborelli | Nithum Thain | Jeffery Sorensen | Lucas Dixon
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

We present a corpus that encompasses the complete history of conversations between contributors to Wikipedia, one of the largest online collaborative communities. By recording the intermediate states of conversations - including not only comments and replies, but also their modifications, deletions and restorations - this data offers an unprecedented view of online conversation. Our framework is designed to be language agnostic, and we show that it extracts high quality data in both Chinese and English. This level of detail supports new research questions pertaining to the process (and challenges) of large-scale online collaboration. We illustrate the corpus’ potential with two case studies on English Wikipedia that highlight new perspectives on earlier work. First, we explore how a person’s conversational behavior depends on how they relate to the discussion’s venue. Second, we show that community moderation of toxic behavior happens at a higher rate than previously estimated.

pdf
Conversations Gone Awry: Detecting Early Signs of Conversational Failure
Justine Zhang | Jonathan Chang | Cristian Danescu-Niculescu-Mizil | Lucas Dixon | Yiqing Hua | Dario Taraborelli | Nithum Thain
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

One of the main challenges online social systems face is the prevalence of antisocial behavior, such as harassment and personal attacks. In this work, we introduce the task of predicting from the very start of a conversation whether it will get out of hand. As opposed to detecting undesirable behavior after the fact, this task aims to enable early, actionable prediction at a time when the conversation might still be salvaged. To this end, we develop a framework for capturing pragmatic devices—such as politeness strategies and rhetorical prompts—used to start a conversation, and analyze their relation to its future trajectory. Applying this framework in a controlled setting, we demonstrate the feasibility of detecting early warning signs of antisocial behavior in online discussions.