arXiv subjects

Lucas Dixon

Publications and source records attributed to Lucas Dixon.

46 records · Page 3Linked to original sources

arXiv2020

Toxicity Detection: Does Context Really Matter?

Moderation is crucial to promoting healthy on-line discussions. Although several `toxicity' detection datasets and models have been published, most of them ignore the context of the posts, implicitly assuming that comments maybe 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.

cs.CL↗

arXiv2019

Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification

Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of threshold-agnostic metrics that provide a nuanced view of this unintended bias, by considering the various ways that a classifier's score distribution can vary across designated groups. We also introduce a large new test set of online comments with crowd-sourced annotations for identity references. We use this to show how our metrics can be used to find new and potentially subtle unintended bias in existing public models.

cs.LG↗

arXiv2019

Limitations of Pinned AUC for Measuring Unintended Bias

This report examines the Pinned AUC metric introduced and highlights some of its limitations. Pinned AUC provides a threshold-agnostic measure of unintended bias in a classification model, inspired by the ROC-AUC metric. However, as we highlight in this report, there are ways that the metric can obscure different kinds of unintended biases when the underlying class distributions on which bias is being measured are not carefully controlled.

stat.ML↗

arXiv2018

WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community

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. 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 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. Finally the reconstruction framework is designed to be language agnostic, and we show that it can extract high quality conversational data in both Chinese and English.

cs.CL↗

arXiv2018

Conversations Gone Awry: Detecting Early Signs of Conversational Failure

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.

cs.CL↗

arXiv2017

Ex Machina: Personal Attacks Seen at Scale

The damage personal attacks cause to online discourse motivates many platforms to try to curb the phenomenon. However, understanding the prevalence and impact of personal attacks in online platforms at scale remains surprisingly difficult. The contribution of this paper is to develop and illustrate a method that combines crowdsourcing and machine learning to analyze personal attacks at scale. We show an evaluation method for a classifier in terms of the aggregated number of crowd-workers it can approximate. We apply our methodology to English Wikipedia, generating a corpus of over 100k high quality human-labeled comments and 63M machine-labeled ones from a classifier that is as good as the aggregate of 3 crowd-workers, as measured by the area under the ROC curve and Spearman correlation. Using this corpus of machine-labeled scores, our methodology allows us to explore some of the open questions about the nature of online personal attacks. This reveals that the majority of personal attacks on Wikipedia are not the result of a few malicious users, nor primarily the consequence of allowing anonymous contributions from unregistered users.

cs.CL↗

arXiv2016

Network Traffic Obfuscation and Automated Internet Censorship

Internet censors seek ways to identify and block internet access to information they deem objectionable. Increasingly, censors deploy advanced networking tools such as deep-packet inspection (DPI) to identify such connections. In response, activists and academic researchers have developed and deployed network traffic obfuscation mechanisms. These apply specialized cryptographic tools to attempt to hide from DPI the true nature and content of connections. In this survey, we give an overview of network traffic obfuscation and its role in circumventing Internet censorship. We provide historical and technical background that motivates the need for obfuscation tools, and give an overview of approaches to obfuscation used by state of the art tools. We discuss the latest research on how censors might detect these efforts. We also describe the current challenges to censorship circumvention research and identify concrete ways for the community to address these challenges.

cs.NI↗

arXiv2010

Open Graphs and Monoidal Theories

String diagrams are a powerful tool for reasoning about physical processes, logic circuits, tensor networks, and many other compositional structures. The distinguishing feature of these diagrams is that edges need not be connected to vertices at both ends, and these unconnected ends can be interpreted as the inputs and outputs of a diagram. In this paper, we give a concrete construction for string diagrams using a special kind of typed graph called an open-graph. While the category of open-graphs is not itself adhesive, we introduce the notion of a selective adhesive functor, and show that such a functor embeds the category of open-graphs into the ambient adhesive category of typed graphs. Using this functor, the category of open-graphs inherits "enough adhesivity" from the category of typed graphs to perform double-pushout (DPO) graph rewriting. A salient feature of our theory is that it ensures rewrite systems are "type-safe" in the sense that rewriting respects the inputs and outputs. This formalism lets us safely encode the interesting structure of a computational model, such as evaluation dynamics, with succinct, explicit rewrite rules, while the graphical representation absorbs many of the tedious details. Although topological formalisms exist for string diagrams, our construction is discreet, finitary, and enjoys decidable algorithms for composition and rewriting. We also show how open-graphs can be parametrised by graphical signatures, similar to the monoidal signatures of Joyal and Street, which define types for vertices in the diagrammatic language and constraints on how they can be connected. Using typed open-graphs, we can construct free symmetric monoidal categories, PROPs, and more general monoidal theories. Thus open-graphs give us a handle for mechanised reasoning in monoidal categories.

math.CT↗

arXiv2010

Open Graphs and Computational Reasoning

We present a form of algebraic reasoning for computational objects which are expressed as graphs. Edges describe the flow of data between primitive operations which are represented by vertices. These graphs have an interface made of half-edges (edges which are drawn with an unconnected end) and enjoy rich compositional principles by connecting graphs along these half-edges. In particular, this allows equations and rewrite rules to be specified between graphs. Particular computational models can then be encoded as an axiomatic set of such rules. Further rules can be derived graphically and rewriting can be used to simulate the dynamics of a computational system, e.g. evaluating a program on an input. Examples of models which can be formalised in this way include traditional electronic circuits as well as recent categorical accounts of quantum information.

cs.LO↗

arXiv2009

Graphical Reasoning in Compact Closed Categories for Quantum Computation

Compact closed categories provide a foundational formalism for a variety of important domains, including quantum computation. These categories have a natural visualisation as a form of graphs. We present a formalism for equational reasoning about such graphs and develop this into a generic proof system with a fixed logical kernel for equational reasoning about compact closed categories. Automating this reasoning process is motivated by the slow and error prone nature of manual graph manipulation. A salient feature of our system is that it provides a formal and declarative account of derived results that can include `ellipses'-style notation. We illustrate the framework by instantiating it for a graphical language of quantum computation and show how this can be used to perform symbolic computation.

cs.SC↗