MemeGraphs: Linking Memes to Knowledge Graphs

Memes are a popular form of communicating trends and ideas in social media and on the internet in general, combining the modalities of images and text. They can express humor and sarcasm but can also have offensive content. Analyzing and classifying memes automatically is challenging since their interpretation relies on the understanding of visual elements, language, and background knowledge. Thus, it is important to meaningfully represent these sources and the interaction between them in order to classify a meme as a whole. In this work, we propose to use scene graphs, that express images in terms of objects and their visual relations, and knowledge graphs as structured representations for meme classification with a Transformer-based architecture. We compare our approach with ImgBERT, a multimodal model that uses only learned (instead of structured) representations of the meme, and observe consistent improvements. We further provide a dataset with human graph annotations that we compare to automatically generated graphs and entity linking. Analysis shows that automatic methods link more entities than human annotators and that automatically generated graphs are better suited for hatefulness classification in memes.

Cross-functional Analysis of Generalisation in Behavioural Learning

In behavioural testing, system functionalities underrepresented in the standard evaluation setting (with a held-out test set) are validated through controlled input-output pairs. Optimising performance on the behavioural tests during training (behavioural learning) would improve coverage of phenomena not sufficiently represented in the i.i.d. data and could lead to seemingly more robust models. However, there is the risk that the model narrowly captures spurious correlations from the behavioural test suite, leading to overestimation and misrepresentation of model performance -- one of the original pitfalls of traditional evaluation. In this work, we introduce BeLUGA, an analysis method for evaluating behavioural learning considering generalisation across dimensions of different granularity levels. We optimise behaviour-specific loss functions and evaluate models on several partitions of the behavioural test suite controlled to leave out specific phenomena. An aggregate score measures generalisation to unseen functionalities (or overfitting). We use BeLUGA to examine three representative NLP tasks (sentiment analysis, paraphrase identification and reading comprehension) and compare the impact of a diverse set of regularisation and domain generalisation methods on generalisation performance.

ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion

Self-supervised knowledge-graph completion (KGC) relies on estimating a scoring model over (entity, relation, entity)-tuples, for example, by embedding an initial knowledge graph. Prediction quality can be improved by calibrating the scoring model, typically by adjusting the prediction thresholds using manually annotated examples. In this paper, we attempt for the first time cold-start calibration for KGC, where no annotated examples exist initially for calibration, and only a limited number of tuples can be selected for annotation. Our new method ACTC finds good per-relation thresholds efficiently based on a limited set of annotated tuples. Additionally to a few annotated tuples, ACTC also leverages unlabeled tuples by estimating their correctness with Logistic Regression or Gaussian Process classifiers. We also experiment with different methods for selecting candidate tuples for annotation: density-based and random selection. Experiments with five scoring models and an oracle annotator show an improvement of 7% points when using ACTC in the challenging setting with an annotation budget of only 10 tuples, and an average improvement of 4% points over different budgets.

ReInform: Selecting paths with reinforcement learning for contextualized link prediction

We propose to use reinforcement learning to inform transformer-based contextualized link prediction models by providing paths that are most useful for predicting the correct answer. This is in contrast to previous approaches, that either used reinforcement learning (RL) to directly search for the answer, or based their prediction on limited or randomly selected context. Our experiments on WN18RR and FB15k-237 show that contextualized link prediction models consistently outperform RL-based answer search, and that additional improvements (of up to 13.5\% MRR) can be gained by combining RL with a link prediction model.

SepLL: Separating Latent Class Labels from Weak Supervision Noise

In the weakly supervised learning paradigm, labeling functions automatically assign heuristic, often noisy, labels to data samples. In this work, we provide a method for learning from weak labels by separating two types of complementary information associated with the labeling functions: information related to the target label and information specific to one labeling function only. Both types of information are reflected to different degrees by all labeled instances. In contrast to previous works that aimed at correcting or removing wrongly labeled instances, we learn a branched deep model that uses all data as-is, but splits the labeling function information in the latent space. Specifically, we propose the end-to-end model SepLL which extends a transformer classifier by introducing a latent space for labeling function specific and task-specific information. The learning signal is only given by the labeling functions matches, no pre-processing or label model is required for our method. Notably, the task prediction is made from the latent layer without any direct task signal. Experiments on Wrench text classification tasks show that our model is competitive with the state-of-the-art, and yields a new best average performance.

XPASC: Measuring Generalization in Weak Supervision

Weak supervision is leveraged in a wide range of domains and tasks due to its ability to create massive amounts of labeled data, requiring only little manual effort. Standard approaches use labeling functions to specify signals that are relevant for the labeling. It has been conjectured that weakly supervised models over-rely on those signals and as a result suffer from overfitting. To verify this assumption, we introduce a novel method, XPASC (eXPlainability-Association SCore), for measuring the generalization of a model trained with a weakly supervised dataset. Considering the occurrences of features, classes and labeling functions in a dataset, XPASC takes into account the relevance of each feature for the predictions of the model as well as the associations of the feature with the class and the labeling function, respectively. The association in XPASC can be measured in two variants: XPASC-CHI SQAURE measures associations relative to their statistical significance, while XPASC-PPMI measures association strength more generally. We use XPASC to analyze KnowMAN, an adversarial architecture intended to control the degree of generalization from the labeling functions and thus to mitigate the problem of overfitting. On one hand, we show that KnowMAN is able to control the degree of generalization through a hyperparameter. On the other hand, results and qualitative analysis show that generalization and performance do not relate one-to-one, and that the highest degree of generalization does not necessarily imply the best performance. Therefore methods that allow for controlling the amount of generalization can achieve the right degree of benign overfitting. Our contributions in this study are i) the XPASC score to measure generalization in weakly-supervised models, ii) evaluation of XPASC across datasets and models and iii) the release of the XPASC implementation.

Topic Segmentation of Research Article Collections

Collections of research article data harvested from the web have become common recently since they are important resources for experimenting on tasks such as named entity recognition, text summarization, or keyword generation. In fact, certain types of experiments require collections that are both large and topically structured, with records assigned to separate research disciplines. Unfortunately, the current collections of publicly available research articles are either small or heterogeneous and unstructured. In this work, we perform topic segmentation of a paper data collection that we crawled and produce a multitopic dataset of roughly seven million paper data records. We construct a taxonomy of topics extracted from the data records and then annotate each document with its corresponding topic from that taxonomy. As a result, it is possible to use this newly proposed dataset in two modalities: as a heterogeneous collection of documents from various disciplines or as a set of homogeneous collections, each from a single research topic.

Is the Computation of Abstract Sameness Relations Human-Like in Neural Language Models?

In recent years, deep neural language models have made strong progress in various NLP tasks. This work explores one facet of the question whether state-of-the-art NLP models exhibit elementary mechanisms known from human cognition. The exploration is focused on a relatively primitive mechanism for which there is a lot of evidence from various psycholinguistic experiments with infants. The computation of "abstract sameness relations" is assumed to play an important role in human language acquisition and processing, especially in learning more complex grammar rules. In order to investigate this mechanism in BERT and other pre-trained language models (PLMs), the experiment designs from studies with infants were taken as the starting point. On this basis, we designed experimental settings in which each element from the original studies was mapped to a component of language models. Even though the task in our experiments was relatively simple, the results suggest that the cognitive faculty of computing abstract sameness relations is stronger in infants than in all investigated PLMs.

WeaNF: Weak Supervision with Normalizing Flows

A popular approach to decrease the need for costly manual annotation of large data sets is weak supervision, which introduces problems of noisy labels, coverage and bias. Methods for overcoming these problems have either relied on discriminative models, trained with cost functions specific to weak supervision, and more recently, generative models, trying to model the output of the automatic annotation process. In this work, we explore a novel direction of generative modeling for weak supervision: Instead of modeling the output of the annotation process (the labeling function matches), we generatively model the input-side data distributions (the feature space) covered by labeling functions. Specifically, we estimate a density for each weak labeling source, or labeling function, by using normalizing flows. An integral part of our method is the flow-based modeling of multiple simultaneously matching labeling functions, and therefore phenomena such as labeling function overlap and correlations are captured. We analyze the effectiveness and modeling capabilities on various commonly used weak supervision data sets, and show that weakly supervised normalizing flows compare favorably to standard weak supervision baselines.

ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision

A way to overcome expensive and time-consuming manual data labeling is weak supervision - automatic annotation of data samples via a predefined set of labeling functions (LFs), rule-based mechanisms that generate potentially erroneous labels. In this work, we investigate noise reduction techniques for weak supervision based on the principle of k-fold cross-validation. In particular, we extend two frameworks for detecting the erroneous samples in manually annotated data to the weakly supervised setting. Our methods profit from leveraging the information about matching LFs and detect noisy samples more accurately. We also introduce a new algorithm for denoising the weakly annotated data called ULF, that refines the allocation of LFs to classes by estimating the reliable LFs-to-classes joint matrix. Evaluation on several datasets shows that ULF successfully improves weakly supervised learning without using any manually labeled data.