A cornerstone of machine learning evaluation is the (often hidden) assumption that model and human responses are reliable enough to evaluate models against unitary, authoritative, “gold standard” data, via simple metrics such as accuracy, precision, and recall. The generative AI revolution would seem to explode this assumption, given the critical role stochastic inference plays. Yet, in spite of public demand for more transparency in AI—along with strong evidence that humans are unreliable judges—estimates of model reliability are conventionally based on, at most, a few output responses per input item. We adapt a method, previously used to evaluate the reliability of various metrics and estimators for machine learning evaluation, to determine whether an (existing or planned) dataset has enough responses per item to assure reliable null hypothesis statistical testing. We show that, for many common metrics, collecting even 5-10 responses per item (from each model and team of human evaluators) is not sufficient. We apply our methods to several of the very few extant gold standard test sets with multiple disaggregated responses per item and show that even these datasets lack enough responses per item. We show how our methods can help AI researchers make better decisions about how to collect data for AI evaluation.

Among the problems with leaderboard culture in NLP has been the widespread lack of confidence estimation in reported results. In this work, we present a framework and simulator for estimating p-values for comparisons between the results of two systems, in order to understand the confidence that one is actually better (i.e. ranked higher) than the other. What has made this difficult in the past is that each system must itself be evaluated by comparison to a gold standard. We define a null hypothesis that each system’s metric scores are drawn from the same distribution, using variance found naturally (though rarely reported) in test set items and individual labels on an item (responses) to produce the metric distributions. We create a test set that evenly mixes the responses of the two systems under the assumption the null hypothesis is true. Exploring how to best estimate the true p-value from a single test set under different metrics, tests, and sampling methods, we find that the presence of response variance (from multiple raters or multiple model versions) has a profound impact on p-value estimates for model comparison, and that choice of metric and sampling method is critical to providing statistical guarantees on model comparisons.

Annotator disagreement is often dismissed as noise or the result of poor annotation process quality. Others have argued that it can be meaningful. But lacking a rigorous statistical foundation, the analysis of disagreement patterns can resemble a high-tech form of tea-leaf-reading. We contribute a framework for analyzing the variation of per-item annotator response distributions to data for humans-in-the-loop machine learning. We provide visualizations for, and use the framework to analyze the variance in, a crowdsourced dataset of hard-to-classify examples from the OpenImages archive.

A common step in developing an understanding of a vertical domain, e.g. shopping, dining, movies, medicine, etc., is curating a taxonomy of categories specific to the domain. These human created artifacts have been the subject of research in embeddings that attempt to encode aspects of the partial ordering property of taxonomies. We compare Box Embeddings, a natural containment representation of category taxonomies, to partial-order embeddings and a baseline Bayes Net, in the context of representing the Medical Subject Headings (MeSH) taxonomy given a set of 300K PubMed articles with subject labels from MeSH. We deeply explore the experimental properties of training box embeddings, including preparation of the training data, sampling ratios and class balance, initialization strategies, and propose a fix to the original box objective. We then present first results in using these techniques for representing a bipartite learning problem (i.e. collaborative filtering) in the presence of taxonomic relations within each partition, inferring disease (anatomical) locations from their use as subject labels in journal articles. Our box model substantially outperforms all baselines for taxonomic reconstruction and bipartite relationship experiments. This performance improvement is observed both in overall accuracy and the weighted spread by true taxonomic depth.

We present a resource for the task of FrameNet semantic frame disambiguation of over 5,000 word-sentence pairs from the Wikipedia corpus. The annotations were collected using a novel crowdsourcing approach with multiple workers per sentence to capture inter-annotator disagreement. In contrast to the typical approach of attributing the best single frame to each word, we provide a list of frames with disagreement-based scores that express the confidence with which each frame applies to the word. This is based on the idea that inter-annotator disagreement is at least partly caused by ambiguity that is inherent to the text and frames. We have found many examples where the semantics of individual frames overlap sufficiently to make them acceptable alternatives for interpreting a sentence. We have argued that ignoring this ambiguity creates an overly arbitrary target for training and evaluating natural language processing systems - if humans cannot agree, why would we expect the correct answer from a machine to be any different? To process this data we also utilized an expanded lemma-set provided by the Framester system, which merges FN with WordNet to enhance coverage. Our dataset includes annotations of 1,000 sentence-word pairs whose lemmas are not part of FN. Finally we present metrics for evaluating frame disambiguation systems that account for ambiguity.

Distant supervision is a popular method for performing relation extraction from text that is known to produce noisy labels. Most progress in relation extraction and classification has been made with crowdsourced corrections to distant-supervised labels, and there is evidence that indicates still more would be better. In this paper, we explore the problem of propagating human annotation signals gathered for open-domain relation classification through the CrowdTruth methodology for crowdsourcing, that captures ambiguity in annotations by measuring inter-annotator disagreement. Our approach propagates annotations to sentences that are similar in a low dimensional embedding space, expanding the number of labels by two orders of magnitude. Our experiments show significant improvement in a sentence-level multi-class relation classifier.