Data quality is crucial for training accurate, unbiased, and trustworthy machine learning models as well as for their correct evaluation. Recent work, however, has shown that even popular datasets used to train and evaluate state-of-the-art models contain a non-negligible amount of erroneous annotations, biases, or artifacts. While practices and guidelines regarding dataset creation projects exist, to our knowledge, large-scale analysis has yet to be performed on how quality management is conducted when creating natural language datasets and whether these recommendations are followed. Therefore, we first survey and summarize recommended quality management practices for dataset creation as described in the literature and provide suggestions for applying them. Then, we compile a corpus of 591 scientific publications introducing text datasets and annotate it for quality-related aspects, such as annotator management, agreement, adjudication, or data validation. Using these annotations, we then analyze how quality management is conducted in practice. A majority of the annotated publications apply good or excellent quality management. However, we deem the effort of 30% of the studies as only subpar. Our analysis also shows common errors, especially when using inter-annotator agreement and computing annotation error rates.

Annotated data is an essential ingredient in natural language processing for training and evaluating machine learning models. It is therefore very desirable for the annotations to be of high quality. Recent work, however, has shown that several popular datasets contain a surprising number of annotation errors or inconsistencies. To alleviate this issue, many methods for annotation error detection have been devised over the years. While researchers show that their approaches work well on their newly introduced datasets, they rarely compare their methods to previous work or on the same datasets. This raises strong concerns on methods’ general performance and makes it difficult to assess their strengths and weaknesses. We therefore reimplement 18 methods for detecting potential annotation errors and evaluate them on 9 English datasets for text classification as well as token and span labeling. In addition, we define a uniform evaluation setup including a new formalization of the annotation error detection task, evaluation protocol, and general best practices. To facilitate future research and reproducibility, we release our datasets and implementations in an easy-to-use and open source software package. 1

The authors of this work (“Annotation Curricula to Implicitly Train Non-Expert Annotators” by Ji-Ung Lee, Jan-Christoph Klie, and Iryna Gurevych in Computational Linguistics 48:2 https://doi.org/10.1162/coli_a_00436 ) discovered an incorrect inequality symbol in section 5.3 (page 360). The paper stated that the differences in the annotation times for the control instances result in a p-value of 0.200 which is smaller than 0.05 ( p = 0.200 < 0.05). As 0.200 is of course larger than 0.05, the correct inequality symbol is p = 0.200 > 0.05, which is in line with the conclusion that follows in the text. The paper has been updated accordingly.

Peer review is a key component of the publishing process in most fields of science. Increasing submission rates put a strain on reviewing quality and efficiency, motivating the development of applications to support the reviewing and editorial work. While existing NLP studies focus on the analysis of individual texts, editorial assistance often requires modeling interactions between pairs of texts—yet general frameworks and datasets to support this scenario are missing. Relationships between texts are the core object of the intertextuality theory—a family of approaches in literary studies not yet operationalized in NLP. Inspired by prior theoretical work, we propose the first intertextual model of text-based collaboration, which encompasses three major phenomena that make up a full iteration of the review–revise–and–resubmit cycle: pragmatic tagging, linking, and long-document version alignment. While peer review is used across the fields of science and publication formats, existing datasets solely focus on conference-style review in computer science. Addressing this, we instantiate our proposed model in the first annotated multidomain corpus in journal-style post-publication open peer review, and provide detailed insights into the practical aspects of intertextual annotation. Our resource is a major step toward multidomain, fine-grained applications of NLP in editorial support for peer review, and our intertextual framework paves the path for general-purpose modeling of text-based collaboration. We make our corpus, detailed annotation guidelines, and accompanying code publicly available. 1

Annotation studies often require annotators to familiarize themselves with the task, its annotation scheme, and the data domain. This can be overwhelming in the beginning, mentally taxing, and induce errors into the resulting annotations; especially in citizen science or crowdsourcing scenarios where domain expertise is not required. To alleviate these issues, this work proposes annotation curricula, a novel approach to implicitly train annotators. The goal is to gradually introduce annotators into the task by ordering instances to be annotated according to a learning curriculum. To do so, this work formalizes annotation curricula for sentence- and paragraph-level annotation tasks, defines an ordering strategy, and identifies well-performing heuristics and interactively trained models on three existing English datasets. Finally, we provide a proof of concept for annotation curricula in a carefully designed user study with 40 voluntary participants who are asked to identify the most fitting misconception for English tweets about the Covid-19 pandemic. The results indicate that using a simple heuristic to order instances can already significantly reduce the total annotation time while preserving a high annotation quality. Annotation curricula thus can be a promising research direction to improve data collection. To facilitate future research—for instance, to adapt annotation curricula to specific tasks and expert annotation scenarios—all code and data from the user study consisting of 2,400 annotations is made available. 1

Cross-document event coreference resolution (CDCR) is an NLP task in which mentions of events need to be identified and clustered throughout a collection of documents. CDCR aims to benefit downstream multidocument applications, but despite recent progress on corpora and system development, downstream improvements from applying CDCR have not been shown yet. We make the observation that every CDCR system to date was developed, trained, and tested only on a single respective corpus. This raises strong concerns on their generalizability—a must-have for downstream applications where the magnitude of domains or event mentions is likely to exceed those found in a curated corpus. To investigate this assumption, we define a uniform evaluation setup involving three CDCR corpora: ECB+, the Gun Violence Corpus, and the Football Coreference Corpus (which we reannotate on token level to make our analysis possible). We compare a corpus-independent, feature-based system against a recent neural system developed for ECB+. Although being inferior in absolute numbers, the feature-based system shows more consistent performance across all corpora whereas the neural system is hit-or-miss. Via model introspection, we find that the importance of event actions, event time, and so forth, for resolving coreference in practice varies greatly between the corpora. Additional analysis shows that several systems overfit on the structure of the ECB+ corpus. We conclude with recommendations on how to achieve generally applicable CDCR systems in the future—the most important being that evaluation on multiple CDCR corpora is strongly necessary. To facilitate future research, we release our dataset, annotation guidelines, and system implementation to the public. 1

Despite an ever-growing number of word representation models introduced for a large number of languages, there is a lack of a standardized technique to provide insights into what is captured by these models. Such insights would help the community to get an estimate of the downstream task performance, as well as to design more informed neural architectures, while avoiding extensive experimentation that requires substantial computational resources not all researchers have access to. A recent development in NLP is to use simple classification tasks, also called probing tasks, that test for a single linguistic feature such as part-of-speech. Existing studies mostly focus on exploring the linguistic information encoded by the continuous representations of English text. However, from a typological perspective the morphologically poor English is rather an outlier: The information encoded by the word order and function words in English is often stored on a subword, morphological level in other languages. To address this, we introduce 15 type-level probing tasks such as case marking, possession, word length, morphological tag count, and pseudoword identification for 24 languages. We present a reusable methodology for creation and evaluation of such tests in a multilingual setting, which is challenging because of a lack of resources, lower quality of tools, and differences among languages. We then present experiments on several diverse multilingual word embedding models, in which we relate the probing task performance for a diverse set of languages to a range of five classic NLP tasks: POS-tagging, dependency parsing, semantic role labeling, named entity recognition, and natural language inference. We find that a number of probing tests have significantly high positive correlation to the downstream tasks, especially for morphologically rich languages. We show that our tests can be used to explore word embeddings or black-box neural models for linguistic cues in a multilingual setting. We release the probing data sets and the evaluation suite LINSPECTOR with https://github.com/UKPLab/linspector .

In this article, we present a novel approach for parsing argumentation structures. We identify argument components using sequence labeling at the token level and apply a new joint model for detecting argumentation structures. The proposed model globally optimizes argument component types and argumentative relations using Integer Linear Programming. We show that our model significantly outperforms challenging heuristic baselines on two different types of discourse. Moreover, we introduce a novel corpus of persuasive essays annotated with argumentation structures. We show that our annotation scheme and annotation guidelines successfully guide human annotators to substantial agreement.

The goal of argumentation mining, an evolving research field in computational linguistics, is to design methods capable of analyzing people's argumentation. In this article, we go beyond the state of the art in several ways. (i) We deal with actual Web data and take up the challenges given by the variety of registers, multiple domains, and unrestricted noisy user-generated Web discourse. (ii) We bridge the gap between normative argumentation theories and argumentation phenomena encountered in actual data by adapting an argumentation model tested in an extensive annotation study. (iii) We create a new gold standard corpus (90k tokens in 340 documents) and experiment with several machine learning methods to identify argument components. We offer the data, source codes, and annotation guidelines to the community under free licenses. Our findings show that argumentation mining in user-generated Web discourse is a feasible but challenging task.

Uncertainty is an important linguistic phenomenon that is relevant in various Natural Language Processing applications, in diverse genres from medical to community generated, newswire or scientific discourse, and domains from science to humanities. The semantic uncertainty of a proposition can be identified in most cases by using a finite dictionary (i.e., lexical cues) and the key steps of uncertainty detection in an application include the steps of locating the (genre- and domain-specific) lexical cues, disambiguating them, and linking them with the units of interest for the particular application (e.g., identified events in information extraction). In this study, we focus on the genre and domain differences of the context-dependent semantic uncertainty cue recognition task. We introduce a unified subcategorization of semantic uncertainty as different domain applications can apply different uncertainty categories. Based on this categorization, we normalized the annotation of three corpora and present results with a state-of-the-art uncertainty cue recognition model for four fine-grained categories of semantic uncertainty. Our results reveal the domain and genre dependence of the problem; nevertheless, we also show that even a distant source domain data set can contribute to the recognition and disambiguation of uncertainty cues, efficiently reducing the annotation costs needed to cover a new domain. Thus, the unified subcategorization and domain adaptation for training the models offer an efficient solution for cross-domain and cross-genre semantic uncertainty recognition.