Model interpretability in toxicity detection greatly profits from token-level annotations. However, currently, such annotations are only available in English. We introduce a dataset annotated for offensive language detection sourced from a news forum, notable for its incorporation of the Austrian German dialect, comprising 4,562 user comments. In addition to binary offensiveness classification, we identify spans within each comment constituting vulgar language or representing targets of offensive statements. We evaluate fine-tuned Transformer models as well as large language models in a zero- and few-shot fashion. The results indicate that while fine-tuned models excel in detecting linguistic peculiarities such as vulgar dialect, large language models demonstrate superior performance in detecting offensiveness in AustroTox.

Taking note of the current challenges of the peer review system, this paper inventories the research tasks for analysing and possibly automating parts of the reviewing process, like matching submissions with a reviewer’s domain of expertise. For each of these tasks we list their associated datasets, analysing their quality in terms of available documentation of creation and use. Building up on this, we give a set of recommendations to take into account when collecting and releasing data.

This paper investigates the transparency in the creation of benchmarks and the use of leaderboards for measuring progress in NLP, with a focus on the relation extraction (RE) task. Existing RE benchmarks often suffer from insufficient documentation, lacking crucial details such as data sources, inter-annotator agreement, the algorithms used for the selection of instances for datasets, and information on potential biases like dataset imbalance. Progress in RE is frequently measured by leaderboards that rank systems based on evaluation methods, typically limited to aggregate metrics like F1-score. However, the absence of detailed performance analysis beyond these metrics can obscure the true generalisation capabilities of models. Our analysis reveals that widely used RE benchmarks, such as TACRED and NYT, tend to be highly imbalanced and contain noisy labels. Moreover, the lack of class-based performance metrics fails to accurately reflect model performance across datasets with a large number of relation types. These limitations should be carefully considered when reporting progress in RE. While our discussion centers on the transparency of RE benchmarks and leaderboards, the observations we discuss are broadly applicable to other NLP tasks as well. Rather than undermining the significance and value of existing RE benchmarks and the development of new models, this paper advocates for improved documentation and more rigorous evaluation to advance the field.

This paper describes the HEVS-TUW team submission to the SemEval-2023 Task 8: Causal Claims. We participated in two subtasks: (1) causal claims detection and (2) PIO identification. For subtask 1, we experimented with an ensemble of weakly supervised question detection and fine-tuned Transformer-based models. For subtask 2 of PIO frame extraction, we used a combination of deep representation learning and a rule-based approach. Our best model for subtask 1 ranks fourth with an F1-score of 65.77%. It shows moderate benefit from ensembling models pre-trained on independent categories. The results for subtask 2 warrant further investigation for improvement.

The definitions of abusive, offensive, toxic and uncivil comments used for annotating corpora for automated content moderation are highly intersected and researchers call for their disambiguation. We summarize the definitions of these terms as they appear in 23 papers across different fields. We compare examples given for uncivil, offensive, and toxic comments, attempting to foster more unified scientific resources. Additionally, we stress that the term incivility that frequently appears in social science literature has hardly been mentioned in the literature we analyzed that focuses on computational linguistics and natural language processing.

This paper describes our contribution to the Answer Localization track of the MedVidQA 2022 Shared Task. We propose two answer localization approaches that use only textual information extracted from the video. In particular, our approaches exploit the text extracted from the video’s transcripts along with the text displayed in the video’s frames to create a set of features. Having created a set of features that represents a video’s textual information, we employ four different models to measure the similarity between a video’s segment and a corresponding question. Then, we employ two different methods to obtain the start and end times of the identified answer. One of them is based on a random forest regressor, whereas the other one uses an unsupervised peak detection model to detect the answer’s start time. Our findings suggest that for this task, leveraging only text-related features (transmitted either verbally or visually) and using a small amount of training data, lead to significant improvements over the benchmark Video Span Localization model that is based on deep neural networks.

We present a new gold-standard dataset and a benchmark for the Research Theme Identification task, a sub-task of the Scholarly Knowledge Graph Generation shared task, at the 3rd Workshop on Scholarly Document Processing. The objective of the shared task was to label given research papers with research themes from a total of 36 themes. The benchmark was compiled using data drawn from the largest overall assessment of university research output ever undertaken globally (the Research Excellence Framework - 2014). We provide a performance comparison of a transformer-based ensemble, which obtains multiple predictions for a research paper, given its multiple textual fields (e.g. title, abstract, reference), with traditional machine learning models. The ensemble involves enriching the initial data with additional information from open-access digital libraries and Argumentative Zoning techniques (CITATION). It uses a weighted sum aggregation for the multiple predictions to obtain a final single prediction for the given research paper. Both data and the ensemble are publicly available on https://www.kaggle.com/competitions/sdp2022-scholarly-knowledge-graph-generation/data?select=task1_test_no_label.csv and https://github.com/ProjectDoSSIER/sdp2022, respectively.

We present DreamDrug, a crowdsourced dataset for detecting mentions of drugs in noisy user-generated item listings from darknet markets. Our dataset contains nearly 15,000 manually annotated drug entities in over 3,500 item listings scraped from the darknet market platform “DreamMarket” in 2017. We also train and evaluate baseline models for detecting these entities, using contextual language models fine-tuned in a few-shot setting and on the full dataset, and examine the effect of pretraining on in-domain unannotated corpora.

The search for Participants, Interventions, and Outcomes (PIO) in clinical trial reports is a critical task in Evidence Based Medicine. For an automatic PIO extraction, high-quality corpora are needed. Obtaining such a corpus from crowdworkers, however, has been shown to be ineffective since (i) workers usually lack domain-specific expertise to conduct the task with sufficient quality, and (ii) the standard approach of annotating entire abstracts of trial reports as one task-instance (i.e. HIT) leads to an uneven distribution in task effort. In this paper, we switch from entire abstract to sentence annotation, referred to as the SenBase approach. We build upon SenBase in SenSupport, where we compensate the lack of domain-specific expertise of crowdworkers by showing for each task-instance similar sentences that are already annotated by experts. Such tailored task-instance examples are retrieved via unsupervised semantic short-text similarity (SSTS) method – and we evaluate nine methods to find an effective solution for SenSupport. We compute the Cohen’s Kappa agreement between crowd-annotations and gold standard annotations and show that (i) both sentence-based approaches outperform a Baseline approach where entire abstracts are annotated; (ii) supporting annotators with tailored task-instance examples is the best performing approach with Kappa agreements of 0.78/0.75/0.69 for P, I, and O respectively.

Volatility prediction—an essential concept in financial markets—has recently been addressed using sentiment analysis methods. We investigate the sentiment of annual disclosures of companies in stock markets to forecast volatility. We specifically explore the use of recent Information Retrieval (IR) term weighting models that are effectively extended by related terms using word embeddings. In parallel to textual information, factual market data have been widely used as the mainstream approach to forecast market risk. We therefore study different fusion methods to combine text and market data resources. Our word embedding-based approach significantly outperforms state-of-the-art methods. In addition, we investigate the characteristics of the reports of the companies in different financial sectors.

In this paper, we address the shortage of evaluation benchmarks on Persian (Farsi) language by creating and making available a new benchmark for English to Persian Cross Lingual Word Sense Disambiguation (CL-WSD). In creating the benchmark, we follow the format of the SemEval 2013 CL-WSD task, such that the introduced tools of the task can also be applied on the benchmark. In fact, the new benchmark extends the SemEval-2013 CL-WSD task to Persian language.