This paper presents our approach to the SemEval-2025 Task 7 on Multilingual and Crosslingual Fact-Checked Claim Retrieval. We implemented a TF-IDF-based retrieval system with experimentation on vector dimensions and tokenization strategies. Our best-performing configuration used word-level tokenization with a vocabulary size of 15,000 features, achieving an average success@10 score of 0.78 on the development set and 0.69 on the test set across ten languages. Our system showed stronger performance on higher resource languages with large performance gaps compared to the top-ranked system, which achieved 0.96 average success@10. Our findings suggest that though advanced neural architectures are increasingly dominant in multilingual retrieval tasks, properly optimized traditional methods like TF-IDF remain competitive baselines, especially in limited resource scenarios.

This paper describes the DuluthNLP system that participated in Task 12 of SemEval-2023 on AfriSenti-SemEval: Sentiment Analysis for Low-resource African Languages using Twitter Dataset. Given a set of tweets, the task requires participating systems to classify each tweet as negative, positive or neutral. We evaluate a range of monolingual and multilingual pretrained models on the Twi language dataset, one among the 14 African languages included in the SemEval task. We introduce TwiBERT, a new pretrained model trained from scratch. We show that TwiBERT, along with mBERT, generally perform best when trained on the Twi dataset, achieving an F1 score of 64.29% on the official evaluation test data, which ranks 14 out of 30 of the total submissions for Track 10. The TwiBERT model is released at https://huggingface.co/sakrah/TwiBERT

This paper describes the DuluthNLP system that participated in Task 7 of SemEval-2022 on Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts. Given an instructional text with an omitted token, the task requires models to classify or rank the plausibility of potential fillers. To solve the task, we fine–tuned the models BERT, RoBERTa, and ELECTRA on training data where potential fillers are rated for plausibility. This is a challenging problem, as shown by BERT-based models achieving accuracy less than 45%. However, our ELECTRA model with tuned class weights on CrossEntropyLoss achieves an accuracy of 53.3% on the official evaluation test data, which ranks 6 out of the 8 total submissions for Subtask A.

As the rate of scientific output continues to grow, it is increasingly important to develop systems to improve interfaces between researchers and scholarly papers. Training models to extract scientific information from the full texts of scholarly documents is important for improving how we structure and access scientific information. However, there are few annotated corpora that provide full paper texts. This paper presents the NLPSharedTasks corpus, a new resource of 254 full text Shared Task Overview papers in NLP domains with annotated task descriptions. We calculated strict and relaxed inter-annotator agreement scores, achieving Cohen’s kappa coefficients of 0.44 and 0.95, respectively. Lastly, we performed a sentence classification task over the dataset, in order to generate a neural baseline for future research and to provide an example of how to preprocess unbalanced datasets of full scientific texts. We achieved an F1 score of 0.75 using SciBERT, fine-tuned and tested on a rebalanced version of the dataset.

There is currently a gap between the natural language expression of scholarly publications and their structured semantic content modeling to enable intelligent content search. With the volume of research growing exponentially every year, a search feature operating over semantically structured content is compelling. The SemEval-2021 Shared Task NLPContributionGraph (a.k.a. ‘the NCG task’) tasks participants to develop automated systems that structure contributions from NLP scholarly articles in the English language. Being the first-of-its-kind in the SemEval series, the task released structured data from NLP scholarly articles at three levels of information granularity, i.e. at sentence-level, phrase-level, and phrases organized as triples toward Knowledge Graph (KG) building. The sentence-level annotations comprised the few sentences about the article’s contribution. The phrase-level annotations were scientific term and predicate phrases from the contribution sentences. Finally, the triples constituted the research overview KG. For the Shared Task, participating systems were then expected to automatically classify contribution sentences, extract scientific terms and relations from the sentences, and organize them as KG triples. Overall, the task drew a strong participation demographic of seven teams and 27 participants. The best end-to-end task system classified contribution sentences at 57.27% F1, phrases at 46.41% F1, and triples at 22.28% F1. While the absolute performance to generate triples remains low, as conclusion to the article, the difficulty of producing such data and as a consequence of modeling it is highlighted.

This paper describes the Duluth system that participated in SemEval-2021 Task 11, NLP Contribution Graph. It details the extraction of contribution sentences and scientific entities and their relations from scholarly articles in the domain of Natural Language Processing. Our solution uses deBERTa for multi-class sentence classification to extract the contributing sentences and their type, and dependency parsing to outline each sentence and extract subject-predicate-object triples. Our system ranked fifth of seven for Phase 1: end-to-end pipeline, sixth of eight for Phase 2 Part 1: phrases and triples, and fifth of eight for Phase 2 Part 2: triples extraction.

We use pretrained transformer-based language models in SemEval-2020 Task 7: Assessing the Funniness of Edited News Headlines. Inspired by the incongruity theory of humor, we use a contrastive approach to capture the surprise in the edited headlines. In the official evaluation, our system gets 0.531 RMSE in Subtask 1, 11th among 49 submissions. In Subtask 2, our system gets 0.632 accuracy, 9th among 32 submissions.

This paper describes the Duluth systems that participated in SemEval–2020 Task 12, Multilingual Offensive Language Identification in Social Media (OffensEval–2020). We participated in the three English language tasks. Our systems provide a simple machine learning baseline using logistic regression. We trained our models on the distantly supervised training data made available by the task organizers and used no other resources. As might be expected we did not rank highly in the comparative evaluation: 79th of 85 in task A, 34th of 43 in task B, and 24th of 39 in task C. We carried out a qualitative analysis of our results and found that the class labels in the gold standard data are somewhat noisy. We hypothesize that the extremely high accuracy (>$ 90%) of the top ranked systems may reflect methods that learn the training data very well but may not generalize to the task of identifying offensive language in English. This analysis includes examples of tweets that despite being mildly redacted are still offensive.

This paper describes the Duluth systems that participated in SemEval–2019 Task 6, Identifying and Categorizing Offensive Language in Social Media (OffensEval). For the most part these systems took traditional Machine Learning approaches that built classifiers from lexical features found in manually labeled training data. However, our most successful system for classifying a tweet as offensive (or not) was a rule-based black–list approach, and we also experimented with combining the training data from two different but related SemEval tasks. Our best systems in each of the three OffensEval tasks placed in the middle of the comparative evaluation, ranking 57th of 103 in task A, 39th of 75 in task B, and 44th of 65 in task C.

This paper describes the Pioquinto Manterola Hyperpartisan News Detector, which participated in SemEval-2019 Task 4. Hyperpartisan news is highly polarized and takes a very biased or one–sided view of a particular story. We developed two variants of our system, the more successful was a Logistic Regression classifier based on unigram features. This was our official entry in the task, and it placed 23rd of 42 participating teams. Our second variant was a Convolutional Neural Network that did not perform as well.

This paper describes the UMDSub system that participated in Task 2 of SemEval-2018. We developed a system that predicts an emoji given the raw text in a English tweet. The system is a Multi-channel Convolutional Neural Network based on subword embeddings for the representation of tweets. This model improves on character or word based methods by about 2%. Our system placed 21st of 48 participating systems in the official evaluation.

This paper describes the Duluth UROP systems that participated in SemEval–2018 Task 2, Multilingual Emoji Prediction. We relied on a variety of ensembles made up of classifiers using Naive Bayes, Logistic Regression, and Random Forests. We used unigram and bigram features and tried to offset the skewness of the data through the use of oversampling. Our task evaluation results place us 19th of 48 systems in the English evaluation, and 5th of 21 in the Spanish. After the evaluation we realized that some simple changes to our pre-processing could significantly improve our results. After making these changes we attained results that would have placed us sixth in the English evaluation, and second in the Spanish.

This paper describes the ALANIS system that participated in Task 3 of SemEval-2018. We develop a system for detection of irony, as well as the detection of three types of irony: verbal polar irony, other verbal irony, and situational irony. The system uses a logistic regression model in subtask A and a voted classifier system with manually developed features to identify ironic tweets. This model improves on a naive bayes baseline by about 8 percent on training set.

Hypernym Discovery is the task of identifying potential hypernyms for a given term. A hypernym is a more generalized word that is super-ordinate to more specific words. This paper explores several approaches that rely on co-occurrence frequencies of word pairs, Hearst Patterns based on regular expressions, and word embeddings created from the UMBC corpus. Our system Babbage participated in Subtask 1A for English and placed 6th of 19 systems when identifying concept hypernyms, and 12th of 18 systems for entity hypernyms.

This paper describes the Duluth system that participated in SemEval-2017 Task 6 #HashtagWars: Learning a Sense of Humor. The system participated in Subtasks A and B using N-gram language models, ranking highly in the task evaluation. This paper discusses the results of our system in the development and evaluation stages and from two post-evaluation runs.

This paper describes the Duluth systems that participated in SemEval-2017 Task 7 : Detection and Interpretation of English Puns. The Duluth systems participated in all three subtasks, and relied on methods that included word sense disambiguation and measures of semantic relatedness.

Vector space methods that measure semantic similarity and relatedness often rely on distributional information such as co–occurrence frequencies or statistical measures of association to weight the importance of particular co–occurrences. In this paper, we extend these methods by incorporating a measure of semantic similarity based on a human curated taxonomy into a second–order vector representation. This results in a measure of semantic relatedness that combines both the contextual information available in a corpus–based vector space representation with the semantic knowledge found in a biomedical ontology. Our results show that incorporating semantic similarity into a second order co-occurrence matrices improves correlation with human judgments for both similarity and relatedness, and that our method compares favorably to various different word embedding methods that have recently been evaluated on the same reference standards we have used.

Health support forums have become a rich source of data that can be used to improve health care outcomes. A user profile, including information such as age and gender, can support targeted analysis of forum data. But users might not always disclose their age and gender. It is desirable then to be able to automatically extract this information from users’ content. However, to the best of our knowledge there is no such resource for author profiling of health forum data. Here we present a large corpus, with close to 85,000 users, for profiling and also outline our approach and benchmark results to automatically detect a user’s age and gender from their forum posts. We use a mix of features from a user’s text as well as forum specific features to obtain accuracy well above the baseline, thus showing that both our dataset and our method are useful and valid.