Canada

This presentation describes the submission of UZH\_CLyp for the SemEval 2023 Task 9 ``Multilingual Tweet Intimacy Analysis&#39;&#39;. We achieved second-best results in all 10 languages according to the official Pearson&#39;s correlation regression evaluation measure. Our cross-lingual transfer learning approach explores the benefits of using a Head-First Fine-Tuning method (HeFiT) that first updates only the regression head parameters and then also updates the pre-trained transformer encoder parameters at a reduced learning rate. Additionally, we study the impact of using a small set of automatically generated examples (in our case, from ChatGPT) for low-resource settings where no human-labeled data is available. Our study shows that HeFiT stabilizes training and consistently improves results for pre-trained models that lack domain adaptation to tweets. Our study also shows a noticeable performance increase in cross-lingual learning when synthetic data is used, confirming the usefulness of current text generation systems to improve zero-shot baseline results. Finally, we examine how possible inconsistencies in the annotated data contribute to cross-lingual interference issues.

ACL 2023

UZH_CLyp at SemEval-2023 Task 9: Head-First Fine-Tuning and ChatGPT Data Generation for Cross-Lingual Learning in Tweet Intimacy Prediction

head first finetuning

cross lingual learning

text generation

domain adaptation

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

This presentation describes the submission of UZH\_CLyp for the SemEval 2023 Task 9 ``Multilingual Tweet Intimacy Analysis''. We achieved second-best results in all 10 languages according to the official Pearson's correlation regression evaluation measure. Our cross-lingual transfer learning approach explores the benefits of using a Head-First Fine-Tuning method (HeFiT) that first updates only the regression head parameters and then also updates the pre-trained transformer encoder parameters at a reduced learning rate. Additionally, we study the impact of using a small set of automatically generated examples (in our case, from ChatGPT) for low-resource settings where no human-labeled data is available. Our study shows that HeFiT stabilizes training and consistently improves results for pre-trained models that lack domain adaptation to tweets. Our study also shows a noticeable performance increase in cross-lingual learning when synthetic data is used, confirming the usefulness of current text generation systems to improve zero-shot baseline results. Finally, we examine how possible inconsistencies in the annotated data contribute to cross-lingual interference issues.

workshop paper

Human Value Detection in Arguments is a complex task requiring a high-level understanding of language due to the hidden nature of opinions and beliefs in arguments. In this presentation, the Augustine of Hippo team shows its solution to SemEval2023 Task 4: the proposed methodology leverages an unsurpervised explainable knowledge extraction system capable of identifying concepts to associate with human values.

Augustine of Hippo at SemEval-2023 Task 4: An Explainable Knowledge Extraction Method to Identify Human Values in Arguments with SuperASKE

We present our submission to SemEval-2023 Task 10: Explainable Detection of Online Sexism (EDOS). We address all three tasks: Task A consists of identifying whether a post is sexist. If so, Task B attempts to assign it one of four classes: threats, derogation, animosity, and prejudiced discussions. Task C aims for an even more fine-grained classification, divided among 11 classes. We experiment with fine-tuning of hate-tuned Transformer-based models and priming for generative models. In addition, we explore model-agnostic strategies, such as data augmentation techniques combined with active learning, as well as obfuscation of identity terms. Our official submissions obtain an F1 score of 0.83 for Task A, 0.58 for Task B and 0.32 for Task C.

UniBoe's at SemEval-2023 Task 10: Model-Agnostic Strategies for the Improvement of Hate-Tuned and Generative Models in the Classification of Sexist Posts

The MultiCoNER II shared task aims at de- tecting complex, ambiguous named entities with fine-grained types in a low context setting. Previous winning systems incorporated external knowledge bases to retrieve helpful contexts. In our submission we additionally propose splitting the NER task into two stages, a Span Extraction Step, and an Entity Classification step. Our results show that the former does not suffer from the low context setting comparably, and in so leading to a higher overall performance for an external KB-assisted system. We achieve 3rd place on the multilin- gual track and an average of 6th place overall.

NLPeople at SemEval-2023 Task 2: A Staged Approach for Multilingual Named Entity Recognition

Using pre-trained language models to implement classifiers from small to modest amounts of training data is an area of active research. The ability of large language models to generalize from few-shot examples and to produce strong classifiers is extended using the engineering approach of parameter-efficient tuning. Using the Explainable Detection of Online Sexism (EDOS) training data and a small number of trainable weights to create a tuned prompt vector, a competitive model for this task was built, which was top-ranked in Subtask B.

JUAGE at SemEval 2023 Task 10: Parameter Efficient Classification

Named Entity Recognition (NER) is a core natural language processing task in which pre-trained language models have shown remarkable performance. However, standard benchmarks like CoNLL 2003 do not address many of the challenges that deployed NER systems face, such as having to classify emerging or complex entities in a fine-grained way. In this paper we present a novel NER cascade approach comprising three steps: first, identifying candidate entities in the input sentence; second, linking the each candidate to an existing knowledge base; third, predicting the fine-grained category for each entity candidate. We empirically demonstrate the significance of external knowledge bases in accurately classifying fine-grained and emerging entities. Our system exhibits robust performance in the MultiCoNER2 shared task, even in the low-resource language setting where we leverage knowledge bases of high-resource languages.

IXA/Cogcomp at SemEval-2023 Task 2: Context-enriched Multilingual Named Entity Recognition Using Knowledge Bases

This paper describes the system and experimental results of an ensemble-based approach to multilingual framing detection for the submission of the ACCEPT team to the SemEval-2023 Task 3 on Framing Detection (Subtask 2). The approach is based on an ensemble that combines three different methods: a classifier based on large language models, a classifier based on static word embeddings, and an approach that uses external commonsense knowledge graphs, in particular, ConceptNet. The results of the three classification heads are aggregated into an overall prediction for each frame class.
Our best submission yielded a micro F1-score of 50.69% (rank 10) and a macro F1-score of 50.20% (rank 3) for English articles. Our experimental results show that static word embeddings and knowledge graphs are useful components for frame detection, while the ensemble of all three methods combines the strengths
of our three proposed methods. Through system ablations, we show that the commonsenseguided knowledge graphs are the outperforming method for many languages.

Team ACCEPT at SemEval-2023 Task 3: An Ensemble-based Approach to Multilingual Framing Detection

The Explainable Detection of Online Sexism task presents the problem of explainable sexism detection through fine-grained categorisation of sexist cases with three subtasks. Our team experimented with different ways to combat class imbalance throughout the tasks using data augmentation and loss alteration techniques. We tackled the challenge by utilising ensembles of Transformer models trained on different datasets, which are tested to find the balance between performance and interpretability. This solution ranked us in the top 40% of teams for each of the tracks. As a result, we present the new balanced dataset for sexism detection and the best model fine-tuned on it.

AdamR at SemEval-2023 Task 10: Solving the Class Imbalance Problem in Sexism Detection with Ensemble Learning

The use of Natural Language Processing techniques in the legal domain has become established for supporting attorneys and domain experts in content retrieval and decision-making. However, understanding the legal text poses relevant challenges in the recognition of domain-specific entities and the adaptation and explanation of predictive models. This paper addresses the Legal Entity Name Recognition (L-NER) and Court judgment Prediction (CPJ) and Explanation (CJPE) tasks. The L-NER solution explores the use of various transformer-based models, including an entity-aware method attending domain-specific entities. The CJPE proposed method relies on hierarchical BERT-based classifiers combined with local input attribution explainers. We propose a broad comparison of eXplainable AI methodologies along with a novel approach based on NER. For the L-NER task, the experimental results remark on the importance of domain-specific pre-training. For CJP our lightweight solution shows performance in line with existing approaches, and our NER-boosted explanations show promising CJPE results in terms of the conciseness of the prediction explanations.

PoliToHFI at SemEval-2023 Task 6: Leveraging Entity-Aware and Hierarchical Transformers for Legal Entity Recognition and Court Judgment Prediction

In this paper, we propose a methodology for task 10 of SemEval23, focusing on detecting and classifying online sexism in social media posts. The task is tackling a serious issue, as detecting harmful content on social media platforms is crucial for mitigating the harm of these posts on users. Our solution for this task is based on an ensemble of finetuned transformer-based models (BERTweet, RoBERTa, and DeBERTa). To alleviate problems related to class imbalance, and to improve the generalization capability of our model, we also experiment with data augmentation and semi-supervised learning. In particular, for data augmentation, we use back-translation, either on all classes, or on the underrepresented classes only. We analyze the impact of these strategies on the overall performance of the
pipeline through extensive experiments. while for semi-supervised learning, we found that with a substantial amount of unlabelled, indomain data available, semi-supervised learning can enhance the performance of certain models. Our proposed method (for which the source code is available on Github ) an F1-score of 0.8613 for sub-taskA, which ranked us 10th in the competition.

NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset

Persuasion techniques detection in news in a multi-lingual setup is non-trivial and comes with challenges, including little training data. 
Our system successfully leverages (back-)translation as data augmentation strategies with multi-lingual transformer models for the task of detecting persuasion techniques. The automatic and human evaluation of our augmented data allows us to explore whether (back-)translation aid or hinder performance.
Our in-depth analyses indicate that both data augmentation strategies boost performance; however, balancing human-produced and machine-generated data seems to be crucial.

Downloads

Next from ACL 2023

Augustine of Hippo at SemEval-2023 Task 4: An Explainable Knowledge Extraction Method to Identify Human Values in Arguments with SuperASKE

Similar lecture

OPI at SemEval 2023 Task 9: A Simple but Effective Approach to Multilingual Tweet Intimacy Analysis