This paper describes our system used in the SemEval-2023 Task12: Sentiment Analysis for Low-resource African Languages using Twit- ter Dataset (Muhammad et al., 2023c). The AfriSenti-SemEval Shared Task 12 is based on a collection of Twitter datasets in 14 African languages for sentiment classification. It con- sists of three sub-tasks. Task A is a monolin- gual sentiment classification which covered 12 African languages. Task B is a multilingual sen- timent classification which combined training data from Task A (12 African languages). Task C is a zero-shot sentiment classification. We uti- lized various strategies, including monolingual training, multilingual mixed training, and trans- lation technology, and proposed a weighted vot- ing method that combined the results of differ- ent strategies. Substantially, in the monolingual subtask, our system achieved Top-1 in two lan- guages (Yoruba and Twi) and Top-2 in four languages (Nigerian Pidgin, Algerian Arabic, and Swahili, Multilingual). In the multilingual subtask, Our system achived Top-2 in publish leaderBoard.

Patronizing and condescending language (PCL) has a large harmful impact and is difficult to detect, both for human judges and existing NLP systems. At SemEval-2022 Task 4, we propose a novel Transformer-based model and its ensembles to accurately understand such language context for PCL detection. To facilitate comprehension of the subtle and subjective nature of PCL, two fine-tuning strategies are applied to capture discriminative features from diverse linguistic behaviour and categorical distribution. The system achieves remarkable results on the official ranking, including 1st in Subtask 1 and 5th in Subtask 2. Extensive experiments on the task demonstrate the effectiveness of our system and its strategies.

This paper describes our system used in the SemEval-2022 Task 5: Multimedia Automatic Misogyny Identification (MAMI). Multimedia automatic misogyny recognition consists of the identification of misogynous memes, taking advantage of both text and images as sources of information. The task will be organized around two main subtasks: Task A is a binary classification task, which should be identified either as misogynous or not misogynous. Task B is a multi-label classification task, in which the types of misogyny should be identified in potential overlapping categories, such as stereotype, shaming, objectification, and violence. In this paper, we proposed a system based on multi-task learning for multi-modal misogynous detection in memes. Our system combined image features with text features to train a multi-label classification. The prediction results were obtained by the simple weighted average method of the results with different fusion models, and the results of Task A were corrected by Task B. Our system achieves a test accuracy of 0.755 on Task A (ranking 3rd on the final leaderboard) and the accuracy of 0.731 on Task B (ranking 1st on the final leaderboard).

This paper describes the method we utilized in the SemEval-2022 Task 6 iSarcasmEval: Intended Sarcasm Detection In English and Arabic. Our system has achieved 1st in SubtaskB, which is to identify the categories of intended sarcasm. The proposed system integrates multiple BERT-based, RoBERTa-based and BERTweet-based models with finetuning. In this task, we contributed the following: 1) we reveal several large pre-trained models’ performance on tasks coping with the tweet-like text. 2) Our methods prove that we can still achieve excellent results in this particular task without a complex classifier adopting some proper training method. 3) we found there is a hierarchical relationship of sarcasm types in this task.

This paper describes the systematic approach applied in “SemEval-2022 Task 6 (iSarcasmEval) : Intended Sarcasm Detection in English and Arabic”. In particular, we illustrate the proposed system in detail for SubTask-A about determining a given text as sarcastic or non-sarcastic in English. We start with the training data from the officially released data and then experiment with different combinations of public datasets to improve the model generalization. Additional experiments conducted on the task demonstrate our strategies are effective in completing the task. Different transformer-based language models, as well as some popular plug-and-play proirs, are mixed into our system to enhance the model’s robustness. Furthermore, statistical and lexical-based text features are mined to improve the accuracy of the sarcasm detection. Our final submission achieves an F1-score for the sarcastic class of 0.6052 on the official test set (the top 1 of the 43 teams in “SubTask-A-English” on the leaderboard).

This paper describes our system used in the SemEval-2022 Task 7(Roth et al.): Identifying Plausible Clarifications of Implicit and Under-specified Phrases. Semeval Task7 is an more complex cloze task, different than normal cloze task, only requiring NLP system could find the best fillers for sentence. In Semeval Task7, NLP system not only need to choose the best fillers for each input instance, but also evaluate the quality of all possible fillers and give them a relative score according to context semantic information. We propose an ensemble of different state-of-the-art transformer-based language models(i.e., RoBERTa and Deberta) with some plug-and-play tricks, such as Grouped Layerwise Learning Rate Decay (GLLRD) strategy, contrastive learning loss, different pooling head and an external input data preprecess block before the information came into pretrained language models, which improve performance significantly. The main contributions of our sys-tem are 1) revealing the performance discrepancy of different transformer-based pretraining models on the downstream task; 2) presenting an efficient learning-rate and parameter attenuation strategy when fintuning pretrained language models; 3) adding different constrative learning loss to improve model performance; 4) showing the useful of the different pooling head structure. Our system achieves a test accuracy of 0.654 on subtask1(ranking 4th on the leaderboard) and a test Spearman’s rank correlation coefficient of 0.785 on subtask2(ranking 2nd on the leaderboard).

This paper describes our system used in the SemEval-2022 Task 09: R2VQ - Competence-based Multimodal Question Answering. We propose a knowledge-enhanced model for predicting answer in QA task, this model use BERT as the backbone. We adopted two knowledge-enhanced methods in this model: the knowledge auxiliary text method and the knowledge embedding method. We also design an answer extraction task pipeline, which contains an extraction-based model, an automatic keyword labeling module, and an answer generation module. Our system ranked 3rd in task 9 and achieved an exact match score of 78.21 and a word-level F1 score of 82.62.

Pre-trained language models have been widely applied to standard benchmarks. Due to the flexibility of natural language, the available resources in a certain domain can be restricted to support obtaining precise representation. To address this issue, we propose a novel Transformer-based language model named VarMAE for domain-adaptive language understanding. Under the masked autoencoding objective, we design a context uncertainty learning module to encode the token’s context into a smooth latent distribution. The module can produce diverse and well-formed contextual representations. Experiments on science- and finance-domain NLU tasks demonstrate that VarMAE can be efficiently adapted to new domains with limited resources.

In this paper we propose a contextual attention based model with two-stage fine-tune training using RoBERTa. First, we perform the first-stage fine-tune on corpus with RoBERTa, so that the model can learn some prior domain knowledge. Then we get the contextual embedding of context words based on the token-level embedding with the fine-tuned model. And we use Kfold cross-validation to get K models and ensemble them to get the final result. Finally, we attain the 2nd place in the final evaluation phase of sub-task 2 with pearson correlation of 0.8575.

This paper presents the PALI team’s winning system for SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation. We fine-tune XLM-RoBERTa model to solve the task of word in context disambiguation, i.e., to determine whether the target word in the two contexts contains the same meaning or not. In implementation, we first specifically design an input tag to emphasize the target word in the contexts. Second, we construct a new vector on the fine-tuned embeddings from XLM-RoBERTa and feed it to a fully-connected network to output the probability of whether the target word in the context has the same meaning or not. The new vector is attained by concatenating the embedding of the [CLS] token and the embeddings of the target word in the contexts. In training, we explore several tricks, such as the Ranger optimizer, data augmentation, and adversarial training, to improve the model prediction. Consequently, we attain the first place in all four cross-lingual tasks.

This paper describes MagicPai’s system for SemEval 2021 Task 7, HaHackathon: Detecting and Rating Humor and Offense. This task aims to detect whether the text is humorous and how humorous it is. There are four subtasks in the competition. In this paper, we mainly present our solution, a multi-task learning model based on adversarial examples, for task 1a and 1b. More specifically, we first vectorize the cleaned dataset and add the perturbation to obtain more robust embedding representations. We then correct the loss via the confidence level. Finally, we perform interactive joint learning on multiple tasks to capture the relationship between whether the text is humorous and how humorous it is. The final result shows the effectiveness of our system.

Question answering from semi-structured tables can be seen as a semantic parsing task and is significant and practical for pushing the boundary of natural language understanding. Existing research mainly focuses on understanding contents from unstructured evidence, e.g., news, natural language sentences and documents. The task of verification from structured evidence, such as tables, charts, and databases, is still less-explored. This paper describes sattiy team’s system in SemEval-2021 task 9: Statement Verification and Evidence Finding with Tables (SEM-TAB-FACT)(CITATION). This competition aims to verify statements and to find evidence from tables for scientific articles and to promote proper interpretation of the surrounding article. In this paper we exploited ensemble models of pre-trained language models over tables, TaPas and TaBERT, for Task A and adjust the result based on some rules extracted for Task B. Finally, in the leadboard, we attain the F1 scores of 0.8496 and 0.7732 in Task A for the 2-way and 3-way evaluation, respectively, and the F1 score of 0.4856 in Task B.

This paper describes the model we apply in the SemEval-2020 Task 10. We formalize the task of emphasis selection as a simplified query-based machine reading comprehension (MRC) task, i.e. answering a fixed question of “Find candidates for emphasis”. We propose our subword puzzle encoding mechanism and subword fusion layer to align and fuse subwords. By introducing the semantic prior knowledge of the informative query and some other techniques, we attain the 7th place during the evaluation phase and the first place during train phase.