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.

This paper describes our system used in the SemEval-2023 Task 10: Towards ExplainableDetection of Online Sexism (Kirk et al., 2023). The harmful effects of sexism on the internet have impacted both men and women, yet current research lacks a fine-grained classification of sexist content. The task involves three hierarchical sub-tasks, which we addressed by employing a multitask-learning framework. To further enhance our system’s performance, we pre-trained the roberta-large (Liu et al., 2019b) and deberta-v3-large (He et al., 2021) models on two million unlabeled data, resulting in significant improvements on sub-tasks A and C. In addition, the multitask-learning approach boosted the performance of our models on subtasks A and B. Our system exhibits promising results in achieving explainable detection of online sexism, attaining a test f1-score of 0.8746 on sub-task A (ranking 1st on the leaderboard), and ranking 5th on sub-tasks B and C.

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.

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.