تصف هذه الورقة نظامنا المشارك في المهمة 7 من Semeval-2021: الكشف عن الفكاهة والجريمة.تم تصميم المهمة للكشف عن الفكاهة والجريمة التي تتأثر بالعوامل الذاتية.من أجل الحصول على معلومات دلالية من كمية كبيرة من البيانات غير المسبقة، طبقنا نماذج اللغة المدربة مسبقا غير مدبونة.من خلال إجراء البحوث والتجارب، وجدنا أن نماذج Ernie 2.0 و Deberta مدربة مسبقا حققت أداء مثير للإعجاب في مختلف المهام الفرعية.لذلك، طبقنا النماذج المدربة مسبقا أعلاه لضبط الشبكة العصبية المصب.في عملية ضبط النموذج بشكل جيد، اعتمكن من استراتيجية التدريب المتعدد المهام وطريقة تعلم الفرقة.استنادا إلى الاستراتيجية والطريقة المذكورة أعلاه، حققنا RMSE 0.4959 ل SubTask 1B، وفاز أخيرا في المقام الأول.
This paper describes our system participated in Task 7 of SemEval-2021: Detecting and Rating Humor and Offense. The task is designed to detect and score humor and offense which are influenced by subjective factors. In order to obtain semantic information from a large amount of unlabeled data, we applied unsupervised pre-trained language models. By conducting research and experiments, we found that the ERNIE 2.0 and DeBERTa pre-trained models achieved impressive performance in various subtasks. Therefore, we applied the above pre-trained models to fine-tune the downstream neural network. In the process of fine-tuning the model, we adopted multi-task training strategy and ensemble learning method. Based on the above strategy and method, we achieved RMSE of 0.4959 for subtask 1b, and finally won the first place.
References used
https://aclanthology.org/
Humor detection has become a topic of interest for several research teams, especially those involved in socio-psychological studies, with the aim to detect the humor and the temper of a targeted population (e.g. a community, a city, a country, the em
This paper describes our contribution to SemEval-2021 Task 7: Detecting and Rating Humor and Of-fense.This task contains two sub-tasks, sub-task 1and sub-task 2. Among them, sub-task 1 containsthree sub-tasks, sub-task 1a ,sub-task 1b and sub-task 1c
In this paper we describe the systems used by the RoMa team in the shared task on Detecting and Rating Humor and Offense (HaHackathon) at SemEval 2021. Our systems rely on data representations learned through fine-tuned neural language models. Partic
SemEval 2021 Task 7, HaHackathon, was the first shared task to combine the previously separate domains of humor detection and offense detection. We collected 10,000 texts from Twitter and the Kaggle Short Jokes dataset, and had each annotated for hum
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 pap