اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدBenchmarking Multi-Task Learning for Sentiment Analysis and Offensive Language Identification in Under-Resourced Dravidian Languages
124
0
0.0
(
0
)
نشر من قبل
Bharathi Raja Chakravarthi
تاريخ النشر
2021
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
To obtain extensive annotated data for under-resourced languages is challenging, so in this research, we have investigated whether it is beneficial to train models using multi-task learning. Sentiment analysis and offensive language identification share similar discourse properties. The selection of these tasks is motivated by the lack of large labelled data for user-generated code-mixed datasets. This paper works on code-mixed YouTube comments for Tamil, Malayalam, and Kannada languages. Our framework is applicable to other sequence classification problems irrespective of the size of the datasets. Experiments show that our multi-task learning model can achieve high results compared with single-task learning while reducing the time and space constraints required to train the models on individual tasks. Analysis of fine-tuned models indicates the preference of multi-task learning over single-task learning resulting in a higher weighted F1-score on all three languages. We apply two multi-task learning approaches to three Dravidian languages: Kannada, Malayalam, and Tamil. Maximum scores on Kannada and Malayalam were achieved by mBERT subjected to cross-entropy loss and with an approach of hard parameter sharing. Best scores on Tamil was achieved by DistilBERT subjected to cross-entropy loss with soft parameter sharing as the architecture type. For the tasks of sentiment analysis and offensive language identification, the best-performing model scored a weighted F1-score of (66.8% and 90.5%), (59% and 70%), and (62.1% and 75.3%) for Kannada, Malayalam, and Tamil on sentiment analysis and offensive language identification, respectively. The data and approaches discussed in this paper are published in Githubfootnote{href{https://github.com/SiddhanthHegde/Dravidian-MTL-Benchmarking}{Dravidian-MTL-Benchmarking}}.
قيم البحث
اقرأ أيضاً
This paper describes the development of a multilingual, manually annotated dataset for three under-resourced Dravidian languages generated from social media comments. The dataset was annotated for sentiment analysis and offensive language identificat
ion for a total of more than 60,000 YouTube comments. The dataset consists of around 44,000 comments in Tamil-English, around 7,000 comments in Kannada-English, and around 20,000 comments in Malayalam-English. The data was manually annotated by volunteer annotators and has a high inter-annotator agreement in Krippendorffs alpha. The dataset contains all types of code-mixing phenomena since it comprises user-generated content from a multilingual country. We also present baseline experiments to establish benchmarks on the dataset using machine learning methods. The dataset is available on Github (https://github.com/bharathichezhiyan/DravidianCodeMix-Dataset) and Zenodo (https://zenodo.org/record/4750858#.YJtw0SYo_0M).
Social media has effectively become the prime hub of communication and digital marketing. As these platforms enable the free manifestation of thoughts and facts in text, images and video, there is an extensive need to screen them to protect individua
ls and groups from offensive content targeted at them. Our work intends to classify codemixed social media comments/posts in the Dravidian languages of Tamil, Kannada, and Malayalam. We intend to improve offensive language identification by generating pseudo-labels on the dataset. A custom dataset is constructed by transliterating all the code-mixed texts into the respective Dravidian language, either Kannada, Malayalam, or Tamil and then generating pseudo-labels for the transliterated dataset. The two datasets are combined using the generated pseudo-labels to create a custom dataset called CMTRA. As Dravidian languages are under-resourced, our approach increases the amount of training data for the language models. We fine-tune several recent pretrained language models on the newly constructed dataset. We extract the pretrained language embeddings and pass them onto recurrent neural networks. We observe that fine-tuning ULMFiT on the custom dataset yields the best results on the code-mixed test sets of all three languages. Our approach yields the best results among the benchmarked models on Tamil-English, achieving a weighted F1-Score of 0.7934 while scoring competitive weighted F1-Scores of 0.9624 and 0.7306 on the code-mixed test sets of Malayalam-English and Kannada-English, respectively.
Nowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task. In this paper, we build an offensive language detection system, which combines multi-task learning with BER
T-based models. Using a pre-trained language model such as BERT, we can effectively learn the representations for noisy text in social media. Besides, to boost the performance of offensive language detection, we leverage the supervision signals from other related tasks. In the OffensEval-2020 competition, our model achieves 91.51% F1 score in English Sub-task A, which is comparable to the first place (92.23%F1). An empirical analysis is provided to explain the effectiveness of our approaches.
Hate Speech has become a major content moderation issue for online social media platforms. Given the volume and velocity of online content production, it is impossible to manually moderate hate speech related content on any platform. In this paper we
utilize a multi-task and multi-lingual approach based on recently proposed Transformer Neural Networks to solve three sub-tasks for hate speech. These sub-tasks were part of the 2019 shared task on hate speech and offensive content (HASOC) identification in Indo-European languages. We expand on our submission to that competition by utilizing multi-task models which are trained using three approaches, a) multi-task learning with separate task heads, b) back-translation, and c) multi-lingual training. Finally, we investigate the performance of various models and identify instances where the Transformer based models perform differently and better. We show that it is possible to to utilize different combined approaches to obtain models that can generalize easily on different languages and tasks, while trading off slight accuracy (in some cases) for a much reduced inference time compute cost. We open source an updated version of our HASOC 2019 code with the new improvements at https://github.com/socialmediaie/MTML_HateSpeech.
Sentiment analysis is directly affected by compositional phenomena in language that act on the prior polarity of the words and phrases found in the text. Negation is the most prevalent of these phenomena and in order to correctly predict sentiment, a
classifier must be able to identify negation and disentangle the effect that its scope has on the final polarity of a text. This paper proposes a multi-task approach to explicitly incorporate information about negation in sentiment analysis, which we show outperforms learning negation implicitly in a data-driven manner. We describe our approach, a cascading neural architecture with selective sharing of LSTM layers, and show that explicitly training the model with negation as an auxiliary task helps improve the main task of sentiment analysis. The effect is demonstrated across several different standard English-language data sets for both tasks and we analyze several aspects of our system related to its performance, varying types and amounts of input data and different multi-task setups.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
