Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised Learning
كيت: نموذج مقاوم للتناقض مسبقا للكشف عن الاستعارة مع التعلم شبه الإشرافه
385
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الاستعارات في كل مكان في اللغة الطبيعية، ويتطلب الكشف عنها منطق سياقي حول ما إذا كان التعارض الدلالي موجود بالفعل.معظم العمل الحالي يعالج هذه المشكلة باستخدام نماذج السياق المدربة مسبقا.على الرغم من نجاحها، تتطلب هذه النماذج كمية كبيرة من البيانات المسمى ولا تستند إلى اللغة اللاحنة.في هذه الورقة، اقترحنا نموذجا متمربا مسبقا مسبقا (كيت) للكشف عن الاستعارة مع التعلم شبه الإشرافه.يستخدم نموذجنا أولا نموذجا مدربا مسبقا للحصول على تمثيل سياقي للكلمات المستهدفة وتوظف هدفا بسيطا لتعزيز المسافة المتزايدة بين الكلمات المستهدفة "الحواس الحرفية والجهزة المجازية القائمة على نظريات لغوية.علاوة على ذلك، نقترح استراتيجية بسيطة لجمع مثيلات مرشحة واسعة النطاق من كوربوس العام وتعميم النموذج عبر التدريب الذاتي.تبين تجارب واسعة أن كيت يحقق أداء أفضل ضد خطوط خطوط البيانات الحديثة على العديد من البيانات القياسية.
Metaphors are ubiquitous in natural language, and detecting them requires contextual reasoning about whether a semantic incongruence actually exists. Most existing work addresses this problem using pre-trained contextualized models. Despite their success, these models require a large amount of labeled data and are not linguistically-based. In this paper, we proposed a ContrAstive pre-Trained modEl (CATE) for metaphor detection with semi-supervised learning. Our model first uses a pre-trained model to obtain a contextual representation of target words and employs a contrastive objective to promote an increased distance between target words' literal and metaphorical senses based on linguistic theories. Furthermore, we propose a simple strategy to collect large-scale candidate instances from the general corpus and generalize the model via self-training. Extensive experiments show that CATE achieves better performance against state-of-the-art baselines on several benchmark datasets.
References used
https://aclanthology.org/
rate research
Read More
In this work, we present our approach and findings for SemEval-2021 Task 5 - Toxic Spans Detection. The task's main aim was to identify spans to which a given text's toxicity could be attributed. The task is challenging mainly due to two constraints:
the small training dataset and imbalanced class distribution. Our paper investigates two techniques, semi-supervised learning and learning with Self-Adjusting Dice Loss, for tackling these challenges. Our submitted system (ranked ninth on the leader board) consisted of an ensemble of various pre-trained Transformer Language Models trained using either of the above-proposed techniques.
Meta learning aims to optimize the model's capability to generalize to new tasks and domains. Lacking a data-efficient way to create meta training tasks has prevented the application of meta-learning to the real-world few shot learning scenarios. Rec
ent studies have proposed unsupervised approaches to create meta-training tasks from unlabeled data for free, e.g., the SMLMT method (Bansal et al., 2020a) constructs unsupervised multi-class classification tasks from the unlabeled text by randomly masking words in the sentence and let the meta learner choose which word to fill in the blank. This study proposes a semi-supervised meta-learning approach that incorporates both the representation power of large pre-trained language models and the generalization capability of prototypical networks enhanced by SMLMT. The semi-supervised meta training approach avoids overfitting prototypical networks on a small number of labeled training examples and quickly learns cross-domain task-specific representation only from a few supporting examples. By incorporating SMLMT with prototypical networks, the meta learner generalizes better to unseen domains and gains higher accuracy on out-of-scope examples without the heavy lifting of pre-training. We observe significant improvement in few-shot generalization after training only a few epochs on the intent classification tasks evaluated in a multi-domain setting.
Fine-tuned pre-trained language models (LMs) have achieved enormous success in many natural language processing (NLP) tasks, but they still require excessive labeled data in the fine-tuning stage. We study the problem of fine-tuning pre-trained LMs u
sing only weak supervision, without any labeled data. This problem is challenging because the high capacity of LMs makes them prone to overfitting the noisy labels generated by weak supervision. To address this problem, we develop a contrastive self-training framework, COSINE, to enable fine-tuning LMs with weak supervision. Underpinned by contrastive regularization and confidence-based reweighting, our framework gradually improves model fitting while effectively suppressing error propagation. Experiments on sequence, token, and sentence pair classification tasks show that our model outperforms the strongest baseline by large margins and achieves competitive performance with fully-supervised fine-tuning methods. Our implementation is available on https://github.com/yueyu1030/COSINE.
Toxic comments contain forms of non-acceptable language targeted towards groups or individuals. These types of comments become a serious concern for government organizations, online communities, and social media platforms. Although there are some app
roaches to handle non-acceptable language, most of them focus on supervised learning and the English language. In this paper, we deal with toxic comment detection as a semi-supervised strategy over a heterogeneous graph. We evaluate the approach on a toxic dataset of the Portuguese language, outperforming several graph-based methods and achieving competitive results compared to transformer architectures.
Hope is an essential aspect of mental health stability and recovery in every individual in this fast-changing world. Any tools and methods developed for detection, analysis, and generation of hope speech will be beneficial. In this paper, we propose
a model on hope-speech detection to automatically detect web content that may play a positive role in diffusing hostility on social media. We perform the experiments by taking advantage of pre-processing and transfer-learning models. We observed that the pre-trained multilingual-BERT model with convolution neural networks gave the best results. Our model ranked first, third, and fourth ranks on English, Malayalam-English, and Tamil-English code-mixed datasets.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
