Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCoarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data
COARSE2FINE: تصنيف النص الرباعي بشكل جيد على البيانات المشروحة المشجعية
566
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تركز أساليب تصنيف النص الحالية أساسا على مجموعة تسمية ثابتة، في حين أن العديد من التطبيقات في العالم الحقيقي تتطلب تمديد فئات جديدة من الرباعي حيث يزيد عدد العينات لكل علامة. لاستيعاب هذه المتطلبات، نقدم مشكلة جديدة تسمى تصنيف الحبيبات الخشنة إلى الدقيقة، والتي تهدف إلى أداء تصنيف جيد الحبيبات على البيانات المشروحة بشكل خشن. بدلا من طلب التعليقات التوضيحية البشرية المحبوبة الجديدة، فإننا نقوم باختيار الاستفادة من أسماء السطح التسمية باعتبارها الإرشادات البشرية الوحيدة والنسج في نماذج لغوية غنية مدربة مسبقا في استراتيجية الإشراف الضعيفة المتكررة. على وجه التحديد، نقترح أولا صياغة صياغة دقيقة مشروطة على التسمية لتحريك هذه المولدات لمهمتنا. علاوة على ذلك، نركض هدف تنظيمي بناء على قيود العلامات الجميلة الخشنة المستمدة من إعداد مشكلتنا، مما يتيح لنا المزيد من التحسينات على الصيغة السابقة. يستخدم إطار عملنا النماذج الإدارية التي تم ضبطها بشكل جيد لعينة بيانات التدريب الزائفة لتدريب المصنف، و BootStraps على البيانات الحقيقية غير المسبقة لتحسين النموذج. تجارب واسعة دراسات حالة عن مجموعات بيانات عالمية في العالم الحقيقي تثبت أداء فائقا فوق خطوط خطوط تصنيف Sota-Shot-Shot.
Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases. To accommodate such requirements, we introduce a new problem called coarse-to-fine grained classification, which aims to perform fine-grained classification on coarsely annotated data. Instead of asking for new fine-grained human annotations, we opt to leverage label surface names as the only human guidance and weave in rich pre-trained generative language models into the iterative weak supervision strategy. Specifically, we first propose a label-conditioned fine-tuning formulation to attune these generators for our task. Furthermore, we devise a regularization objective based on the coarse-fine label constraints derived from our problem setting, giving us even further improvements over the prior formulation. Our framework uses the fine-tuned generative models to sample pseudo-training data for training the classifier, and bootstraps on real unlabeled data for model refinement. Extensive experiments and case studies on two real-world datasets demonstrate superior performance over SOTA zero-shot classification baselines.
References used
https://aclanthology.org/
rate research
Read More
BERTScore, a recently proposed automatic metric for machine translation quality, uses BERT, a large pre-trained language model to evaluate candidate translations with respect to a gold translation. Taking advantage of BERT's semantic and syntactic ab
ilities, BERTScore seeks to avoid the flaws of earlier approaches like BLEU, instead scoring candidate translations based on their semantic similarity to the gold sentence. However, BERT is not infallible; while its performance on NLP tasks set a new state of the art in general, studies of specific syntactic and semantic phenomena have shown where BERT's performance deviates from that of humans more generally. This naturally raises the questions we address in this paper: what are the strengths and weaknesses of BERTScore? Do they relate to known weaknesses on the part of BERT? We find that while BERTScore can detect when a candidate differs from a reference in important content words, it is less sensitive to smaller errors, especially if the candidate is lexically or stylistically similar to the reference.
Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to improving perf
ormance on fine-grained tasks. In this work, we analyse the contrastive fine-tuning of pre-trained language models on two fine-grained text classification tasks, emotion classification and sentiment analysis. We adaptively embed class relationships into a contrastive objective function to help differently weigh the positives and negatives, and in particular, weighting closely confusable negatives more than less similar negative examples. We find that Label-aware Contrastive Loss outperforms previous contrastive methods, in the presence of larger number and/or more confusable classes, and helps models to produce output distributions that are more differentiated.
NLP models are vulnerable to data poisoning attacks. One type of attack can plant a backdoor in a model by injecting poisoned examples in training, causing the victim model to misclassify test instances which include a specific pattern. Although defe
nces exist to counter these attacks, they are specific to an attack type or pattern. In this paper, we propose a generic defence mechanism by making the training process robust to poisoning attacks through gradient shaping methods, based on differentially private training. We show that our method is highly effective in mitigating, or even eliminating, poisoning attacks on text classification, with only a small cost in predictive accuracy.
Text style transfer aims to controllably generate text with targeted stylistic changes while maintaining core meaning from the source sentence constant. Many of the existing style transfer benchmarks primarily focus on individual high-level semantic
changes (e.g. positive to negative), which enable controllability at a high level but do not offer fine-grained control involving sentence structure, emphasis, and content of the sentence. In this paper, we introduce a large-scale benchmark, StylePTB, with (1) paired sentences undergoing 21 fine-grained stylistic changes spanning atomic lexical, syntactic, semantic, and thematic transfers of text, as well as (2) compositions of multiple transfers which allow modeling of fine-grained stylistic changes as building blocks for more complex, high-level transfers. By benchmarking existing methods on StylePTB, we find that they struggle to model fine-grained changes and have an even more difficult time composing multiple styles. As a result, StylePTB brings novel challenges that we hope will encourage future research in controllable text style transfer, compositional models, and learning disentangled representations. Solving these challenges would present important steps towards controllable text generation.
This paper proposes AEDA (An Easier Data Augmentation) technique to help improve the performance on text classification tasks. AEDA includes only random insertion of punctuation marks into the original text. This is an easier technique to implement f
or data augmentation than EDA method (Wei and Zou, 2019) with which we compare our results. In addition, it keeps the order of the words while changing their positions in the sentence leading to a better generalized performance. Furthermore, the deletion operation in EDA can cause loss of information which, in turn, misleads the network, whereas AEDA preserves all the input information. Following the baseline, we perform experiments on five different datasets for text classification. We show that using the AEDA-augmented data for training, the models show superior performance compared to using the EDA-augmented data in all five datasets. The source code will be made available for further study and reproduction of the results.
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
