Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSeed Word Selection for Weakly-Supervised Text Classification with Unsupervised Error Estimation
اختيار كلمة البذور لتصنيف النص الإشراف ضعيف مع تقدير الأخطاء غير المركبات
314
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يهدف تصنيف النص الخاضع للإشراف ضعيف إلى حثص نصوص النص من عدد قليل من كلمات البذور التي توفرها المستخدم. غالبية العمل العظمى من العمل السابق يفترض أن كلمات البذور عالية الجودة تعطى. ومع ذلك، فإن كلمات البذور المشروح للخبراء في بعض الأحيان غير تافهة للتوصل إلى ذلك. علاوة على ذلك، في إعداد التعلم الإشراف ضعيف، ليس لدينا أي وثيقة مسمى لقياس فعالية كلمات البذور، مما يجعل عملية اختيار كلمة البذور المشي في الظلام ". في هذا العمل، نقوم بإزالة الحاجة إلى كلمات البذور التي يديرها الخبراء من قبل كلمات البذور المرشحة الأولى (صاخبة) المرتبطة بأسماء الفئات. ثم تدريب نماذج مؤقتة بكلمات البذور المرشحة الفردية. أخيرا، نقدر معدل خطأ النماذج المؤقتة بطريقة غير منشأة. تتم إضافة كلمات البذور التي تسفر عن أدنى معدلات الخطأ المقدرة إلى مجموعة كلمات البذور النهائية. يوضح تقييم شامل لستة مهام التصنيف الثنائية على أربع مجموعات بيانات شائعة أن الطريقة المقترحة تتفوق على خط أساس باستخدام كلمات البذور اسم الفئة فقط والحصول على أداء مماثل كظرف باستخدام كلمات البذور المشروح من الخبراء.
Weakly-supervised text classification aims to induce text classifiers from only a few user-provided seed words. The vast majority of previous work assumes high-quality seed words are given. However, the expert-annotated seed words are sometimes non-trivial to come up with. Furthermore, in the weakly-supervised learning setting, we do not have any labeled document to measure the seed words' efficacy, making the seed word selection process a walk in the dark''. In this work, we remove the need for expert-curated seed words by first mining (noisy) candidate seed words associated with the category names. We then train interim models with individual candidate seed words. Lastly, we estimate the interim models' error rate in an unsupervised manner. The seed words that yield the lowest estimated error rates are added to the final seed word set. A comprehensive evaluation of six binary classification tasks on four popular datasets demonstrates that the proposed method outperforms a baseline using only category name seed words and obtained comparable performance as a counterpart using expert-annotated seed words.
References used
https://aclanthology.org/
rate research
Read More
An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current approaches i
mproved the response quality, but they over-look the training signals present in the dialogue data. We can leverage these signals to generate the weakly supervised training data for learning dialog policy and reward estimator, and make the policy take actions (generates responses) which can foresee the future direction for a successful (rewarding) conversation. We simulate the dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses. Each simulated state-action pair is evaluated (works as a weak annotation) with three quality modules: Semantic Relevant, Semantic Coherence and Consistent Flow. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation on both automatic evaluation and human judgment.
Automatic summarization aims to extract important information from large amounts of textual data in order to create a shorter version of the original texts while preserving its information. Training traditional extractive summarization models relies
heavily on human-engineered labels such as sentence-level annotations of summary-worthiness. However, in many use cases, such human-engineered labels do not exist and manually annotating thousands of documents for the purpose of training models may not be feasible. On the other hand, indirect signals for summarization are often available, such as agent actions for customer service dialogues, headlines for news articles, diagnosis for Electronic Health Records, etc. In this paper, we develop a general framework that generates extractive summarization as a byproduct of supervised learning tasks for indirect signals via the help of attention mechanism. We test our models on customer service dialogues and experimental results demonstrated that our models can reliably select informative sentences and words for automatic summarization.
Paraphrase generation is a longstanding NLP task that has diverse applications on downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised endeavors have be
en proposed to alleviate this issue, they may fail to generate meaningful paraphrases due to the lack of supervision signals. In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with data of weak supervision. Specifically, we tackle the weakly-supervised paraphrase generation problem by: (1) obtaining abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion; and (2) developing a meta-learning framework to progressively select valuable samples for fine-tuning a pre-trained language model BART on the sentential paraphrasing task. We demonstrate that our approach achieves significant improvements over existing unsupervised approaches, and is even comparable in performance with supervised state-of-the-arts.
In cross-lingual text classification, it is required that task-specific training data in high-resource source languages are available, where the task is identical to that of a low-resource target language. However, collecting such training data can b
e infeasible because of the labeling cost, task characteristics, and privacy concerns. This paper proposes an alternative solution that uses only task-independent word embeddings of high-resource languages and bilingual dictionaries. First, we construct a dictionary-based heterogeneous graph (DHG) from bilingual dictionaries. This opens the possibility to use graph neural networks for cross-lingual transfer. The remaining challenge is the heterogeneity of DHG because multiple languages are considered. To address this challenge, we propose dictionary-based heterogeneous graph neural network (DHGNet) that effectively handles the heterogeneity of DHG by two-step aggregations, which are word-level and language-level aggregations. Experimental results demonstrate that our method outperforms pretrained models even though it does not access to large corpora. Furthermore, it can perform well even though dictionaries contain many incorrect translations. Its robustness allows the usage of a wider range of dictionaries such as an automatically constructed dictionary and crowdsourced dictionary, which are convenient for real-world applications.
Weakly-supervised text classification has received much attention in recent years for it can alleviate the heavy burden of annotating massive data. Among them, keyword-driven methods are the mainstream where user-provided keywords are exploited to ge
nerate pseudo-labels for unlabeled texts. However, existing methods treat keywords independently, thus ignore the correlation among them, which should be useful if properly exploited. In this paper, we propose a novel framework called ClassKG to explore keyword-keyword correlation on keyword graph by GNN. Our framework is an iterative process. In each iteration, we first construct a keyword graph, so the task of assigning pseudo labels is transformed to annotating keyword subgraphs. To improve the annotation quality, we introduce a self-supervised task to pretrain a subgraph annotator, and then finetune it. With the pseudo labels generated by the subgraph annotator, we then train a text classifier to classify the unlabeled texts. Finally, we re-extract keywords from the classified texts. Extensive experiments on both long-text and short-text datasets show that our method substantially outperforms the existing ones.
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
