Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMeta-Learning for Domain Generalization in Semantic Parsing
التعلم التعريف لتعميم المجال في التحليل الدلالي
278
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
لقد تم الاعتراف بأهمية بناء المحللين الدلاليين الذين يمكن تطبيقهم على مجالات جديدة وإنشاء برامج غير مرئية في التدريب لفترة طويلة، وقد تم الاعتراف لفترة طويلة، وتصبح مجموعات البيانات اختبار الأداء خارج النطاق متاحة بشكل متزايد. ومع ذلك، فقد تم تخصيص اهتمام ضئيل أو معدوني لتعلم الخوارزميات أو الأهداف التي تعزز تعميم المجال، حيث تعتمد جميع الأساليب الموجودة تقريبا على التعلم المعياري الإشرافي. في هذا العمل، نستخدم إطارا للتعلم من التعريف الذي يستهدف تعميم المجال الصفرية للتحليل الدلالي. نحن نطبق خوارزمية التدريب النموذجية المرجعية التي تحاكي تحليل اللقطة الصفرية من خلال بناء القطار الافتراضي ومجموعات الاختبار من مجالات Disfoint. يستحق الهدف التعلم عن الحدس الذي يجب عليه اتخاذ خطوات التدرج التي تعمل على تحسين أداء مجال المصدر أيضا على تحسين أداء المجال المستهدف، وبالتالي تشجيع المحلل المحلل على تعميم المجالات المستهدفة غير المرئية. النتائج التجريبية على (الإنجليزية) عن مجموعات البيانات العنكبوت والصينية الصينية تظهر أن هدف التعلم التلوي يعزز بشكل كبير أداء محلل الأساس.
The importance of building semantic parsers which can be applied to new domains and generate programs unseen at training has long been acknowledged, and datasets testing out-of-domain performance are becoming increasingly available. However, little or no attention has been devoted to learning algorithms or objectives which promote domain generalization, with virtually all existing approaches relying on standard supervised learning. In this work, we use a meta-learning framework which targets zero-shot domain generalization for semantic parsing. We apply a model-agnostic training algorithm that simulates zero-shot parsing by constructing virtual train and test sets from disjoint domains. The learning objective capitalizes on the intuition that gradient steps that improve source-domain performance should also improve target-domain performance, thus encouraging a parser to generalize to unseen target domains. Experimental results on the (English) Spider and Chinese Spider datasets show that the meta-learning objective significantly boosts the performance of a baseline parser.
References used
https://aclanthology.org/
rate research
Read More
Semantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs, which can be executed against a real-world environment. The expensive annotation of utterance-program pairs has long been acknowledged as a maj
or bottleneck for the deployment of contemporary neural models to real-life applications. In this work, we focus on the task of semi-supervised learning where a limited amount of annotated data is available together with many unlabeled NL utterances. Based on the observation that programs which correspond to NL utterances should always be executable, we propose to encourage a parser to generate executable programs for unlabeled utterances. Due to the large search space of executable programs, conventional methods that use beam-search for approximation, such as self-training and top-k marginal likelihood training, do not perform as well. Instead, we propose a set of new training objectives that are derived by approaching the problem of learning from executions from the posterior regularization perspective. Our new objectives outperform conventional methods on Overnight and GeoQuery, bridging the gap between semi-supervised and supervised learning.
Humans are capable of learning novel concepts from very few examples; in contrast, state-of-the-art machine learning algorithms typically need thousands of examples to do so. In this paper, we propose an algorithm for learning novel concepts by repre
senting them as programs over existing concepts. This way the concept learning problem is naturally a program synthesis problem and our algorithm learns from a few examples to synthesize a program representing the novel concept. In addition, we perform a theoretical analysis of our approach for the case where the program defining the novel concept over existing ones is context-free. We show that given a learned grammar-based parser and a novel production rule, we can augment the parser with the production rule in a way that provably generalizes. We evaluate our approach by learning concepts in the semantic parsing domain extended to the few-shot novel concept learning setting, showing that our approach significantly outperforms end-to-end neural semantic parsers.
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.
Meta-learning has recently been proposed to learn models and algorithms that can generalize from a handful of examples. However, applications to structured prediction and textual tasks pose challenges for meta-learning algorithms. In this paper, we a
pply two meta-learning algorithms, Prototypical Networks and Reptile, to few-shot Named Entity Recognition (NER), including a method for incorporating language model pre-training and Conditional Random Fields (CRF). We propose a task generation scheme for converting classical NER datasets into the few-shot setting, for both training and evaluation. Using three public datasets, we show these meta-learning algorithms outperform a reasonable fine-tuned BERT baseline. In addition, we propose a novel combination of Prototypical Networks and Reptile.
Recent researches show that pre-trained models (PTMs) are beneficial to Chinese Word Segmentation (CWS). However, PTMs used in previous works usually adopt language modeling as pre-training tasks, lacking task-specific prior segmentation knowledge an
d ignoring the discrepancy between pre-training tasks and downstream CWS tasks. In this paper, we propose a CWS-specific pre-trained model MetaSeg, which employs a unified architecture and incorporates meta learning algorithm into a multi-criteria pre-training task. Empirical results show that MetaSeg could utilize common prior segmentation knowledge from different existing criteria and alleviate the discrepancy between pre-trained models and downstream CWS tasks. Besides, MetaSeg can achieve new state-of-the-art performance on twelve widely-used CWS datasets and significantly improve model performance in low-resource settings.
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
