Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGetting to Production with Few-shot Natural Language Generation Models
الوصول إلى الإنتاج مع عدد قليل من نماذج توليد اللغة الطبيعية
211
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذه الورقة، ندرس استخدام النماذج اللغوية المدربة مسبقا لتمكين توليد لغة البندقية القليلة (NLG) في أنظمة الحوار الموجهة نحو المهام. نقدم نظاما يتكون من التدريب الذاتي التكراري وإطار قالب صغير قابل للتوسيع يتم تخصيص بيانات الإدخال المهيكلة في نص شبه طبيعي للاستفادة الكاملة من نماذج اللغة المدربة مسبقا. نحن نقارن تمثيلات Var Ious لإدخال ونماذج NLG وإخراجها وإظهار أن تحويل المدخلات والمخرجات لتكون مشابهة لما شابه نموذج اللغة من قبل أثناء التدريب المسبق يحسن أداء الطراز القليل من الطرازات. نظظ أن Mod-Els العصبي يمكن تدريبها على أساس عدد قليل من الأمثلة المشروحة مع توفير الدقة العالية، وخفضت إلى حد كبير متطلبات الموارد الخاصة بوقوف مجال جديد أو لغة. هذا مستوى كفاءة البيانات يزيل الحاجة إلى جمع بيانات الحشد مما أدى إلى جودة أعلى جودة مشروح من قبل اللغويين الخبراء. بالإضافة إلى ذلك، ستحسن عمليات صيانة النموذج والتصحيح في هذا الإعداد القليل من الرصاص. أخيرا، نستكشف تقطير واستخدام نظام التخزين المؤقت لإرضاء متطلبات الكمون لأنظمة العالم الحقيقي.
In this paper, we study the utilization of pre-trained language models to enable few-shotNatural Language Generation (NLG) in task-oriented dialog systems. We introduce a system consisting of iterative self-training and an extensible mini-template framework that textualizes the structured input data into semi-natural text to fully take advantage of pre-trained language models. We compare var-ious representations of NLG models' input and output and show that transforming the input and output to be similar to what the language model has seen before during pre-training improves the model's few-shot performance substantially. We show that neural mod-els can be trained with as few as 300 annotated examples while providing high fidelity, considerably lowering the resource requirements for standing up a new domain or language.This level of data efficiency removes the need for crowd-sourced data collection resulting in higher quality data annotated by expert linguists. In addition, model maintenance and debugging processes will improve in this few-shot setting. Finally, we explore distillation and using a caching system to satisfy latency requirements of real-world systems.
References used
https://aclanthology.org/
rate research
Read More
Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields impressive few-shot
results for a wide range of text classification tasks. It is also a promising direction to improve data efficiency in generative settings, but there are several challenges to using a combination of task descriptions and example-based learning for text generation. In particular, it is crucial to find task descriptions that are easy to understand for the pretrained model and to ensure that it actually makes good use of them; furthermore, effective measures against overfitting have to be implemented. In this paper, we show how these challenges can be tackled: We introduce GenPET, a method for text generation that is based on pattern-exploiting training, a recent approach for combining textual instructions with supervised learning that only works for classification tasks. On several summarization and headline generation datasets, GenPET gives consistent improvements over strong baselines in few-shot settings.
General-purpose language models have demonstrated impressive capabilities, performing on par with state-of-the-art approaches on a range of downstream natural language processing (NLP) tasks and benchmarks when inferring instructions from very few ex
amples. Here, we evaluate the multilingual skills of the GPT and T5 models in conducting multi-class classification on non-English languages without any parameter updates. We show that, given a few English examples as context, pre-trained language models can predict not only English test samples but also non-English ones. Finally, we find the in-context few-shot cross-lingual prediction results of language models are significantly better than random prediction, and they are competitive compared to the existing state-of-the-art cross-lingual models and translation models.
When scaled to hundreds of billions of parameters, pretrained language models such as GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance. However, enormous amounts of compute are required for training and applying such big models, res
ulting in a large carbon footprint and making it difficult for researchers and practitioners to use them. We show that performance similar to GPT-3 can be obtained with language models that are much greener'' in that their parameter count is several orders of magnitude smaller. This is achieved by converting textual inputs into cloze questions that contain a task description, combined with gradient-based optimization; exploiting unlabeled data gives further improvements. We identify key factors required for successful natural language understanding with small language models.
Knowledge-enriched text generation poses unique challenges in modeling and learning, driving active research in several core directions, ranging from integrated modeling of neural representations and symbolic information in the sequential/hierarchica
l/graphical structures, learning without direct supervisions due to the cost of structured annotation, efficient optimization and inference with massive and global constraints, to language grounding on multiple modalities, and generative reasoning with implicit commonsense knowledge and background knowledge. In this tutorial we will present a roadmap to line up the state-of-the-art methods to tackle these challenges on this cutting-edge problem. We will dive deep into various technical components: how to represent knowledge, how to feed knowledge into a generation model, how to evaluate generation results, and what are the remaining challenges?
Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain. In this paper, we explore retrieval-based methods for intent c
lassification and slot filling tasks in few-shot settings. Retrieval-based methods make predictions based on labeled examples in the retrieval index that are similar to the input, and thus can adapt to new domains simply by changing the index without having to retrain the model. However, it is non-trivial to apply such methods on tasks with a complex label space like slot filling. To this end, we propose a span-level retrieval method that learns similar contextualized representations for spans with the same label via a novel batch-softmax objective. At inference time, we use the labels of the retrieved spans to construct the final structure with the highest aggregated score. Our method outperforms previous systems in various few-shot settings on the CLINC and SNIPS benchmarks.
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
