اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدGood-Enough Example Extrapolation
179
0
0.0
(
0
)
تأليف
Jason Wei
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
This paper asks whether extrapolating the hidden space distribution of text examples from one class onto another is a valid inductive bias for data augmentation. To operationalize this question, I propose a simple data augmentation protocol called good-enough example extrapolation (GE3). GE3 is lightweight and has no hyperparameters. Applied to three text classification datasets for various data imbalance scenarios, GE3 improves performance more than upsampling and other hidden-space data augmentation methods.
قيم البحث
اقرأ أيضاً
In many applications of machine learning, certain categories of examples may be underrepresented in the training data, causing systems to underperform on such few-shot cases at test time. A common remedy is to perform data augmentation, such as by du
plicating underrepresented examples, or heuristically synthesizing new examples. But these remedies often fail to cover the full diversity and complexity of real examples. We propose a data augmentation approach that performs neural Example Extrapolation (Ex2). Given a handful of exemplars sampled from some distribution, Ex2 synthesizes new examples that also belong to the same distribution. The Ex2 model is learned by simulating the example generation procedure on data-rich slices of the data, and it is applied to underrepresented, few-shot slices. We apply Ex2 to a range of language understanding tasks and significantly improve over state-of-the-art methods on multiple few-shot learning benchmarks, including for relation extraction (FewRel) and intent classification + slot filling (SNIPS).
In the classical synthesis problem, we are given an LTL formula psi over sets of input and output signals, and we synthesize a system T that realizes psi: with every input sequences x, the system associates an output sequence T(x) such that the gener
ated computation x otimes T(x) satisfies psi. In practice, the requirement to satisfy the specification in all environments is often too strong, and it is common to add assumptions on the environment. We introduce a new type of relaxation on this requirement. In good-enough synthesis (GE-synthesis), the system is required to generate a satisfying computation only if one exists. Formally, an input sequence x is hopeful if there exists some output sequence y such that the computation x otimes y satisfies psi, and a system GE-realizes psi if it generates a computation that satisfies psi on all hopeful input sequences. GE-synthesis is particularly relevant when the notion of correctness is multi-valued (rather than Boolean), and thus we seek systems of the highest possible quality, and when synthesizing autonomous systems, which interact with unexpected environments and are often only expected to do their best. We study GE-synthesis in Boolean and multi-valued settings. In both, we suggest and solve various definitions of GE-synthesis, corresponding to different ways a designer may want to take hopefulness into account. We show that in all variants, GE-synthesis is not computationally harder than traditional synthesis, and can be implemented on top of existing tools. Our algorithms are based on careful combinations of nondeterministic and universal automata. We augment systems that GE-realize their specifications by monitors that provide satisfaction information. In the multi-valued setting, we provide both a worst-case analysis and an expectation-based one, the latter corresponding to an interaction with a stochastic environment.
Since the early 1980s, the research community has developed ever more sophisticated algorithms for the problem of energy disaggregation, but despite decades of research, there is still a dearth of applications with demonstrated value. In this work, w
e explore a question that is highly pertinent to this research community: how good does energy disaggregation need to be in order to infer characteristics of a household? We present novel techniques that use unsupervised energy disaggregation to predict both household occupancy and static properties of the household such as size of the home and number of occupants. Results show that basic disaggregation approaches performs up to 30% better at occupancy estimation than using aggregate power data alone, and are up to 10% better at estimating static household characteristics. These results show that even rudimentary energy disaggregation techniques are sufficient for improved inference of household characteristics. To conclude, we re-evaluate the bar set by the community for energy disaggregation accuracy and try to answer the question how good is good enough?
Ontology-based data integration has been one of the practical methodologies for heterogeneous legacy database integrated service construction. However, it is neither efficient nor economical to build the cross-domain ontology on top of the schemas of
each legacy database for the specific integration application than to reuse the existed ontologies. Then the question lies in whether the existed ontology is compatible with the cross-domain queries and with all the legacy systems. It is highly needed an effective criteria to evaluate the compatibility as it limits the upbound quality of the integrated services. This paper studies the semantic similarity of schemas from the aspect of properties. It provides a set of in-depth criteria, namely coverage and flexibility to evaluate the compatibility among the queries, the schemas and the existing ontology. The weights of classes are extended to make precise compatibility computation. The use of such criteria in the practical project verifies the applicability of our method.
Many top-performing image captioning models rely solely on object features computed with an object detection model to generate image descriptions. However, recent studies propose to directly use scene graphs to introduce information about object rela
tions into captioning, hoping to better describe interactions between objects. In this work, we thoroughly investigate the use of scene graphs in image captioning. We empirically study whether using additional scene graph encoders can lead to better image descriptions and propose a conditional graph attention network (C-GAT), where the image captioning decoder state is used to condition the graph updates. Finally, we determine to what extent noise in the predicted scene graphs influence caption quality. Overall, we find no significant difference between models that use scene graph features and models that only use object detection features across different captioning metrics, which suggests that existing scene graph generation models are still too noisy to be useful in image captioning. Moreover, although the quality of predicted scene graphs is very low in general, when using high quality scene graphs we obtain gains of up to 3.3 CIDEr compared to a strong Bottom-Up Top-Down baseline. We open source code to reproduce all our experiments in https://github.com/iacercalixto/butd-image-captioning.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
