For real-world language applications, detecting an out-of-distribution (OOD) sample is helpful to alert users or reject such unreliable samples. However, modern over-parameterized language models often produce overconfident predictions for both in-distribution (ID) and OOD samples. In particular, language models suffer from OOD samples with a similar semantic representation to ID samples since these OOD samples lie near the ID manifold. A rejection network can be trained with ID and diverse outlier samples to detect test OOD samples, but explicitly collecting auxiliary OOD datasets brings an additional burden for data collection. In this paper, we propose a simple but effective method called Pseudo Outlier Exposure (POE) that constructs a surrogate OOD dataset by sequentially masking tokens related to ID classes. The surrogate OOD sample introduced by POE shows a similar representation to ID data, which is most effective in training a rejection network. Our method does not require any external OOD data and can be easily implemented within off-the-shelf Transformers. A comprehensive comparison with state-of-the-art algorithms demonstrates POE's competitiveness on several text classification benchmarks.
相關內容
The Function-as-a-service (FaaS) computing model has recently seen significant growth especially for highly scalable, event-driven applications. The easy-to-deploy and cost-efficient fine-grained billing of FaaS is highly attractive to big data applications. However, the stateless nature of serverless platforms poses major challenges when supporting stateful I/O intensive workloads such as a lack of native support for stateful execution, state sharing, and inter-function communication. In this paper, we explore the feasibility of performing stateful big data analytics on serverless platforms and improving I/O throughput of functions by using modern storage technologies such as Intel Optane DC Persistent Memory (PMEM). To this end, we propose Marvel, an end-to-end architecture built on top of the popular serverless platform, Apache OpenWhisk and Apache Hadoop. Marvel makes two main contributions: (1) enable stateful function execution on OpenWhisk by maintaining state information in an in-memory caching layer; and (2) provide access to PMEM backed HDFS storage for faster I/O performance. Our evaluation shows that Marvel reduces the overall execution time of big data applications by up to 86.6% compared to current MapReduce implementations on AWS Lambda.
Graded type systems, such as the one underlying the Granule programming language, allow various different properties of a program's behaviour to be tracked via annotating types with additional information, which we call grades. One example of such a property, often used as a case study in prior work on graded types, is information flow control, in which types are graded by a lattice of security levels allowing noninterference properties to be automatically verified and enforced. These typically focus on one particular aspect of security, however, known as confidentiality; public outputs are prohibited from depending on private inputs. Integrity, a property specifying that trusted outputs must not depend on untrusted inputs, has not been examined in this context. This short paper aims to remedy this omission. It is well-known that confidentiality and integrity are in some sense dual properties, but simply reversing the ordering of the security lattice turns out to be unsatisfactory for the purpose of combining both kinds of property in a single system, at least in our setting. We analogize the situation to recent work on embedding both linear and uniqueness types in a graded framework, and use this framing to demonstrate that we can enforce both integrity and confidentiality alongside one another. The main idea is to add an additional flavour of modality annotated for integrity, such that the existing graded comonad for tracking confidentiality now also acts as a relative monad over the new modality, with rules allowing information to flow from trusted to public to private.
In surgical computer vision applications, obtaining labeled training data is challenging due to data-privacy concerns and the need for expert annotation. Unpaired image-to-image translation techniques have been explored to automatically generate large annotated datasets by translating synthetic images to the realistic domain. However, preserving the structure and semantic consistency between the input and translated images presents significant challenges, mainly when there is a distributional mismatch in the semantic characteristics of the domains. This study empirically investigates unpaired image translation methods for generating suitable data in surgical applications, explicitly focusing on semantic consistency. We extensively evaluate various state-of-the-art image translation models on two challenging surgical datasets and downstream semantic segmentation tasks. We find that a simple combination of structural-similarity loss and contrastive learning yields the most promising results. Quantitatively, we show that the data generated with this approach yields higher semantic consistency and can be used more effectively as training data.
Out-of-domain (OOD) detection is a crucial component in industrial applications as it helps identify when a model encounters inputs that are outside the training distribution. Most industrial pipelines rely on pre-trained models for downstream tasks such as CNN or Vision Transformers. This paper investigates the performance of those models on the task of out-of-domain detection. Our experiments demonstrate that pre-trained transformers models achieve higher detection performance out of the box. Furthermore, we show that pre-trained ViT and CNNs can be combined with refinement methods such as CIDER to improve their OOD detection performance even more. Our results suggest that transformers are a promising approach for OOD detection and set a stronger baseline for this task in many contexts
We investigate the equational theory of Kleene algebra terms with variable complements -- (language) complement where it applies only to variables -- w.r.t. languages. While the equational theory w.r.t. languages coincides with the language equivalence (under the standard language valuation) for Kleene algebra terms, this coincidence is broken if we extend the terms with complements. In this paper, we prove the decidability of some fragments of the equational theory: the universality problem is coNP-complete, and the inequational theory t <= s is coNP-complete when t does not contain Kleene-star. To this end, we introduce words-to-letters valuations; they are sufficient valuations for the equational theory and ease us in investigating the equational theory w.r.t. languages. Additionally, we prove that for words with variable complements, the equational theory coincides with the word equivalence.
Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels or distilling using LLM-generated labels. However, finetuning and distillation require large amounts of training data to achieve comparable performance to LLMs. We introduce Distilling step-by-step, a new mechanism that (a) trains smaller models that outperform LLMs, and (b) achieves so by leveraging less training data needed by finetuning or distillation. Our method extracts LLM rationales as additional supervision for small models within a multi-task training framework. We present three findings across 4 NLP benchmarks: First, compared to both finetuning and distillation, our mechanism achieves better performance with much fewer labeled/unlabeled training examples. Second, compared to LLMs, we achieve better performance using substantially smaller model sizes. Third, we reduce both the model size and the amount of data required to outperform LLMs; our 770M T5 model outperforms the 540B PaLM model using only 80% of available data on a benchmark task.
Pre-trained Language Models (PLMs) which are trained on large text corpus via self-supervised learning method, have yielded promising performance on various tasks in Natural Language Processing (NLP). However, though PLMs with huge parameters can effectively possess rich knowledge learned from massive training text and benefit downstream tasks at the fine-tuning stage, they still have some limitations such as poor reasoning ability due to the lack of external knowledge. Research has been dedicated to incorporating knowledge into PLMs to tackle these issues. In this paper, we present a comprehensive review of Knowledge-Enhanced Pre-trained Language Models (KE-PLMs) to provide a clear insight into this thriving field. We introduce appropriate taxonomies respectively for Natural Language Understanding (NLU) and Natural Language Generation (NLG) to highlight these two main tasks of NLP. For NLU, we divide the types of knowledge into four categories: linguistic knowledge, text knowledge, knowledge graph (KG), and rule knowledge. The KE-PLMs for NLG are categorized into KG-based and retrieval-based methods. Finally, we point out some promising future directions of KE-PLMs.
Existing recommender systems extract the user preference based on learning the correlation in data, such as behavioral correlation in collaborative filtering, feature-feature, or feature-behavior correlation in click-through rate prediction. However, regretfully, the real world is driven by causality rather than correlation, and correlation does not imply causation. For example, the recommender systems can recommend a battery charger to a user after buying a phone, in which the latter can serve as the cause of the former, and such a causal relation cannot be reversed. Recently, to address it, researchers in recommender systems have begun to utilize causal inference to extract causality, enhancing the recommender system. In this survey, we comprehensively review the literature on causal inference-based recommendation. At first, we present the fundamental concepts of both recommendation and causal inference as the basis of later content. We raise the typical issues that the non-causality recommendation is faced. Afterward, we comprehensively review the existing work of causal inference-based recommendation, based on a taxonomy of what kind of problem causal inference addresses. Last, we discuss the open problems in this important research area, along with interesting future works.
Visual information extraction (VIE) has attracted considerable attention recently owing to its various advanced applications such as document understanding, automatic marking and intelligent education. Most existing works decoupled this problem into several independent sub-tasks of text spotting (text detection and recognition) and information extraction, which completely ignored the high correlation among them during optimization. In this paper, we propose a robust visual information extraction system (VIES) towards real-world scenarios, which is a unified end-to-end trainable framework for simultaneous text detection, recognition and information extraction by taking a single document image as input and outputting the structured information. Specifically, the information extraction branch collects abundant visual and semantic representations from text spotting for multimodal feature fusion and conversely, provides higher-level semantic clues to contribute to the optimization of text spotting. Moreover, regarding the shortage of public benchmarks, we construct a fully-annotated dataset called EPHOIE (//github.com/HCIILAB/EPHOIE), which is the first Chinese benchmark for both text spotting and visual information extraction. EPHOIE consists of 1,494 images of examination paper head with complex layouts and background, including a total of 15,771 Chinese handwritten or printed text instances. Compared with the state-of-the-art methods, our VIES shows significant superior performance on the EPHOIE dataset and achieves a 9.01% F-score gain on the widely used SROIE dataset under the end-to-end scenario.
Dynamic programming (DP) solves a variety of structured combinatorial problems by iteratively breaking them down into smaller subproblems. In spite of their versatility, DP algorithms are usually non-differentiable, which hampers their use as a layer in neural networks trained by backpropagation. To address this issue, we propose to smooth the max operator in the dynamic programming recursion, using a strongly convex regularizer. This allows to relax both the optimal value and solution of the original combinatorial problem, and turns a broad class of DP algorithms into differentiable operators. Theoretically, we provide a new probabilistic perspective on backpropagating through these DP operators, and relate them to inference in graphical models. We derive two particular instantiations of our framework, a smoothed Viterbi algorithm for sequence prediction and a smoothed DTW algorithm for time-series alignment. We showcase these instantiations on two structured prediction tasks and on structured and sparse attention for neural machine translation.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191