Identification of the Relevance of Comments in Codes Using Bag of Words and Transformer Based Models
The Forum for Information Retrieval (FIRE) started a shared task this year for classification of comments of different code segments. This is binary text classification task where the objective is to identify whether comments given for certain code segments are relevant or not. The BioNLP-IISERB group at the Indian Institute of Science Education and Research Bhopal (IISERB) participated in this task and submitted five runs for five different models. The paper presents the overview of the models and other significant findings on the training corpus. The methods involve different feature engineering schemes and text classification techniques. The performance of the classical bag of words model and transformer-based models were explored to identify significant features from the given training corpus. We have explored different classifiers viz., random forest, support vector machine and logistic regression using the bag of words model. Furthermore, the pre-trained transformer based models like BERT, RoBERT and ALBERT were also used by fine-tuning them on the given training corpus. The performance of different such models over the training corpus were reported and the best five models were implemented on the given test corpus. The empirical results show that the bag of words model outperforms the transformer based models, however, the performance of our runs are not reasonably well in both training and test corpus. This paper also addresses the limitations of the models and scope for further improvement.
相關內容
Graphics Processing Units (GPUs) are over-stressed to accelerate High-Performance Computing applications and are used to accelerate Deep Neural Networks in several domains where they have a life expectancy of many years. These conditions expose the GPUs hardware to (premature) aging, causing permanent faults to arise after the usual end-of-manufacturing test. Techniques to assess the impact of permanent faults in GPUs are then strongly required, thus allowing to estimate the reliability risk and to possibly mitigate it. In this paper, we present a method to evaluate the effects of permanent faults affecting the GPU scheduler and control units, which are the most peculiar and stressed resources, along with the first figures that allow quantifying these effects. We characterize over 5.83x10^5 permanent fault effects in the scheduler and controllers of a gate-level GPU model. Then, we map the observed error categories in software by instrumenting the code of 13 applications and two convolutional neural networks, injecting more than 1.65x10^5 permanent errors. Our two-level fault injection strategy reduces the evaluation time from hundreds of years of gate-level evaluation to hundreds of hours.We found that faults in the GPU parallelism management units can modify the opcode, the addresses, and the status of thread(s) and warp(s). The large majority (up to 99%) of these hardware permanent errors impacts the running software execution. Errors affecting the instruction operation or resource management hang the code, while 45% of errors in the parallelism management or control-flow induce silent data corruptions.
SHACL is a W3C-proposed schema language for expressing structural constraints on RDF graphs. Recent work on formalizing this language has revealed a striking relationship to description logics. SHACL expressions can use three fundamental features that are not so common in description logics. These features are equality tests; disjointness tests; and closure constraints. Moreover, SHACL is peculiar in allowing only a restricted form of expressions (so-called targets) on the left-hand side of inclusion constraints. The goal of this paper is to obtain a clear picture of the impact and expressiveness of these features and restrictions. We show that each of the four features is primitive: using the feature, one can express boolean queries that are not expressible without using the feature. We also show that the restriction that SHACL imposes on allowed targets is inessential, as long as closure constraints are not used. In addition, we show that enriching SHACL with "full" versions of equality tests, or disjointness tests, results in a strictly more powerful language.
We study universal traits which emerge both in real-world complex datasets, as well as in artificially generated ones. Our approach is to analogize data to a physical system and employ tools from statistical physics and Random Matrix Theory (RMT) to reveal their underlying structure. We focus on the feature-feature covariance matrix, analyzing both its local and global eigenvalue statistics. Our main observations are: (i) The power-law scalings that the bulk of its eigenvalues exhibit are vastly different for uncorrelated normally distributed data compared to real-world data, (ii) this scaling behavior can be completely modeled by generating gaussian data with long range correlations, (iii) both generated and real-world datasets lie in the same universality class from the RMT perspective, as chaotic rather than integrable systems, (iv) the expected RMT statistical behavior already manifests for empirical covariance matrices at dataset sizes significantly smaller than those conventionally used for real-world training, and can be related to the number of samples required to approximate the population power-law scaling behavior, (v) the Shannon entropy is correlated with local RMT structure and eigenvalues scaling, and substantially smaller in strongly correlated datasets compared to uncorrelated synthetic data, and requires fewer samples to reach the distribution entropy. These findings show that with sufficient sample size, the Gram matrix of natural image datasets can be well approximated by a Wishart random matrix with a simple covariance structure, opening the door to rigorous studies of neural network dynamics and generalization which rely on the data Gram matrix.
Machine Learning approaches like clustering methods deal with massive datasets that present an increasing challenge. We devise parallel algorithms to compute the Multi-Slice Clustering (MSC) for 3rd-order tensors. The MSC method is based on spectral analysis of the tensor slices and works independently on each tensor mode. Such features fit well in the parallel paradigm via a distributed memory system. We show that our parallel scheme outperforms sequential computing and allows for the scalability of the MSC method.
Large language models (large LMs) are increasingly trained on massive codebases and used to generate code. However, LMs lack awareness of security and are found to frequently produce unsafe code. This work studies the security of LMs along two important axes: (i) security hardening, which aims to enhance LMs' reliability in generating secure code, and (ii) adversarial testing, which seeks to evaluate LMs' security at an adversarial standpoint. We address both of these by formulating a new security task called controlled code generation. The task is parametric and takes as input a binary property to guide the LM to generate secure or unsafe code, while preserving the LM's capability of generating functionally correct code. We propose a novel learning-based approach called SVEN to solve this task. SVEN leverages property-specific continuous vectors to guide program generation towards the given property, without modifying the LM's weights. Our training procedure optimizes these continuous vectors by enforcing specialized loss terms on different regions of code, using a high-quality dataset carefully curated by us. Our extensive evaluation shows that SVEN is highly effective in achieving strong security control. For instance, a state-of-the-art CodeGen LM with 2.7B parameters generates secure code for 59.1% of the time. When we employ SVEN to perform security hardening (or adversarial testing) on this LM, the ratio is significantly boosted to 92.3% (or degraded to 36.8%). Importantly, SVEN closely matches the original LMs in functional correctness.
This work investigates the potential of 5G and beyond sidelink (SL) communication to support multi-hop tactical networks. We first provide a technical and historical overview of 3GPP SL standardization activities, and then consider applications to current problems of interest in tactical networking. We consider a number of multi-hop routing techniques which are expected to be of interest for SL-enabled multi-hop tactical networking and examine open-source tools useful for network emulation. Finally, we discuss relevant research directions which may be of interest for 5G SL-enabled tactical communications, namely the integration of RF sensing and positioning, as well as emerging machine learning tools such as federated and decentralized learning, which may be of great interest for resource allocation and routing problems that arise in tactical applications. We conclude by summarizing recent developments in the 5G SL literature and provide guidelines for future research.
Since the popularization of BiLSTMs and Transformer-based bidirectional encoders, state-of-the-art syntactic parsers have lacked incrementality, requiring access to the whole sentence and deviating from human language processing. This paper explores whether fully incremental dependency parsing with modern architectures can be competitive. We build parsers combining strictly left-to-right neural encoders with fully incremental sequence-labeling and transition-based decoders. The results show that fully incremental parsing with modern architectures considerably lags behind bidirectional parsing, noting the challenges of psycholinguistically plausible parsing.
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this paper, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.
Recent developments in image classification and natural language processing, coupled with the rapid growth in social media usage, have enabled fundamental advances in detecting breaking events around the world in real-time. Emergency response is one such area that stands to gain from these advances. By processing billions of texts and images a minute, events can be automatically detected to enable emergency response workers to better assess rapidly evolving situations and deploy resources accordingly. To date, most event detection techniques in this area have focused on image-only or text-only approaches, limiting detection performance and impacting the quality of information delivered to crisis response teams. In this paper, we present a new multimodal fusion method that leverages both images and texts as input. In particular, we introduce a cross-attention module that can filter uninformative and misleading components from weak modalities on a sample by sample basis. In addition, we employ a multimodal graph-based approach to stochastically transition between embeddings of different multimodal pairs during training to better regularize the learning process as well as dealing with limited training data by constructing new matched pairs from different samples. We show that our method outperforms the unimodal approaches and strong multimodal baselines by a large margin on three crisis-related tasks.
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191