Developers expend a significant amount of time in editing code for a variety of reasons such as bug fixing or adding new features. Designing effective methods to predict code edits has been an active yet challenging area of research due to the diversity of code edits and the difficulty of capturing the developer intent. In this work, we address these challenges by endowing pre-trained large language models (LLMs) of code with the knowledge of prior, relevant edits. The generative capability of the LLMs helps address the diversity in code changes and conditioning code generation on prior edits helps capture the latent developer intent. We evaluate two well-known LLMs, Codex and CodeT5, in zero-shot and fine-tuning settings respectively. In our experiments with two datasets, the knowledge of prior edits boosts the performance of the LLMs significantly and enables them to generate 29% and 54% more correctly edited code in top-1 suggestions relative to the current state-of-the-art symbolic and neural approaches, respectively.
相關內容
Methods to generate text from structured data have advanced significantly in recent years, primarily due to fine-tuning of pre-trained language models on large datasets. However, such models can fail to produce output faithful to the input data, particularly on out-of-domain data. Sufficient annotated data is often not available for specific domains, leading us to seek an unsupervised approach to improve the faithfulness of output text. Since the problem is fundamentally one of consistency between the representations of the structured data and text, we evaluate the effectiveness of cycle training in this work. Cycle training uses two models which are inverses of each other: one that generates text from structured data, and one which generates the structured data from natural language text. We show that cycle training, when initialized with a small amount of supervised data (100 samples in our case), achieves nearly the same performance as fully supervised approaches for the data-to-text generation task on the WebNLG, E2E, WTQ, and WSQL datasets. We perform extensive empirical analysis with automated evaluation metrics and a newly designed human evaluation schema to reveal different cycle training strategies' effectiveness of reducing various types of generation errors. Our code is publicly available at //github.com/Edillower/CycleNLG.
Large amounts of tabular data remain underutilized due to privacy, data quality, and data sharing limitations. While training a generative model producing synthetic data resembling the original distribution addresses some of these issues, most applications require additional constraints from the generated data. Existing synthetic data approaches are limited as they typically only handle specific constraints, e.g., differential privacy (DP) or increased fairness, and lack an accessible interface for declaring general specifications. In this work, we introduce ProgSyn, the first programmable synthetic tabular data generation algorithm that allows for comprehensive customization over the generated data. To ensure high data quality while adhering to custom specifications, ProgSyn pre-trains a generative model on the original dataset and fine-tunes it on a differentiable loss automatically derived from the provided specifications. These can be programmatically declared using statistical and logical expressions, supporting a wide range of requirements (e.g., DP or fairness, among others). We conduct an extensive experimental evaluation of ProgSyn on a number of constraints, achieving a new state-of-the-art on some, while remaining general. For instance, at the same fairness level we achieve 2.3% higher downstream accuracy than the state-of-the-art in fair synthetic data generation on the Adult dataset. Overall, ProgSyn provides a versatile and accessible framework for generating constrained synthetic tabular data, allowing for specifications that generalize beyond the capabilities of prior work.
Encountering outdated documentation is not a rare occurrence for developers and users in the software engineering community. To ensure that software documentation is up-to-date, developers often have to manually check whether the documentation needs to be updated whenever changes are made to the source code. In our previous work, we proposed an approach to automatically detect outdated code element references in software repositories and found that more than a quarter of the 1000 most popular projects on GitHub contained at least one outdated reference. In this paper, we present a GitHub Actions tool that builds on our previous work's approach that GitHub developers can configure to automatically scan for outdated code element references in their GitHub project's documentation whenever a pull request is submitted.
Recommendation systems are ubiquitous yet often difficult for users to control and adjust when recommendation quality is poor. This has motivated the development of conversational recommendation systems (CRSs), with control over recommendations provided through natural language feedback. However, building conversational recommendation systems requires conversational training data involving user utterances paired with items that cover a diverse range of preferences. Such data has proved challenging to collect scalably using conventional methods like crowdsourcing. We address it in the context of item-set recommendation, noting the increasing attention to this task motivated by use cases like music, news and recipe recommendation. We present a new technique, TalkTheWalk, that synthesizes realistic high-quality conversational data by leveraging domain expertise encoded in widely available curated item collections, showing how these can be transformed into corresponding item set curation conversations. Specifically, TalkTheWalk generates a sequence of hypothetical yet plausible item sets returned by a system, then uses a language model to produce corresponding user utterances. Applying TalkTheWalk to music recommendation, we generate over one million diverse playlist curation conversations. A human evaluation shows that the conversations contain consistent utterances with relevant item sets, nearly matching the quality of small human-collected conversational data for this task. At the same time, when the synthetic corpus is used to train a CRS, it improves Hits@100 by 10.5 points on a benchmark dataset over standard baselines and is preferred over the top-performing baseline in an online evaluation.
Recent generalizations of the Hopfield model of associative memories are able to store a number $P$ of random patterns that grows exponentially with the number $N$ of neurons, $P=\exp(\alpha N)$. Besides the huge storage capacity, another interesting feature of these networks is their connection to the attention mechanism which is part of the Transformer architectures widely applied in deep learning. In this work, we consider a generic family of pattern ensembles, and thanks to the statistical mechanics analysis of an auxiliary Random Energy Model, we are able to provide exact asymptotic thresholds for the retrieval of a typical pattern, $\alpha_1$, and lower bounds for the maximum of the load $\alpha$ for which all patterns can be retrieved, $\alpha_c$. Additionally, we characterize the size of the basins of attractions. We discuss in detail the cases of Gaussian and spherical patterns, and show that they display rich and qualitatively different phase diagrams.
Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledge-grounded dialogue systems often require a large number of dialogue instances to learn as they fail to capture the correlations between different diseases and neglect the diagnostic experience shared among them. To address this issue, we propose a more natural and practical paradigm, i.e., low-resource medical dialogue generation, which can transfer the diagnostic experience from source diseases to target ones with a handful of data for adaptation. It is capitalized on a commonsense knowledge graph to characterize the prior disease-symptom relations. Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues. More importantly, by dynamically evolving disease-symptom graphs, GEML also well addresses the real-world challenges that the disease-symptom correlations of each disease may vary or evolve along with more diagnostic cases. Extensive experiment results on the CMDD dataset and our newly-collected Chunyu dataset testify the superiority of our approach over state-of-the-art approaches. Besides, our GEML can generate an enriched dialogue-sensitive knowledge graph in an online manner, which could benefit other tasks grounded on knowledge graph.
The content based image retrieval aims to find the similar images from a large scale dataset against a query image. Generally, the similarity between the representative features of the query image and dataset images is used to rank the images for retrieval. In early days, various hand designed feature descriptors have been investigated based on the visual cues such as color, texture, shape, etc. that represent the images. However, the deep learning has emerged as a dominating alternative of hand-designed feature engineering from a decade. It learns the features automatically from the data. This paper presents a comprehensive survey of deep learning based developments in the past decade for content based image retrieval. The categorization of existing state-of-the-art methods from different perspectives is also performed for greater understanding of the progress. The taxonomy used in this survey covers different supervision, different networks, different descriptor type and different retrieval type. A performance analysis is also performed using the state-of-the-art methods. The insights are also presented for the benefit of the researchers to observe the progress and to make the best choices. The survey presented in this paper will help in further research progress in image retrieval using deep learning.
The chronological order of user-item interactions can reveal time-evolving and sequential user behaviors in many recommender systems. The items that users will interact with may depend on the items accessed in the past. However, the substantial increase of users and items makes sequential recommender systems still face non-trivial challenges: (1) the hardness of modeling the short-term user interests; (2) the difficulty of capturing the long-term user interests; (3) the effective modeling of item co-occurrence patterns. To tackle these challenges, we propose a memory augmented graph neural network (MA-GNN) to capture both the long- and short-term user interests. Specifically, we apply a graph neural network to model the item contextual information within a short-term period and utilize a shared memory network to capture the long-range dependencies between items. In addition to the modeling of user interests, we employ a bilinear function to capture the co-occurrence patterns of related items. We extensively evaluate our model on five real-world datasets, comparing with several state-of-the-art methods and using a variety of performance metrics. The experimental results demonstrate the effectiveness of our model for the task of Top-K sequential recommendation.
Knowledge graph (KG) embedding encodes the entities and relations from a KG into low-dimensional vector spaces to support various applications such as KG completion, question answering, and recommender systems. In real world, knowledge graphs (KGs) are dynamic and evolve over time with addition or deletion of triples. However, most existing models focus on embedding static KGs while neglecting dynamics. To adapt to the changes in a KG, these models need to be re-trained on the whole KG with a high time cost. In this paper, to tackle the aforementioned problem, we propose a new context-aware Dynamic Knowledge Graph Embedding (DKGE) method which supports the embedding learning in an online fashion. DKGE introduces two different representations (i.e., knowledge embedding and contextual element embedding) for each entity and each relation, in the joint modeling of entities and relations as well as their contexts, by employing two attentive graph convolutional networks, a gate strategy, and translation operations. This effectively helps limit the impacts of a KG update in certain regions, not in the entire graph, so that DKGE can rapidly acquire the updated KG embedding by a proposed online learning algorithm. Furthermore, DKGE can also learn KG embedding from scratch. Experiments on the tasks of link prediction and question answering in a dynamic environment demonstrate the effectiveness and efficiency of DKGE.
Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks. Motivated by this observation, we develop new network architectures that increase adversarial robustness by performing feature denoising. Specifically, our networks contain blocks that denoise the features using non-local means or other filters; the entire networks are trained end-to-end. When combined with adversarial training, our feature denoising networks substantially improve the state-of-the-art in adversarial robustness in both white-box and black-box attack settings. On ImageNet, under 10-iteration PGD white-box attacks where prior art has 27.9% accuracy, our method achieves 55.7%; even under extreme 2000-iteration PGD white-box attacks, our method secures 42.6% accuracy. A network based on our method was ranked first in Competition on Adversarial Attacks and Defenses (CAAD) 2018 --- it achieved 50.6% classification accuracy on a secret, ImageNet-like test dataset against 48 unknown attackers, surpassing the runner-up approach by ~10%. Code and models will be made publicly available.
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