Automated planning is a prominent area of Artificial Intelligence, and an important component for intelligent autonomous agents. A cornerstone of domain-independent planning is the separation between planning logic, i.e. the automated reasoning side, and the knowledge model, that encodes a formal representation of domain knowledge needed to reason upon a given problem to synthesise a solution plan. Such a separation enables the use of reformulation techniques, which transform how a model is represented in order to improve the efficiency of plan generation. Over the past decades, significant research effort has been devoted to the design of reformulation techniques. In this paper, we present a systematic review of the large body of work on reformulation techniques for classical planning, aiming to provide a holistic view of the field and to foster future research in the area. As a tangible outcome, we provide a qualitative comparison of the existing classes of techniques, that can help researchers gain an overview of their strengths and weaknesses.

Training large neural networks is known to be time-consuming, with the learning duration taking days or even weeks. To address this problem, large-batch optimization was introduced. This approach demonstrated that scaling mini-batch sizes with appropriate learning rate adjustments can speed up the training process by orders of magnitude. While long training time was not typically a major issue for model-free deep offline RL algorithms, recently introduced Q-ensemble methods achieving state-of-the-art performance made this issue more relevant, notably extending the training duration. In this work, we demonstrate how this class of methods can benefit from large-batch optimization, which is commonly overlooked by the deep offline RL community. We show that scaling the mini-batch size and naively adjusting the learning rate allows for (1) a reduced size of the Q-ensemble, (2) stronger penalization of out-of-distribution actions, and (3) improved convergence time, effectively shortening training duration by 3-4x times on average.

Recent deep learning (DL) applications are mostly built on top of DL libraries. The quality assurance of these libraries is critical to the dependable deployment of DL applications. Techniques have been proposed to generate various DL models and apply them to test these libraries. However, their test effectiveness is constrained by the diversity of layer API calls in their generated DL models. Our study reveals that these techniques can cover at most 34.1% layer inputs, 25.9% layer parameter values, and 15.6% layer sequences. As a result, we find that many bugs arising from specific layer API calls (i.e., specific layer inputs, parameter values, or layer sequences) can be missed by existing techniques. Because of this limitation, we propose COMET to effectively generate DL models with diverse layer API calls for DL library testing. COMET: (1) designs a set of mutation operators and a coverage-based search algorithm to diversify layer inputs, layer parameter values, and layer sequences in DL models. (2) proposes a model synthesis method to boost the test efficiency without compromising the layer API call diversity. Our evaluation result shows that COMET outperforms baselines by covering twice as many layer inputs (69.7% vs. 34.1%), layer parameter values (50.2% vs. 25.9%), and layer sequences (39.0% vs. 15.6%) as those by the state-of-the-art. Moreover, COMET covers 3.4% more library branches than those by existing techniques. Finally, COMET detects 32 new bugs in the latest version of eight popular DL libraries, including TensorFlow and MXNet, with 21 of them confirmed by DL library developers and 7 of those confirmed bugs have been fixed by developers.

While human evaluation remains best practice for accurately judging the faithfulness of automatically-generated summaries, few solutions exist to address the increased difficulty and workload when evaluating long-form summaries. Through a survey of 162 papers on long-form summarization, we first shed light on current human evaluation practices surrounding long-form summaries. We find that 73% of these papers do not perform any human evaluation on model-generated summaries, while other works face new difficulties that manifest when dealing with long documents (e.g., low inter-annotator agreement). Motivated by our survey, we present LongEval, a set of guidelines for human evaluation of faithfulness in long-form summaries that addresses the following challenges: (1) How can we achieve high inter-annotator agreement on faithfulness scores? (2) How can we minimize annotator workload while maintaining accurate faithfulness scores? and (3) Do humans benefit from automated alignment between summary and source snippets? We deploy LongEval in annotation studies on two long-form summarization datasets in different domains (SQuALITY and PubMed), and we find that switching to a finer granularity of judgment (e.g., clause-level) reduces inter-annotator variance in faithfulness scores (e.g., std-dev from 18.5 to 6.8). We also show that scores from a partial annotation of fine-grained units highly correlates with scores from a full annotation workload (0.89 Kendall's tau using 50% judgments). We release our human judgments, annotation templates, and our software as a Python library for future research.

To mitigate gender bias in contextualized language models, different intrinsic mitigation strategies have been proposed, alongside many bias metrics. Considering that the end use of these language models is for downstream tasks like text classification, it is important to understand how these intrinsic bias mitigation strategies actually translate to fairness in downstream tasks and the extent of this. In this work, we design a probe to investigate the effects that some of the major intrinsic gender bias mitigation strategies have on downstream text classification tasks. We discover that instead of resolving gender bias, intrinsic mitigation techniques and metrics are able to hide it in such a way that significant gender information is retained in the embeddings. Furthermore, we show that each mitigation technique is able to hide the bias from some of the intrinsic bias measures but not all, and each intrinsic bias measure can be fooled by some mitigation techniques, but not all. We confirm experimentally, that none of the intrinsic mitigation techniques used without any other fairness intervention is able to consistently impact extrinsic bias. We recommend that intrinsic bias mitigation techniques should be combined with other fairness interventions for downstream tasks.

The sentence is a fundamental unit in many NLP applications. Sentence segmentation is widely used as the first preprocessing task, where an input text is split into consecutive sentences considering the end of the sentence (EOS) as their boundaries. This task formulation relies on a strong assumption that the input text consists only of sentences, or what we call the sentential units (SUs). However, real-world texts often contain non-sentential units (NSUs) such as metadata, sentence fragments, nonlinguistic markers, etc. which are unreasonable or undesirable to be treated as a part of an SU. To tackle this issue, we formulate a novel task of sentence identification, where the goal is to identify SUs while excluding NSUs in a given text. To conduct sentence identification, we propose a simple yet effective method which combines the beginning of the sentence (BOS) and EOS labels to determine the most probable SUs and NSUs based on dynamic programming. To evaluate this task, we design an automatic, language-independent procedure to convert the Universal Dependencies corpora into sentence identification benchmarks. Finally, our experiments on the sentence identification task demonstrate that our proposed method generally outperforms sentence segmentation baselines which only utilize EOS labels.

Statutory article retrieval (SAR), the task of retrieving statute law articles relevant to a legal question, is a promising application of legal text processing. In particular, high-quality SAR systems can improve the work efficiency of legal professionals and provide basic legal assistance to citizens in need at no cost. Unlike traditional ad-hoc information retrieval, where each document is considered a complete source of information, SAR deals with texts whose full sense depends on complementary information from the topological organization of statute law. While existing works ignore these domain-specific dependencies, we propose a novel graph-augmented dense statute retriever (G-DSR) model that incorporates the structure of legislation via a graph neural network to improve dense retrieval performance. Experimental results show that our approach outperforms strong retrieval baselines on a real-world expert-annotated SAR dataset.

The basic idea of lifelike computing systems is the transfer of concepts in living systems to technical use that goes even beyond existing concepts of self-adaptation and self-organisation (SASO). As a result, these systems become even more autonomous and changeable - up to a runtime transfer of the actual target function. Maintaining controllability requires a complete and dynamic (self-)quantification of the system behaviour with regard to aspects of SASO but also, in particular, lifelike properties. In this article, we discuss possible approaches for such metrics and establish a first metric for transferability. We analyse the behaviour of the metric using example applications and show that it is suitable for describing the system's behaviour at runtime.

OpenAI has quietly hired hundreds of international contractors to help train its AI tech, according to Semafor. Some are teaching software engineering to AI, potentially paving the way to replace some human coders. OpenAI's chatbot, ChatGPT, already threatens to disrupt many industries just a few months after its launch. OpenAI has quietly hired hundreds of international contractors to train its artificial intelligence in software engineering, according to a report from Semafor. Some contractors, hired in the last 6 months from places like Latin America and Eastern Europe, have reportedly been tasked with creating data to coach AI to learn simple software engineering tasks.

OpenAI, the company behind the chatbot ChatGPT, has ramped up its hiring around the world, bringing on roughly 1,000 remote contractors over the past six months in regions like Latin America and Eastern Europe, according to people familiar with the matter. About 60% of the contractors were hired to do what's called "data labeling" -- creating massive sets of images, audio clips, and other information that can then be used to train artificial intelligence tools or autonomous vehicles. The other 40% are computer programmers who are creating data for OpenAI's models to learn software engineering tasks. OpenAI's existing Codex product, launched in Aug. 2021, is designed to translate natural language into code. "A well-established company, which is determined to provide world-class AI technology to make the world a better and more efficient place, is looking for a Python Developer," reads one OpenAI job listing in Spanish, which was posted by an outsourcing agency.