Integrating technology with the distinctive characteristics of craftsmanship has become a key issue in the field of digital craftsmanship. This paper introduces Layered Interactions, a design approach that seamlessly merges Human-Computer Interaction (HCI) technologies with traditional lacquerware craftsmanship. By leveraging the multi-layer structure and material properties of lacquerware, we embed interactive circuits and integrate programmable hardware within the layers, creating tangible interfaces that support diverse interactions. This method enhances the adaptability and practicality of traditional crafts in modern digital contexts. Through the development of a lacquerware toolkit, along with user experiments and semi-structured interviews, we demonstrate that this approach not only makes technology more accessible to traditional artisans but also enhances the materiality and emotional qualities of interactive interfaces. Additionally, it fosters mutual learning and collaboration between artisans and technologists. Our research introduces a cross-disciplinary perspective to the HCI community, broadening the material and design possibilities for interactive interfaces.

Moritz Altemeyer, Steffen Eger, Johannes Daxenberger, Yanran Chen, Tim Altendorf, Philipp Cimiano, Benjamin Schiller. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Natural Language Generation (NLG), and more generally generative AI, are among the currently most impactful research fields.Creative NLG, such as automatic poetry generation, is a fascinating niche in this area.While most previous research has focused on forms of the Turing test when evaluating automatic poetry generation -can humans distinguish between automatic and human generated poetry -we evaluate the diversity of automatically generated poetry (with a focus on quatrains), by comparing distributions of generated poetry to distributions of human poetry along structural, lexical, semantic and stylistic dimensions, assessing different model types (word vs. character-level, general purpose LLMs vs. poetry-specific models), including the very recent LLaMA3-8B, and types of fine-tuning (conditioned vs. unconditioned).We find that current automatic poetry systems are considerably underdiverse along multiple dimensions -they often do not rhyme sufficiently, are semantically too uniform and even do not match the length distribution of human poetry.Our experiments reveal, however, that style-conditioning and character-level modeling clearly increases diversity across virtually all dimensions we explore.Our identified limitations may serve as the basis for more genuinely diverse future poetry generation models. 1 L 0.62 12 34 20.18 20 2.84 de LLaMA3 con 0.76 10 47 21.69 21 4.14 en HUMAN 1.00 4 67 28.06 28 6.26 en DeepSpeare 0.57 15 33 23.85 24 2.85 en SA 0.92 12 52 27.36 27 5.38 en ByGPT5 S 0.80 12 44 25.30 25 5.09 en ByGPT5 L 0.77 11 47 24.97 25 4.87 en GPT2 S 0.69 13 55 24.11 24 4.48 en GPT2 L 0.72 13 56 24.74 24 4.94 en GPTNeo S 0.55 11 55 22.67 22 3.89 en GPTNeo L 0.48 13 34 21.93 22 3.16 en LLaMA2 S 0.87 15 75 28.60 27 7.52 en LLaMA2 L 0.67 12 54 23.95 24 4.50 en LLaMA3 0.59 14 60 23.20 23 4.23 en ByGPT5 con S 0.85 13 42 26.21 26 4.96 en ByGPT5 con L 0.84 14 42 25.85 25 4.84 en GPT2 con S 0.86 17 61 28.37 27 6.18 en GPT2 con L 0.83 16 70 27.8227 6.15 en GPTNeo con S 0.74 16 49 25.13 24 4.47 en GPTNeo con L 0.53 12 35 22.26 22 3.36 en LLaMA2 con S 0.70 17 74 33.55 32 7.83 en LLaMA2 con L 0.81 15 56 26.92 26 5.80 en LLaMA3 con 0.78 16 65 27.12 26 5.35

Abstract Recently proposed BERT-based evaluation metrics for text generation perform well on standard benchmarks but are vulnerable to adversarial attacks, e.g., relating to information correctness. We argue that this stems (in part) from the fact that they are models of semantic similarity. In contrast, we develop evaluation metrics based on Natural Language Inference (NLI), which we deem a more appropriate modeling. We design a preference-based adversarial attack framework and show that our NLI based metrics are much more robust to the attacks than the recent BERT-based metrics. On standard benchmarks, our NLI based metrics outperform existing summarization metrics, but perform below SOTA MT metrics. However, when combining existing metrics with our NLI metrics, we obtain both higher adversarial robustness (15%–30%) and higher quality metrics as measured on standard benchmarks (+5% to 30%).

The application of recommendation systems online services is becoming more and more extensive. However, most existing recommendation algorithms centralize multi-party information into a central processor, which may lead to the risk of privacy leakage. And many enterprises or institutions still have the problem that data cannot be shared. Federated learning has been introduced into recommendation algorithms for privacy- aware distributed learning. A typical federated learning is that each client uses local data to train a shared model, the server uses their gradient information to form a global model, and then each client updates. In this paper, we propose a federated deep recommendation algorithm called FedHe-mlp that applies a federated deep learning for data privacy protection, and combines heterogeneous information network (HIN) and matrix factorization technique for better prediction performance. First, each client obtains heterogeneous information through meta- paths, then we combine matrix factorization and heterogeneous information to mine the latent features and heterogeneous features of each client. Finally, We propose a deep neural network that considers features from multiple views. Extensive experiments on three public datasets demonstrate that FedHe- mlp can provide excellent convergence speed, recommendation accuracy, and communication efficiency while preserving data privacy.

Reproducibility is of utmost concern in machine learning and natural language processing (NLP).In the field of natural language generation (especially machine translation), the seminal paper of Post (2018) has pointed out problems of reproducibility of the dominant metric, BLEU, at the time of publication.Nowadays, BERT-based evaluation metrics considerably outperform BLEU.In this paper, we ask whether results and claims from four recent BERT-based metrics can be reproduced.We find that reproduction of claims and results often fails because of (i) heavy undocumented preprocessing involved in the metrics, (ii) missing code and (iii) reporting weaker results for the baseline metrics.(iv) In one case, the problem stems from correlating not to human scores but to a wrong column in the csv file, inflating scores by 5 points.Motivated by the impact of preprocessing, we then conduct a second study where we examine its effects more closely (for one of the metrics).We find that preprocessing can have large effects, especially for highly inflectional languages.In this case, the effect of preprocessing may be larger than the effect of the aggregation mechanism (e.g., greedy alignment vs. Word Mover Distance).

The goal of this paper is to develop an ultrasonic detection device that can be mounted on an underwater snake vehicle (USV) for underwater district heating pipe (DHP) detection in the future. Ultrasonic detection technology (UDT) is the detection means used, and the cavitation defects in polyurethane (PUR) layer of DHPs are the object being detected. Due to the large thickness of PUR layer and the complex interface information of multi-layer structure, detecting defects of DHPs quantitatively is a difficult task. To address this issue, this paper proposes an approach that combines feature extraction and crow search algorithm (CSA) optimized support vector machine (SVM). Firstly, the main parameters and detection method of UDT are designed after investigation. Secondly, defective signals are pre-processed by signal processing to extract the features form three domains. Finally, four different classifiers are used to identify cavitation defects based on the feature-set. When compared among optimized random forest (RF), k-nearest neighbor (KNN), and ordinary SVM, the experimental results show that CSA-SVM had the highest accuracy in defect size prediction, and the validation-experiment verifies the practicability and feasibility of the CSA-SVM classifier. All experiments illustrate that the issue could be well solved by our method.

This paper describes our contribution to the Shared Task ReproGen by Belz et al. (2021), which investigates the reproducibility of human evaluations in the context of Natural Language Generation.We selected the paper "Generation of Company descriptions using concept-to-text and text-to-text deep models: data set collection and systems evaluation" (Qader et al., 2018) and aimed to replicate, as closely to the original as possible, the human evaluation and the subsequent comparison between the human judgements and the automatic evaluation metrics.Here, we first outline the text generation task of the paper of Qader et al. (2018).Then, we document how we approached our replication of the paper's human evaluation.We also discuss the difficulties we encountered and which information was missing.Our replication has medium to strong correlation (0.66 Spearman overall) with the original results of Qader et al. (2018), but due to the missing information about how Qader et al. (2018) compared the human judgements with the metric scores, we have refrained from reproducing this comparison.