One of the major problems with text simplification is the lack of high-quality data. The sources of simplification datasets are limited to Wikipedia and Newsela, restricting further development of this field. In this paper, we analyzed the similarity between text summarization and text simplification and exploited summarization data to help simplify. First, we proposed an alignment algorithm to extract sentence pairs from summarization datasets. Then, we designed four attributes to characterize the degree of simplification and proposed a method to filter suitable pairs. We named these pairs Sum4Simp (S4S). Next, we conducted human evaluations to show that S4S is high-quality and compared it with a real simplification dataset. Finally, we conducted experiments to illustrate that the S4S can improve the performance of several mainstream simplification models, especially in low-resource scenarios.

Finding the best way to schedule operations in a computation graph is a classical NP-hard problem which is central to compiler optimization. However, evaluating the goodness of a schedule on the target hardware can be very time-consuming. Traditional approaches as well as previous machine learning ones typically optimize proxy metrics, which are fast to evaluate but can lead to bad schedules when tested on the target hardware. In this work, we propose a new approach to scheduling by sampling proportionally to the proxy metric using a novel GFlowNet method. We introduce a technique to control the trade-off between diversity and goodness of the proposed schedules at inference time and demonstrate empirically that the pure optimization baselines can lead to subpar performance with respect to our approach when tested on a target model. Furthermore, we show that conditioning the GFlowNet on the computation graph enables generalization to unseen scheduling problems for both synthetic and real-world compiler datasets. Efficient execution of computation graphs is paramount to many scientific and industrial applications, with deep learning being a prominent example (Amodei & Hernandez, 2018). Scheduling is the action of assigning operations to the available compute resources, such as threads, cores, or nodes in a cluster (Kwok & Ahmad, 1999; Hennessy & Patterson, 2011; Pinedo, 2012). Unfortunately, finding the schedule with the shortest possible makespan (start-to-end runtime) is in general NP-hard (Papadimitriou & Steiglitz, 1998). As a result, domain experts have come up with heuristics that are tailored to specific problem instances (Ibarra & Kim, 1977).

Characterizing the sensing and communication performance tradeoff in integrated sensing and communication (ISAC) systems is challenging in the applications of learning-based human motion recognition. This is because of the large experimental datasets and the black-box nature of deep neural networks. This paper presents SDP3, a Simulation-Driven Performance Predictor and oPtimizer, which consists of SDP3 data simulator, SDP3 performance predictor and SDP3 performance optimizer. Specifically, the SDP3 data simulator generates vivid wireless sensing datasets in a virtual environment, the SDP3 performance predictor predicts the sensing performance based on the function regression method, and the SDP3 performance optimizer investigates the sensing and communication performance tradeoff analytically. It is shown that the simulated sensing dataset matches the experimental dataset very well in the motion recognition accuracy. By leveraging SDP3, it is found that the achievable region of recognition accuracy and communication throughput consists of a communication saturation zone, a sensing saturation zone, and a communication-sensing adversarial zone, of which the desired balanced performance for ISAC systems lies in the third one.

We introduce The Benchmark of Linguistic Minimal Pairs (shortened to BLiMP), a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English. BLiMP consists of 67 sub-datasets, each containing 1000 minimal pairs isolating specific contrasts in syntax, morphology, or semantics. The data is automatically generated according to expert-crafted grammars, and aggregate human agreement with the labels is 96.4%. We use it to evaluate n-gram, LSTM, and Transformer (GPT-2 and Transformer-XL) LMs. We find that state-of-the-art models identify morphological contrasts reliably, but they struggle with semantic restrictions on the distribution of quantifiers and negative polarity items and subtle syntactic phenomena such as extraction islands.

If you received this in your inbox, thank you for signing up and your vote of confidence. If you're reading this as a post on our site, sign up here so you can receive it directly in the future. Every week, I'll take a look at the hottest fintech news of the previous week. This will include everything from funding rounds to trends to an analysis of a particular space to hot takes on a particular company or phenomenon. There's a lot of fintech news out there and it's my job to stay on top of it -- and make sense of it -- so you can stay in the know.

In this paper, we investigate the effect of addressing difficult samples from a given text dataset on the downstream text classification task. We define difficult samples as being non-obvious cases for text classification by analysing them in the semantic embedding space; specifically - (i) semantically similar samples that belong to different classes and (ii) semantically dissimilar samples that belong to the same class. We propose a penalty function to measure the overall difficulty score of every sample in the dataset. We conduct exhaustive experiments on 13 standard datasets to show a consistent improvement of up to 9% and discuss qualitative results to show effectiveness of our approach in identifying difficult samples for a text classification model.

Tree fruit breeding is a long-term activity involving repeated measurements of various fruit quality traits on a large number of samples. These traits are traditionally measured by manually counting the fruits, weighing to indirectly measure the fruit size, and fruit colour is classified subjectively into different color categories using visual comparison to colour charts. These processes are slow, expensive and subject to evaluators' bias and fatigue. Recent advancements in deep learning can help automate this process. Objective data can be generated for consistent characterization of germplasm, with greater speed and higher accuracy. A method was developed to automatically count the number of sweet cherry fruits in a camera's field of view in real time using YOLOv3. A system capable of analyzing the image data for other traits such as size and color was also developed using Python. The YOLO model obtained close to 99% accuracy in object detection and counting of cherries and 90% on the Intersection over Union metric for object localization when extracting size and colour information. The model surpasses human performance and offers a significant improvement compared to manual counting.

Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models. Nevertheless, assessing the quality of the generation is an even more arduous task than the generation itself, and this issue has not been given adequate consideration recently. This paper proposes a novel evaluation framework, GPTScore, which utilizes the emergent abilities (e.g., zero-shot instruction) of generative pre-trained models to score generated texts. There are 19 pre-trained models explored in this paper, ranging in size from 80M (e.g., FLAN-T5-small) to 175B (e.g., GPT3). Experimental results on four text generation tasks, 22 evaluation aspects, and corresponding 37 datasets demonstrate that this approach can effectively allow us to achieve what one desires to evaluate for texts simply by natural language instructions. This nature helps us overcome several long-standing challenges in text evaluation--how to achieve customized, multi-faceted evaluation without the need for annotated samples. We make our code publicly available at https://github.com/jinlanfu/GPTScore.

Recent advances in discourse parsing performance create the impression that, as in other NLP tasks, performance for high-resource languages such as English is finally becoming reliable. In this paper we demonstrate that this is not the case, and thoroughly investigate the impact of data diversity on RST parsing stability. We show that state-of-the-art architectures trained on the standard English newswire benchmark do not generalize well, even within the news domain. Using the two largest RST corpora of English with text from multiple genres, we quantify the impact of genre diversity in training data for achieving generalization to text types unseen during training. Our results show that a heterogeneous training regime is critical for stable and generalizable models, across parser architectures. We also provide error analyses of model outputs and out-of-domain performance. To our knowledge, this study is the first to fully evaluate cross-corpus RST parsing generalizability on complete trees, examine between-genre degradation within an RST corpus, and investigate the impact of genre diversity in training data composition.

Recent years have seen an exponential increase in the application of machine learning (ML) techniques to several fields, including physics and astrophysics (Nguyen et al., 2019; Zhou et al., 2021; Reiss et al., 2021; Rüdisser et al., 2022). ML-based tools provide predictions more accurate than other models due to their generalisation properties. Furthermore, the current availability of computational power makes feasible building complex and prediction-effective predictors. These are the main reasons behind the heavy application of ML algorithms, even though they usually require a huge amount of training data to be provided. This need of large training data sets may be challenging in some scenarios, but it does not constitute a limitation when ML predictors rely on observations gathered on beam experiments in high-energy physics and by long-lasting space missions, for instance. Predictive tools in general, and ML models in particular, are precious resources for space missions to achieve several goals, as time series missing data filling and pattern recognition (Villani et al., 2022).