While machine translation evaluation metrics based on string overlap (e.g., BLEU) have their limitations, their computations are transparent: the BLEU score assigned to a particular candidate translation can be traced back to the presence or absence of certain words. The operations of newer learned metrics (e.g., BLEURT, COMET), which leverage pretrained language models to achieve higher correlations with human quality judgments than BLEU, are opaque in comparison. In this paper, we shed light on the behavior of these learned metrics by creating DEMETR, a diagnostic dataset with 31K English examples (translated from 10 source languages) for evaluating the sensitivity of MT evaluation metrics to 35 different linguistic perturbations spanning semantic, syntactic, and morphological error categories. All perturbations were carefully designed to form minimal pairs with the actual translation (i.e., differ in only one aspect). We find that learned metrics perform substantially better than string-based metrics on DEMETR. Additionally, learned metrics differ in their sensitivity to various phenomena (e.g., BERTScore is sensitive to untranslated words but relatively insensitive to gender manipulation, while COMET is much more sensitive to word repetition than to aspectual changes). We publicly release DEMETR to spur more informed future development of machine translation evaluation metrics

This study presents a novel approach for modeling and simulating human-vehicle interactions in order to examine the effects of automated driving systems (ADS) on driving performance and driver control workload. Existing driver-ADS interaction studies have relied on simulated or real-world human driver experiments that are limited in providing objective evaluation of the dynamic interactions and control workloads on the driver. Our approach leverages an integrated human model-based active driving system (HuMADS) to simulate the dynamic interaction between the driver model and the haptic-based ADS during a vehicle overtaking task. Two driver arm-steering models were developed for both tense and relaxed human driver conditions and validated against experimental data. We conducted a simulation study to evaluate the effects of three different haptic shared control conditions (based on the presence and type of control conflict) on overtaking task performance and driver workloads. We found that No Conflict shared control scenarios result in improved driving performance and reduced control workloads, while Conflict scenarios result in unsafe maneuvers and increased workloads. These findings, which are consistent with experimental studies, demonstrate the potential for our approach to improving future ADS design for safer driver assistance systems.

We introduce the first automated models for classifying natural language descriptions provided in cost documents called "Bills of Quantities" (BoQs) popular in the infrastructure construction industry, into the International Construction Measurement Standard (ICMS). The models we deployed and systematically evaluated for multi-class text classification are learnt from a dataset of more than 50 thousand descriptions of items retrieved from 24 large infrastructure construction projects across the United Kingdom. We describe our approach to language representation and subsequent modelling to examine the strength of contextual semantics and temporal dependency of language used in construction project documentation. To do that we evaluate two experimental pipelines to inferring ICMS codes from text, on the basis of two different language representation models and a range of state-of-the-art sequence-based classification methods, including recurrent and convolutional neural network architectures. The findings indicate a highly effective and accurate ICMS automation model is within reach, with reported accuracy results above 90% F1 score on average, on 32 ICMS categories. Furthermore, due to the specific nature of language use in the BoQs text; short, largely descriptive and technical, we find that simpler models compare favourably to achieving higher accuracy results. Our analysis suggest that information is more likely embedded in local key features in the descriptive text, which explains why a simpler generic temporal convolutional network (TCN) exhibits comparable memory to recurrent architectures with the same capacity, and subsequently outperforms these at this task.

Decoding strategies play a crucial role in natural language generation systems. They are usually designed and evaluated in open-ended text-only tasks, and it is not clear how different strategies handle the numerous challenges that goal-oriented multimodal systems face (such as grounding and informativeness). To answer this question, we compare a wide variety of different decoding strategies and hyper-parameter configurations in a Visual Dialogue referential game. Although none of them successfully balance lexical richness, accuracy in the task, and visual grounding, our in-depth analysis allows us to highlight the strengths and weaknesses of each decoding strategy. We believe our findings and suggestions may serve as a starting point for designing more effective decoding algorithms that handle the challenges of Visual Dialogue tasks.

Proper noun compounds, e.g., "Covid vaccine", convey information in a succinct manner (a "Covid vaccine" is a "vaccine that immunizes against the Covid disease"). These are commonly used in short-form domains, such as news headlines, but are largely ignored in information-seeking applications. To address this limitation, we release a new manually annotated dataset, ProNCI, consisting of 22.5K proper noun compounds along with their free-form semantic interpretations. ProNCI is 60 times larger than prior noun compound datasets and also includes non-compositional examples, which have not been previously explored. We experiment with various neural models for automatically generating the semantic interpretations from proper noun compounds, ranging from few-shot prompting to supervised learning, with varying degrees of knowledge about the constituent nouns. We find that adding targeted knowledge, particularly about the common noun, results in performance gains of upto 2.8%. Finally, we integrate our model generated interpretations with an existing Open IE system and observe an 7.5% increase in yield at a precision of 85%. The dataset and code are available at https://github.com/dair-iitd/pronci.

The type of tasks that falls in the 4 D's of Robotisation: Dull, Dirty, Dangerous and Dear, task taken over by robots Full Stack developer Kernel Augmentation Aminekammoun55@gmail.com Abstract-- For a robot to be perfect and enter the everyday Safety Thus, any type of produce robot parts [Research in progress] task that falls in the 4 D's of Robotisation: Dull, Dirty, Dangerous and Dear can be achieved by adding a module to Size and shape complexity [4]: In relation to the price The architecture of such robots is sophisticated and full of Security [6]: Robots are, for most cases, built insecure and different options that we can choose from. The complexity of a robotic developers, roboticists, Embedded System Developers and system makes the vendors and robotic companies unable to cyber security experts must pay attention to a lot of caveats cover the complete threat landscape. The robot's modules are themselves modular. These types of robots may be used on a daily basis in hospitals and maybe used in response to a crisis like a pandemic. Charging time 4h The robot is equipped with a joystick implemented in Sensor Lidar, artificial vision, depth vision, the web application to guide the robot manually.

Most vision-and-language pretraining research focuses on English tasks. However, the creation of multilingual multimodal evaluation datasets (e.g. Multi30K, xGQA, XVNLI, and MaRVL) poses a new challenge in finding high-quality training data that is both multilingual and multimodal. In this paper, we investigate whether machine translating English multimodal data can be an effective proxy for the lack of readily available multilingual data. We call this framework TD-MML: Translated Data for Multilingual Multimodal Learning, and it can be applied to any multimodal dataset and model. We apply it to both pretraining and fine-tuning data with a state-of-the-art model. In order to prevent models from learning from low-quality translated text, we propose two metrics for automatically removing such translations from the resulting datasets. In experiments on five tasks across 20 languages in the IGLUE benchmark, we show that translated data can provide a useful signal for multilingual multimodal learning, both at pretraining and fine-tuning.

Customer feedback can be an important signal for improving commercial machine translation systems. One solution for fixing specific translation errors is to remove the related erroneous training instances followed by re-training of the machine translation system, which we refer to as instance-specific data filtering. Influence functions (IF) have been shown to be effective in finding such relevant training examples for classification tasks such as image classification, toxic speech detection and entailment task. Given a probing instance, IF find influential training examples by measuring the similarity of the probing instance with a set of training examples in gradient space. In this work, we examine the use of influence functions for Neural Machine Translation (NMT). We propose two effective extensions to a state of the art influence function and demonstrate on the sub-problem of copied training examples that IF can be applied more generally than handcrafted regular expressions.

Reference Expression Generation (REG) and Comprehension (REC) are two highly correlated tasks. Modeling REG and REC simultaneously for utilizing the relation between them is a promising way to improve both. However, the problem of distinct inputs, as well as building connections between them in a single model, brings challenges to the design and training of the joint model. To address the problems, we propose a unified model for REG and REC, named UniRef. It unifies these two tasks with the carefully-designed Image-Region-Text Fusion layer (IRTF), which fuses the image, region and text via the image cross-attention and region cross-attention. Additionally, IRTF could generate pseudo input regions for the REC task to enable a uniform way for sharing the identical representation space across the REC and REG. We further propose Vision-conditioned Masked Language Modeling (VMLM) and Text-Conditioned Region Prediction (TRP) to pre-train UniRef model on multi-granular corpora. The VMLM and TRP are directly related to REG and REC, respectively, but could help each other. We conduct extensive experiments on three benchmark datasets, RefCOCO, RefCOCO+ and RefCOCOg. Experimental results show that our model outperforms previous state-of-the-art methods on both REG and REC.

Text summarization has been intensively studied in many languages, and some languages have reached advanced stages. Yet, Arabic Text Summarization (ATS) is still in its developing stages. Existing ATS datasets are either small or lack diversity. We build, LANS, a large-scale and diverse dataset for Arabic Text Summarization task. LANS offers 8.4 million articles and their summaries extracted from newspapers websites metadata between 1999 and 2019. The high-quality and diverse summaries are written by journalists from 22 major Arab newspapers, and include an eclectic mix of at least more than 7 topics from each source. We conduct an intrinsic evaluation on LANS by both automatic and human evaluations. Human evaluation of 1000 random samples reports 95.4% accuracy for our collected summaries, and automatic evaluation quantifies the diversity and abstractness of the summaries. The dataset is publicly available upon request.