Abstract

With an increasing number of vehicles on the road every day, intelligent traffic monitoring and control is essential. This entails development of cost-effective, scalable, and easy-to-install monitoring systems. In this letter, a versatile piezoresistance-based cost-effective on-road sensor system is presented to estimate vehicle speed and vehicle wheelbase length. The system consists of a velostat thin film sensing element placed on the road, with read out circuits and control electronics located at the sidewalk. The system measures the speed of a vehicle with 90.4% accuracy, and the length of the wheelbase with 94.3% accuracy. The wheelbase length can be used to classify the vehicle type. Our experiments show that the system is reliable, as the sensor output returns to the initial values after each vehicle passes. The utilization of flexible piezoresistive sensors makes this system convenient to deploy in different applications where basic traffic activity monitoring is required with speed, count, and classification estimation of vehicles.

Abstract

This paper presents an evaluation of 16 machine translation systems submitted to the Shared Task of the 9th Conference of Machine Translation (WMT24) for the English-Hindi (en-hi) language pair using our Complex Structures Test (CoST) suite. Aligning with this year’s test suite sub-task theme, “Help us break LLMs”, we curated a comprehensive test suite encompassing diverse datasets across various categories, including autobiography, poetry, legal, conversation, play, narration, technical, and mixed genres. Our evaluation reveals that all the systems struggle significantly with the archaic style of text like legal and technical writings or text with creative twist like conversation and poetry datasets, highlighting their weaknesses in handling complex linguistic structures and stylistic nuances inherent in these text types. Our evaluation identifies the strengths and limitations of the submitted models, pointing to specific areas where further research and development are needed to enhance their performance. Our test suite is available at https://github.com/AnanyaCoder/CoST-WMT-24-Test-Suite-Task.

Abstract

Machine translation (MT) evaluation metrics like BLEU and chrF++ are widely used reference-based metrics that do not require training and are language-independent. However, these metrics primarily focus on n-gram matching and often overlook semantic depth and contextual understanding. To address this gap, we introduce chrF-S (Semantic chrF++), an enhanced metric that integrates sentence embeddings to evaluate translation quality more comprehensively. By combining traditional character and word n-gram analysis with semantic information derived from embeddings, chrF-S captures both syntactic accuracy and sentence-level semantics. This paper presents our contributions to the WMT24 shared metrics task, showcasing our participation and the development of chrF-S. We also demonstrate that, according to preliminary results on the leaderboard, our metric performs on par with other supervised and LLM-based metrics. By merging semantic insights with n-gram precision, chrF-S offers a significant enhancement in the assessment of machine-generated translations, advancing the field of MT evaluation. Our code and data will be made available at https://github.com/AnanyaCoder/chrF-S.

Abstract

Translating for languages with limited resources poses a persistent challenge due to the scarcity of high-quality training data. To enhance translation accuracy, we explored controlled generation mechanisms, focusing on the importance of control tokens. In our experiments, while training, we encoded the target sentence length as a control token to the source sentence, treating it as an additional feature for the source sentence. We developed various NMT models using transformer architecture and conducted experiments across 8 language directions (English = Assamese, Manipuri, Khasi, and Mizo), exploring four variations of length encoding mechanisms. Through comparative analysis against the baseline model, we submitted two systems for each language direction. We report our findings for the same in this work.

Abstract

With the primary focus on evaluating the ef- fectiveness of large language models for au- tomatic reference-less translation assessment, this work presents our experiments on mimick- ing human direct assessment to evaluate the quality of translations in English and Indian languages. We constructed a translation evalua- tion task where we performed zero-shot learn- ing, in-context example-driven learning, and fine-tuning of large language models to pro- vide a score out of 100, where 100 represents a perfect translation and 1 represents a poor translation. We compared the performance of our trained systems with existing methods such as COMET, BERT-Scorer, and LABSE, and found that the LLM-based evaluator (LLaMA- 2-13B) achieves a comparable or higher overall correlation with human judgments for the con- sidered Indian language pairs (Refer figure 1).

Abstract

The objective of the MTIL track in FIRE 2023 was to encourage the development of Indian Language to Indian Language (IL-IL) Neural Machine Translation models. The languages covered in the track included Hindi, Gujarati, Kannada, Odia, Punjabi, Urdu, Telugu, Kashmiri, and Sindhi. The track consists of two tasks: (i) a General Translation Task and (ii) a Domain specific Translation Task with Governance and Healthcare being the chosen domains. For the listed languages, we proposed 12 diverse language directions for the general domain translation task and 8 each for healthcare and governance domains. Participants were encouraged to submit models for one or more language pairs. We witnessed the creation of 34 distinct models spanning various language pairs and domains. Model assessments were conducted using five evaluation metrics: BLEU, CHRF, CHRF++, TER, and COMET. The submitted model outputs were ranked based on the CHRF score.

Abstract

The demand for daily form digitization requires extensive manual effort. This paper presents an efficient pipeline for digitizing Indic handwritten forms, minimizing human intervention. We validate the pipeline using textit{Hindi} and textit{Bengali} forms, creating a dedicated test set, textit{IIIT-Indic-Form-Test}. Our approach enables form capture and orientation alignment via smartphone, extracting printed and handwritten fields with OCR enhanced by template annotations. A predefined word list supports post-processing for fields like textit{name}, textit{state}, and textit{country}. We compare our pipeline with tools like Google Parser and Microsoft Azure and conduct ablation studies on form style, rotation, and handwriting variations. A GUI-based application for digitization is also developed. The code and model are publicly available at https://github.com/shaoncvit/Indic_Handwritten_Form_dataset.

Abstract

The landscape of human memory and event cognition research has witnessed a transformative journey toward the use of naturalistic contexts and tasks. In this review, we track this progression from abrupt, artificial stimuli used in extensively controlled laboratory experiments to more naturalistic tasks and stimuli that present a more faithful representation of the real world. We argue that in order to improve ecological validity, naturalistic study designs must consider the complexity of the cognitive phenomenon being studied. Then, we review the current state of “naturalistic” event segmentation studies and critically assess frequently employed movie stimuli. We evaluate recently developed tools like lifelogging and other extended reality technologies to help address the challenges we identified with existing naturalistic approaches. We conclude by offering some guidelines that can be used to design ecologically valid cognitive neuroscience studies of memory and event cognition.

Abstract

Traditional evaluation metrics like BLEU and ROUGE fall short when capturing the nuanced qualities of generated text, particularly when there is no single ground truth. In this paper, we explore the potential of Large Language Models (LLMs), specifically Google Gemini 1, to serve as automatic evaluators for non-standardized metrics in summarization and dialog-based tasks. We conduct experiments across multiple prompting strategies to examine how LLMs fare as quality evaluators when compared with human judgments on the SummEval and USR datasets, asking the model to generate both a score as well as a justification for the score. Furthermore, we explore the robustness of the LLM evaluator by using perturbed inputs. Our findings suggest that while LLMs show promise, their alignment with human evaluators is limited, they are not robust against perturbations and significant improvements are required for their standalone use as reliable evaluators for subjective metrics.

Abstract

The integration of Vision-Language Models (VLMs) into various applications has highlighted the importance of evaluating these models for inherent biases, especially along gender and racial lines. Traditional bias assessment methods in VLMs typically rely on accuracy metrics, assessing disparities in performance across different demographic groups. These methods, however, often overlook the impact of the model’s disabilities, like lack spatial reasoning, which may skew the bias assessment. In this work, we propose an approach that systematically examines how current bias evaluation metrics account for the model’s limitations. We introduce two methods that circumvent these disabilities by integrating spatial guidance from textual and visual modalities. Our experiments aim to refine bias quantification by effectively mitigating the impact of spatial reasoning limitations, offering a more accurate assessment of biases in VLMs.