Abstract

Missing values in time-series is a frequently occurring problem in multi-sensor data analysis. The current state-of-the-art imputation networks don’t generalize well across the benchmarks. Further, some directly operate on space-time product graphs which may minimize the information loss but are prohibitively expensive. We propose Product Graph U-networks using Temporal pooling for Spa- tiotemporal imputation (P-GUTS). It uses pooled representations of the space-time sequence in the bottleneck part of the U-network and is memory efficient. Since datasets can have differing levels of redundancy, relying on a single view (pooled representation) of the data can be limiting. Therefore, P-GUTS uses multiple U-Nets with different pooling factors and aggregates the representations. We demonstrate the effectiveness of P-GUTS on multiple real-world imputation datasets and robustness across increasing missing rates. P-GUTS also gives encouraging results in spatiotemporal forecast- ing.

Abstract

Mangoes hold significant economic and cultural importance in India and globally, making accurate yield prediction crucial for optimizing domestic consumption, enhancing international trade, and supporting farmers in decision-making. Traditional yield estimation methods, such as manual counting, are labor-intensive, error-prone, and impractical for large-scale orchards, necessitating automated solutions. This study presents a novel time-series vision dataset for mango yield prediction, capturing images from 12 trees across eight spatial orientations (SW, S, SE, E, NE, N, NW, W) over 2.5 months to analyze fruit growth and flowering patterns. A high-resolution image dataset was created and annotated using a semi-automatic pipeline integrating YOLO for object detection and SAM for precise segmentation, significantly reducing manual annotation efforts. Benchmarking was conducted using state-of-the-art deep learning models for segmentation (DeepLabV3+, PSPNet, SegFormer, Swin-S, YOLO+SAM) and detection (Mask R-CNN, Faster R-CNN, DETR, YOLO). For flower segmentation, Swin-S achieved the best results with 67.35 IoU, followed closely by SegFormer with 66.44 IoU, while for fruitlet segmentation, YOLO+SAM obtained the highest IoU of 78.97. In detection tasks, YOLO achieved the best performance for both flowers and fruitlets, with 63.8 mAP50 and 80.5 mAP50, respectively. Additionally, segmentation is identified as a suitable approach for flower feature extraction in yield prediction models, with SegFormer emerging as a strong choice due to its lower computational cost. Furthermore, this study discusses the relationship between wind direction patterns and the flower-to-fruit conversion ratio, challenging previous research that attributed yield variations solely to canopy structure differences with respect to orientation.

Abstract

The scarcity of high-quality annotated data presents a sig- nificant challenge in developing effective end-to-end speech- to-text translation (ST) systems, particularly for low-resource languages. This paper explores the hypothesis that weakly la- beled data can be used to build ST models for low-resource lan- guage pairs. We constructed speech-to-text translation datasets with the help of bitext mining using state-of-the-art sentence encoders. We mined the multilingual Shrutilipi corpus to build Shrutilipi-anuvaad, a dataset comprising ST data for lan- guage pairs Bengali-Hindi, Malayalam-Hindi, Odia-Hindi, and Telugu-Hindi. We created multiple versions of training data with varying degrees of quality and quantity to investigate the effect of quality versus quantity of weakly labeled data on ST model performance. Results demonstrate that ST systems can be built using weakly labeled data, with performance compa- rable to massive multi-modal multilingual baselines such as SONAR and SeamlessM4T.

Abstract

The National Institutional Ranking Framework (NIRF) provides a comprehensive evaluation of colleges across India based on various parameters such as teaching, learning, resources, research, and outreach. It integrates these parameters by giving a fixed priority to each of them. In today’s competitive academic landscape, choosing the right college is a crucial decision for students seeking higher education. This depends on several factors specific to each student such as their social background, location, economic status and rank in the qualifying examination, etc.This research introduces a novel approach to enhance the utility of NIRF data by creating user-specific rankings tailored to individual preferences. By incorporating user-defined criteria such as median salary, number of students placed, facilities for Physically Challenged Students (PCS), faculty strength, research funding, the proposed system generates personalized rankings that align with the unique needs and aspirations of each student.Our system utilizes a novel skyline-based approach and analyzes the NIRF data alongside user preferences to generate dynamic rankings that adapt to evolving student priorities. We show multiple use-cases to demonstrate the utility of our approach in real-world scenarios, and study the way colleges are ranked for different user preferences. Our study shows that the college rankings so obtained can be quite different from the standard NIRF ranking.

Abstract

Computer-Assisted Language Learning systems provide speech exaggerating at mispronounced word locations as a feedback to the L2 learners. Traditionally, expert speakers recordings (which limit the scalability) are considered for this task though there are advancements in text-to-speech (TTS) that can generate native like natural sounding speech. To address these, this work proposes two novel controllable strategies for scalable speech exaggeration. One strategy is direct speech exaggeration that incorporates the proposed label conditioned tokenization in GlowTTS. Another strategy is cascading the state-of-the-art TTS to a WORLD vocoder with proposed energy and duration modifications. A subset of Tatoeba corpus, that we annotated with prominent words, is used for experimentation. Automatic and manual assessment reveals that the exaggerated speech quality from both direct and cascaded strategy with duration modification is closer to the prominent words in the native speaker's speech.

Abstract

Despite advancements in Speech-to-Speech Translation, maintaining expressiveness between the source and target speech, particularly between English and Indian languages, remains challenging. This study investigates prosodic similarities and variations between English and Malayalam, a language spoken in southern India. A set of 22 prompts from the IViE corpus, covering five categories—simple sentences, WH-questions, questions without morphosyntactic markers, inversion questions, and coordinations—was selected. These prompts, originally spoken by UK speakers, were translated into Malayalam and both language prompts were recorded by bilingual Malayalam speakers while preserving expressiveness. Word-level prominence was manually annotated, and comparisons were made across Indian English, Malayalam, and UK English. The analysis reveals that prominence is retained at key points in Indian English, whereas in Malayalam, it is low due to question specific diacritics and agglutinative nature.

Abstract

We present our shared task on text-based emotion detection, covering more than 30 languages from seven distinct language families. These languages are predominantly low-resource and are spoken across various continents. The data instances are multi-labeled with six emotional classes, with additional datasets in 11 languages annotated for emotion intensity. Participants were asked to predict labels in three tracks: (a) multilabel emotion detection, (b) emotion intensity score detection, and (c) cross-lingual emotion detection. The task attracted over 700 participants. We received final submissions from more than 200 teams and 93 system description papers. We report baseline results, along with findings on the best-performing systems, the most common approaches, and the most effective methods across different tracks and languages. The datasets for this task are publicly available.

Abstract

People worldwide use language in subtle and complex ways to express emotions. Although emotion recognition--an umbrella term for several NLP tasks--impacts various applications within NLP and beyond, most work in this area has focused on high-resource languages. This has led to significant disparities in research efforts and proposed solutions, particularly for under-resourced languages, which often lack high-quality annotated datasets. In this paper, we present BRIGHTER--a collection of multilabeled, emotion-annotated datasets in 28 different languages and across several domains. BRIGHTER primarily covers low-resource languages from Africa, Asia, Eastern Europe, and Latin America, with instances labeled by fluent speakers. We highlight the challenges related to the data collection and annotation processes, and then report experimental results for monolingual and crosslingual multi-label emotion identification, as well as emotion intensity recognition. We analyse the variability in performance across languages and text domains, both with and without the use of LLMs, and show that the BRIGHTER datasets represent a meaningful step towards addressing the gap in text-based emotion recognition.

Abstract

We present a diffusion-based generative model for coordinated trajectory planning in multi-UAV swarms. The proposed method represents each UAV’s trajectory in a Bernstein polynomial coefficient space and employs a de- noising diffusion process with self-attention layers to generate diverse, feasible motion plans. A safety filter is integrated into the generation pipeline to refine candidate trajectories, enforcing inter-drone collision avoidance and other feasibility constraints. The model is trained offline on a large set of expert demonstration trajectories, eliminating the need for reinforcement learning and manual reward function design. In experiments with a 16-UAV swarm using a dataset of collision-free trajectories, the approach achieved a high success rate in producing safe and smooth flight paths. These results demonstrate that the learned planner can rapidly generate a diverse set of smooth, collision-free trajectories for the swarm. Keywords- Swarm, Diffusion, UAV path planning, Joint Opti- mization

Abstract

Machine Translation (MT) revolutionizes cross-lingual communication but is prone to errors, necessitating thorough evaluation for enhancement. Translation quality can be assessed by humans and automatic evaluation metrics. Human evaluation, though valuable, is costly and subject to limitations in scalability and consistency. While automated metrics supplement manual evaluations, this field still has considerable potential for development. However, there exists prior survey work on automatic evaluation metrics, it is worth noting that most of these are focused on resource-rich languages, leaving a significant gap in evaluating MT outputs across other language families. To bridge this gap, we present an exhaustive survey, encompassing discussions on MT meta-evaluation datasets, human assessments, and diverse metrics. We categorize both human and automatic evaluation approaches, and offer decision trees to aid in selecting the appropriate approach. Additionally, we evaluate sentences across languages, domains and linguistic features, and further meta-evaluate the metrics by correlating them with human scores. We critically examine the limitations and challenges inherent in current datasets and evaluation approaches. We propose suggestions for future research aimed at enhancing MT evaluation, including the importance of diverse and well-distributed datasets, the refinement of human evaluation methodologies, and the development of robust metrics that closely align with human judgments.