Search

Sign language discourse is an essential mode of daily communication for the deaf and hard-of-hearing people. However, research on Bangla Sign Language (BdSL) faces notable limitations, primarily due to the lack of datasets. Recognizing wordlevel signs in BdSL (WL-BdSL) presents a multitude of challenges, including the need for well-annotated datasets, capturing the dynamic nature of sign gestures from facial or hand landmarks, developing suitable machine learning or deep learning-based models with substantial video samples, and so on. In this paper, we address these challenges by creating a comprehensive BdSL word-level dataset named BdSLW60 in an unconstrained and natural setting, allowing positional and temporal variations and allowing sign users to change hand dominance freely. The dataset encompasses 60 Bangla sign words, with a significant scale of 9307 video trials provided by 18 signers under the supervision of a sign language professional. The dataset was rigorously annotated and cross-checked by 60 annotators. We also introduced a unique approach of a relative quantization-based key frame encoding technique for landmark based sign gesture recognition. We report the benchmarking of our BdSLW60 dataset using the Support Vector Machine (SVM) with testing accuracy up to 67.6% and an attention-based bi-LSTM with testing accuracy up to 75.1%. The dataset is available at https://www.kaggle.com/datasets/hasaniut/bdslw60 and the code base is accessible from https://github.com/hasanssl/BdSLW60_Code.

Sharing cooking recipes is a great way to exchange culinary ideas and provide instructions for food preparation. However, categorizing raw recipes found online into appropriate food genres can be challenging due to a lack of adequate labeled data. In this study, we present a dataset named the ``Assorted, Archetypal, and Annotated Two Million Extended (3A2M+) Cooking Recipe Dataset" that contains two million culinary recipes labeled in respective categories with extended named entities extracted from recipe descriptions. This collection of data includes various features such as title, NER, directions, and extended NER, as well as nine different labels representing genres including bakery, drinks, non-veg, vegetables, fast food, cereals, meals, sides, and fusions. The proposed pipeline named 3A2M+ extends the size of the Named Entity Recognition (NER) list to address missing named entities like heat, time or process from the recipe directions using two NER extraction tools. 3A2M+ dataset provides a comprehensive solution to the various challenging recipe-related tasks, including classification, named entity recognition, and recipe generation. Furthermore, we have demonstrated traditional machine learning, deep learning and pre-trained language models to classify the recipes into their corresponding genre and achieved an overall accuracy of 98.6\%. Our investigation indicates that the title feature played a more significant role in classifying the genre.

The art of mathematical reasoning stands as a fundamental pillar of intellectual progress and is a central catalyst in cultivating human ingenuity. Researchers have recently published a plethora of works centered around the task of solving Math Word Problems (MWP) $-$ a crucial stride towards general AI. These existing models are susceptible to dependency on shallow heuristics and spurious correlations to derive the solution expressions. In order to ameliorate this issue, in this paper, we propose a framework for MWP solvers based on the generation of linguistic variants of the problem text. The approach involves solving each of the variant problems and electing the predicted expression with the majority of the votes. We use DeBERTa (Decoding-enhanced BERT with disentangled attention) as the encoder to leverage its rich textual representations and enhanced mask decoder to construct the solution expressions. Furthermore, we introduce a challenging dataset, $\mathrm{P\small{ARA}\normalsize{MAWPS}}$, consisting of paraphrased, adversarial, and inverse variants of selectively sampled MWPs from the benchmark $\mathrm{M\small{AWPS}}$ dataset. We extensively experiment on this dataset along with other benchmark datasets using some baseline MWP solver models. We show that training on linguistic variants of problem statements and voting on candidate predictions improve the mathematical reasoning and robustness of the model. We make our code and data publicly available., Comment: Accepted in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics: Student Research Workshop (ACL-SRW 2023), 17 pages, 2 figures, 7 tables

The analysis of consumer sentiment, as expressed through reviews, can provide a wealth of insight regarding the quality of a product. While the study of sentiment analysis has been widely explored in many popular languages, relatively less attention has been given to the Bangla language, mostly due to a lack of relevant data and cross-domain adaptability. To address this limitation, we present BanglaBook, a large-scale dataset of Bangla book reviews consisting of 158,065 samples classified into three broad categories: positive, negative, and neutral. We provide a detailed statistical analysis of the dataset and employ a range of machine learning models to establish baselines including SVM, LSTM, and Bangla-BERT. Our findings demonstrate a substantial performance advantage of pre-trained models over models that rely on manually crafted features, emphasizing the necessity for additional training resources in this domain. Additionally, we conduct an in-depth error analysis by examining sentiment unigrams, which may provide insight into common classification errors in under-resourced languages like Bangla. Our codes and data are publicly available at https://github.com/mohsinulkabir14/BanglaBook., Comment: Accepted in Findings of the Association for Computational Linguistics: ACL 2023

Sarcasm is a form of figurative language that serves as a humorous tool for mockery and ridicule. We present a novel architecture for sarcasm generation with emoji from a non-sarcastic input sentence in English. We divide the generation task into two sub tasks: one for generating textual sarcasm and another for collecting emojis associated with those sarcastic sentences. Two key elements of sarcasm are incorporated into the textual sarcasm generation task: valence reversal and semantic incongruity with context, where the context may involve shared commonsense or general knowledge between the speaker and their audience. The majority of existing sarcasm generation works have focused on this textual form. However, in the real world, when written texts fall short of effectively capturing the emotional cues of spoken and face-to-face communication, people often opt for emojis to accurately express their emotions. Due to the wide range of applications of emojis, incorporating appropriate emojis to generate textual sarcastic sentences helps advance sarcasm generation. We conclude our study by evaluating the generated sarcastic sentences using human judgement. All the codes and data used in this study has been made publicly available., Comment: Accepted in the 61st Annual Meeting of the Association for Computational Linguistics: Student Research Workshop (ACL SRW 2023)

Cooking recipes allow individuals to exchange culinary ideas and provide food preparation instructions. Due to a lack of adequate labeled data, categorizing raw recipes found online to the appropriate food genres is a challenging task in this domain. Utilizing the knowledge of domain experts to categorize recipes could be a solution. In this study, we present a novel dataset of two million culinary recipes labeled in respective categories leveraging the knowledge of food experts and an active learning technique. To construct the dataset, we collect the recipes from the RecipeNLG dataset. Then, we employ three human experts whose trustworthiness score is higher than 86.667% to categorize 300K recipe by their Named Entity Recognition (NER) and assign it to one of the nine categories: bakery, drinks, non-veg, vegetables, fast food, cereals, meals, sides and fusion. Finally, we categorize the remaining 1900K recipes using Active Learning method with a blend of Query-by-Committee and Human In The Loop (HITL) approaches. There are more than two million recipes in our dataset, each of which is categorized and has a confidence score linked with it. For the 9 genres, the Fleiss Kappa score of this massive dataset is roughly 0.56026. We believe that the research community can use this dataset to perform various machine learning tasks such as recipe genre classification, recipe generation of a specific genre, new recipe creation, etc. The dataset can also be used to train and evaluate the performance of various NLP tasks such as named entity recognition, part-of-speech tagging, semantic role labeling, and so on. The dataset will be available upon publication: https://tinyurl.com/3zu4778y.

Upper limb disability may be caused either due to accidents, neurological disorders, or even birth defects, imposing limitations and restrictions on the interaction with a computer for the concerned individuals using a generic optical mouse. Our work proposes the design and development of a working prototype of a sensor-based wireless head-mounted Assistive Mouse Controller (AMC), Auxilio, facilitating interaction with a computer for people with upper limb disability. Combining commercially available, low-cost motion and infrared sensors, Auxilio solely utilizes head and cheek movements for mouse control. Its performance has been juxtaposed with that of a generic optical mouse in different pointing tasks as well as in typing tasks, using a virtual keyboard. Furthermore, our work also analyzes the usability of Auxilio, featuring the System Usability Scale. The results of different experiments reveal the practicality and effectiveness of Auxilio as a head-mounted AMC for empowering the upper limb disabled community., Comment: 28 pages, 9 figures, 5 tables

Mental health research through data-driven methods has been hindered by a lack of standard typology and scarcity of adequate data. In this study, we leverage the clinical articulation of depression to build a typology for social media texts for detecting the severity of depression. It emulates the standard clinical assessment procedure Diagnostic and Statistical Manual of Mental Disorders (DSM-5) and Patient Health Questionnaire (PHQ-9) to encompass subtle indications of depressive disorders from tweets. Along with the typology, we present a new dataset of 40191 tweets labeled by expert annotators. Each tweet is labeled as 'non-depressed' or 'depressed'. Moreover, three severity levels are considered for 'depressed' tweets: (1) mild, (2) moderate, and (3) severe. An associated confidence score is provided with each label to validate the quality of annotation. We examine the quality of the dataset via representing summary statistics while setting strong baseline results using attention-based models like BERT and DistilBERT. Finally, we extensively address the limitations of the study to provide directions for further research., Comment: 17 pages, 6 figures, 6 tables, Accepted in Computers in Human Behavior

Sarcasm can be defined as saying or writing the opposite of what one truly wants to express, usually to insult, irritate, or amuse someone. Because of the obscure nature of sarcasm in textual data, detecting it is difficult and of great interest to the sentiment analysis research community. Though the research in sarcasm detection spans more than a decade, some significant advancements have been made recently, including employing unsupervised pre-trained transformers in multimodal environments and integrating context to identify sarcasm. In this study, we aim to provide a brief overview of recent advancements and trends in computational sarcasm research for the English language. We describe relevant datasets, methodologies, trends, issues, challenges, and tasks relating to sarcasm that are beyond detection. Our study provides well-summarized tables of sarcasm datasets, sarcastic features and their extraction methods, and performance analysis of various approaches which can help researchers in related domains understand current state-of-the-art practices in sarcasm detection., Comment: 50 pages, 3 tables, Submitted to 'Data Mining and Knowledge Discovery' for possible publication

In this paper, we propose an efficient MLP-based approach for learning audio representations, namely timestamp and scene-level audio embeddings. We use an encoder consisting of sequentially stacked gated MLP blocks, which accept 2D MFCCs as inputs. In addition, we also provide a simple temporal interpolation-based algorithm for computing scene-level embeddings from timestamp embeddings. The audio representations generated by our method are evaluated across a diverse set of benchmarks at the Holistic Evaluation of Audio Representations (HEAR) challenge, hosted at the NeurIPS 2021 competition track. We achieved first place on the Speech Commands (full), Speech Commands (5 hours), and the Mridingham Tonic benchmarks. Furthermore, our approach is also the most resource-efficient among all the submitted methods, in terms of both the number of model parameters and the time required to compute embeddings., Comment: In submission to Proceedings of Machine Learning Research (PMLR): NeurIPS 2021 Competition Track

Human intention is an internal, mental characterization for acquiring desired information. From interactive interfaces containing either textual or graphical information, intention to perceive desired information is subjective and strongly connected with eye gaze. In this work, we determine such intention by analyzing real-time eye gaze data with a low-cost regular webcam. We extracted unique features (e.g., Fixation Count, Eye Movement Ratio) from the eye gaze data of 31 participants to generate a dataset containing 124 samples of visual intention for perceiving textual or graphical information, labeled as either TEXT or IMAGE, having 48.39% and 51.61% distribution, respectively. Using this dataset, we analyzed 5 classifiers, including Support Vector Machine (SVM) (Accuracy: 92.19%). Using the trained SVM, we investigated the variation of visual intention among 30 participants, distributed in 3 age groups, and found out that young users were more leaned towards graphical contents whereas older adults felt more interested in textual ones. This finding suggests that real-time eye gaze data can be a potential source of identifying visual intention, analyzing which intention aware interactive interfaces can be designed and developed to facilitate human cognition., Comment: 15 pages, 9 figures, 4 tables

A language agnostic approach to recognizing emotions from speech remains an incomplete and challenging task. In this paper, we performed a step-by-step comparative analysis of Speech Emotion Recognition (SER) using Bangla and English languages to assess whether distinguishing emotions from speech is independent of language. Six emotions were categorized for this study, such as - happy, angry, neutral, sad, disgust, and fear. We employed three Emotional Speech Sets (ESS), of which the first two were developed by native Bengali speakers in Bangla and English languages separately. The third was a subset of the Toronto Emotional Speech Set (TESS), which was developed by native English speakers from Canada. We carefully selected language-independent prosodic features, adopted a Support Vector Machine (SVM) model, and conducted three experiments to carry out our proposition. In the first experiment, we measured the performance of the three speech sets individually, followed by the second experiment, where different ESS pairs were integrated to analyze the impact on SER. Finally, we measured the recognition rate by training and testing the model with different speech sets in the third experiment. Although this study reveals that SER in Bangla and English languages is mostly language-independent, some disparities were observed while recognizing emotional states like disgust and fear in these two languages. Moreover, our investigations revealed that non-native speakers convey emotions through speech, much like expressing themselves in their native tongue., Comment: 13 pages [currently under review]

Shannon's Index of Difficulty ($ID$), reputable for quantifying the perceived difficulty of pointing tasks as a logarithmic relationship between movement-amplitude ($A$) and target-width ($W$), is used for modelling the corresponding observed movement-times ($MT_O$) in such tasks in controlled experimental setup. However, real-life pointing tasks are both spatially and temporally uncontrolled, being influenced by factors such as - human aspects, subjective behavior, the context of interaction, the inherent speed-accuracy trade-off where, emphasizing accuracy compromises speed of interaction and vice versa, and so on. Effective target-width ($W_e$) is considered as spatial adjustment for compensating accuracy. However, no significant adjustment exists in the literature for compensating speed in different contexts of interaction in these tasks. As a result, without any temporal adjustment, the true difficulty of an uncontrolled pointing task may be inaccurately quantified using Shannon's ID. To verify this, we propose the ANTASID (A Novel Temporal Adjustment to Shannon's ID) formulation with detailed performance analysis. We hypothesized a temporal adjustment factor ($t$) as a binary logarithm of $MT_O$, compensating for speed due to contextual differences and minimizing the non-linearity between movement-amplitude and target-width. Considering spatial and/or temporal adjustments to ID, we conducted regression analysis using our own and Benchmark datasets in both controlled and uncontrolled scenarios of pointing tasks with a generic mouse.ANTASID formulation showed significantly superior fitness values and throughput in all the scenarios while reducing the standard error. Furthermore, the quantification of ID with ANTASID varied significantly compared to the classical formulations of Shannon's ID, validating the purpose of this study., Comment: 14 pages, 7 figures, 7 tables

Stroke patients with Upper Limb Disability (ULD) are re-acclimated to their lost motor capability through therapeutic interventions, following assessment by Physiotherapists (PTs) using various qualitative assessment protocols. However, the assessments are often biased and prone to errors. Real-time visualization and quantitative analysis of various Performance Metrics (PMs) of patient's motion data, such as - Range of Motion (RoM), Repetition Rate (RR), Velocity (V), etc., may be vital for proper assessment. In this study, we present Renovo, a wearable inertial sensor-based therapeutic system, which assists PTs with real-time visualization and quantitative patient assessment, while providing patients with progress feedback. We showcase the results of a three-week pilot study on the rehabilitation of ULD patients (N=16), in 3 successive sessions at one-week interval, following evaluation both by Renovo and PTs (N=5). Results suggest that sensor-based quantitative assessment reduces the possibility of human error and bias, enhancing efficiency of rehabilitation., Comment: 27 pages, 10 figures, 5 tables

The dynamic hand gesture recognition task has seen studies on various unimodal and multimodal methods. Previously, researchers have explored depth and 2D-skeleton-based multimodal fusion CRNNs (Convolutional Recurrent Neural Networks) but have had limitations in getting expected recognition results. In this paper, we revisit this approach to hand gesture recognition and suggest several improvements. We observe that raw depth images possess low contrast in the hand regions of interest (ROI). They do not highlight important fine details, such as finger orientation, overlap between the finger and palm, or overlap between multiple fingers. We thus propose quantizing the depth values into several discrete regions, to create a higher contrast between several key parts of the hand. In addition, we suggest several ways to tackle the high variance problem in existing multimodal fusion CRNN architectures. We evaluate our method on two benchmarks: the DHG-14/28 dataset and the SHREC'17 track dataset. Our approach shows a significant improvement in accuracy and parameter efficiency over previous similar multimodal methods, with a comparable result to the state-of-the-art.