Atul Kr. Ojha

Mohit Raj, Shyam Ratan, Deepak Alok et al.

In this paper, we discuss the development of treebanks for two low-resourced Indian languages - Magahi and Braj based on the Universal Dependencies framework. The Magahi treebank contains 945 sentences and Braj treebank around 500 sentences marked with their lemmas, part-of-speech, morphological features and universal dependencies. This paper gives a description of the different dependency relationship found in the two languages and give some statistics of the two treebanks. The dataset will be made publicly available on Universal Dependency (UD) repository (https://github.com/UniversalDependencies/UD_Magahi-MGTB/tree/master) in the next(v2.10) release.

Ritesh Kumar, Siddharth Singh, Shyam Ratan et al.

In this paper we discuss an in-progress work on the development of a speech corpus for four low-resource Indo-Aryan languages -- Awadhi, Bhojpuri, Braj and Magahi using the field methods of linguistic data collection. The total size of the corpus currently stands at approximately 18 hours (approx. 4-5 hours each language) and it is transcribed and annotated with grammatical information such as part-of-speech tags, morphological features and Universal dependency relationships. We discuss our methodology for data collection in these languages, most of which was done in the middle of the COVID-19 pandemic, with one of the aims being to generate some additional income for low-income groups speaking these languages. In the paper, we also discuss the results of the baseline experiments for automatic speech recognition system in these languages.

Shantipriya Parida, Kalyanamalini Sahoo, Atul Kr. Ojha et al.

This paper presents the first publicly available treebank of Odia, a morphologically rich low resource Indian language. The treebank contains approx. 1082 tokens (100 sentences) in Odia selected from "Samantar", the largest available parallel corpora collection for Indic languages. All the selected sentences are manually annotated following the ``Universal Dependency (UD)" guidelines. The morphological analysis of the Odia treebank was performed using machine learning techniques. The Odia annotated treebank will enrich the Odia language resource and will help in building language technology tools for cross-lingual learning and typological research. We also build a preliminary Odia parser using a machine learning approach. The accuracy of the parser is 86.6% Tokenization, 64.1% UPOS, 63.78% XPOS, 42.04% UAS and 21.34% LAS. Finally, the paper briefly discusses the linguistic analysis of the Odia UD treebank.

Ritesh Kumar, Atul Kr. Ojha, Bornini Lahiri et al.

In the present paper, we will present the results of an acoustic analysis of political discourse in Hindi and discuss some of the conventionalised acoustic features of aggressive speech regularly employed by the speakers of Hindi and English. The study is based on a corpus of slightly over 10 hours of political discourse and includes debates on news channel and political speeches. Using this study, we develop two automatic classification systems for identifying aggression in English and Hindi speech, based solely on an acoustic model. The Hindi classifier, trained using 50 hours of annotated speech, and English classifier, trained using 40 hours of annotated speech, achieve a respectable accuracy of over 73% and 66% respectively. In this paper, we discuss the development of this annotated dataset, the experiments for developing the classifier and discuss the errors that it makes.

Ibrahim Said Ahmad, Antonios Anastasopoulos, Ondřej Bojar et al.

This paper reports on the shared tasks organized by the 21st IWSLT Conference. The shared tasks address 7 scientific challenges in spoken language translation: simultaneous and offline translation, automatic subtitling and dubbing, speech-to-speech translation, dialect and low-resource speech translation, and Indic languages. The shared tasks attracted 18 teams whose submissions are documented in 26 system papers. The growing interest towards spoken language translation is also witnessed by the constantly increasing number of shared task organizers and contributors to the overview paper, almost evenly distributed across industry and academia.

Sourabrata Mukherjee, Akanksha Bansal, Atul Kr. Ojha et al.

This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where the text style changes while its content is preserved. We present three approaches: knowledge transfer from a similar task, multi-task learning approach, combining sequence-to-sequence modeling with various toxicity classification tasks, and delete and reconstruct approach. To support our research, we utilize a dataset provided by Dementieva et al.(2021), which contains multiple versions of detoxified texts corresponding to toxic texts. In our experiments, we selected the best variants through expert human annotators, creating a dataset where each toxic sentence is paired with a single, appropriate detoxified version. Additionally, we introduced a small Hindi parallel dataset, aligning with a part of the English dataset, suitable for evaluation purposes. Our results demonstrate that our approach effectively balances text detoxication while preserving the actual content and maintaining fluency.

David Ifeoluwa Adelani, A. Seza Doğruöz, André Coneglian et al.

Large Language Models are transforming NLP for a variety of tasks. However, how LLMs perform NLP tasks for low-resource languages (LRLs) is less explored. In line with the goals of the AmericasNLP workshop, we focus on 12 LRLs from Brazil, 2 LRLs from Africa and 2 high-resource languages (HRLs) (e.g., English and Brazilian Portuguese). Our results indicate that the LLMs perform worse for the part of speech (POS) labeling of LRLs in comparison to HRLs. We explain the reasons behind this failure and provide an error analysis through examples observed in our data set.

Sourabrata Mukherjee, Atul Kr. Ojha, John P. McCrae et al.

Text style transfer (TST) is the task of transforming a text to reflect a particular style while preserving its original content. Evaluating TST outputs is a multidimensional challenge, requiring the assessment of style transfer accuracy, content preservation, and naturalness. Using human evaluation is ideal but costly, as is common in other natural language processing (NLP) tasks, however, automatic metrics for TST have not received as much attention as metrics for, e.g., machine translation or summarization. In this paper, we examine both set of existing and novel metrics from broader NLP tasks for TST evaluation, focusing on two popular subtasks, sentiment transfer and detoxification, in a multilingual context comprising English, Hindi, and Bengali. By conducting meta-evaluation through correlation with human judgments, we demonstrate the effectiveness of these metrics when used individually and in ensembles. Additionally, we investigate the potential of large language models (LLMs) as tools for TST evaluation. Our findings highlight newly applied advanced NLP metrics and LLM-based evaluations provide better insights than existing TST metrics. Our oracle ensemble approaches show even more potential.

Gaurav Negi, Atul Kr. Ojha, Omnia Zayed et al.

We propose a scalable method for constructing a temporal opinion knowledge base with large language models (LLMs) as automated annotators. Despite the demonstrated utility of time-series opinion analysis of text for downstream applications such as forecasting and trend analysis, existing methodologies underexploit this potential due to the absence of temporally grounded fine-grained annotations. Our approach addresses this gap by integrating well-established opinion mining formulations into a declarative LLM annotation pipeline, enabling structured opinion extraction without manual prompt engineering. We define three data models grounded in sentiment and opinion mining literature, serving as schemas for structured representation. We perform rigorous quantitative evaluation of our pipeline using human-annotated test samples. We carry out the final annotations using two separate LLMs, and inter-annotator agreement is computed label-wise across the fine-grained opinion dimensions, analogous to human annotation protocols. The resulting knowledge base encapsulates time-aligned, structured opinions and is compatible with applications in Retrieval-Augmented Generation (RAG), temporal question answering, and timeline summarisation.

Sourabrata Mukherjee, Atul Kr. Ojha, Ondřej Dušek

We analyze the performance of large language models (LLMs) on Text Style Transfer (TST), specifically focusing on sentiment transfer and text detoxification across three languages: English, Hindi, and Bengali. Text Style Transfer involves modifying the linguistic style of a text while preserving its core content. We evaluate the capabilities of pre-trained LLMs using zero-shot and few-shot prompting as well as parameter-efficient finetuning on publicly available datasets. Our evaluation using automatic metrics, GPT-4 and human evaluations reveals that while some prompted LLMs perform well in English, their performance in on other languages (Hindi, Bengali) remains average. However, finetuning significantly improves results compared to zero-shot and few-shot prompting, making them comparable to previous state-of-the-art. This underscores the necessity of dedicated datasets and specialized models for effective TST.

Swapnil Fadte, Edna Vaz, Atul Kr. Ojha et al.

Konkani is a highly nasalised language which makes it unique among Indo-Aryan languages. This work investigates the acoustic-phonetic properties of Konkani oral and nasal vowels. For this study, speech samples from six speakers (3 male and 3 female) were collected. A total of 74 unique sentences were used as a part of the recording script, 37 each for oral and nasal vowels, respectively. The final data set consisted of 1135 vowel phonemes. A comparative F1-F2 plot of Konkani oral and nasal vowels is presented with an experimental result and formant analysis. The average F1, F2 and F3 values are also reported for the first time through experimentation for all nasal and oral vowels. This study can be helpful for the linguistic research on vowels and speech synthesis systems specific to the Konkani language.

Esha Banerjee, Atul Kr. Ojha, Girish Nath Jha

This study aims to develop a semi-automatically labelled prosody database for Hindi, for enhancing the intonation component in ASR and TTS systems, which is also helpful for building Speech to Speech Machine Translation systems. Although no single standard for prosody labelling exists in Hindi, researchers in the past have employed perceptual and statistical methods in literature to draw inferences about the behaviour of prosody patterns in Hindi. Based on such existing research and largely agreed upon theories of intonation in Hindi, this study attempts to first develop a manually annotated prosodic corpus of Hindi speech data, which is then used for training prediction models for generating automatic prosodic labels. A total of 5,000 sentences (23,500 words) for declarative and interrogative types have been labelled. The accuracy of the trained models for pitch accent, intermediate phrase boundaries and accentual phrase boundaries is 73.40%, 93.20%, and 43% respectively.

Atul Kr. Ojha, Chao-Hong Liu, Katharina Kann et al.

We present the findings of the LoResMT 2021 shared task which focuses on machine translation (MT) of COVID-19 data for both low-resource spoken and sign languages. The organization of this task was conducted as part of the fourth workshop on technologies for machine translation of low resource languages (LoResMT). Parallel corpora is presented and publicly available which includes the following directions: English$\leftrightarrow$Irish, English$\leftrightarrow$Marathi, and Taiwanese Sign language$\leftrightarrow$Traditional Chinese. Training data consists of 8112, 20933 and 128608 segments, respectively. There are additional monolingual data sets for Marathi and English that consist of 21901 segments. The results presented here are based on entries from a total of eight teams. Three teams submitted systems for English$\leftrightarrow$Irish while five teams submitted systems for English$\leftrightarrow$Marathi. Unfortunately, there were no systems submissions for the Taiwanese Sign language$\leftrightarrow$Traditional Chinese task. Maximum system performance was computed using BLEU and follow as 36.0 for English--Irish, 34.6 for Irish--English, 24.2 for English--Marathi, and 31.3 for Marathi--English.

Shiladitya Bhattacharya, Siddharth Singh, Ritesh Kumar et al.

In this paper, we discuss the development of a multilingual annotated corpus of misogyny and aggression in Indian English, Hindi, and Indian Bangla as part of a project on studying and automatically identifying misogyny and communalism on social media (the ComMA Project). The dataset is collected from comments on YouTube videos and currently contains a total of over 20,000 comments. The comments are annotated at two levels - aggression (overtly aggressive, covertly aggressive, and non-aggressive) and misogyny (gendered and non-gendered). We describe the process of data collection, the tagset used for annotation, and issues and challenges faced during the process of annotation. Finally, we discuss the results of the baseline experiments conducted to develop a classifier for misogyny in the three languages.

Atul Kr. Ojha

This thesis has been divided into six chapters namely: Introduction, Karaka Model and it impacts on Dependency Parsing, LT Resources for Bhojpuri, English-Bhojpuri SMT System: Experiment, Evaluation of EB-SMT System, and Conclusion. Chapter one introduces this PhD research by detailing the motivation of the study, the methodology used for the study and the literature review of the existing MT related work in Indian Languages. Chapter two talks of the theoretical background of Karaka and Karaka model. Along with this, it talks about previous related work. It also discusses the impacts of the Karaka model in NLP and dependency parsing. It compares Karaka dependency and Universal Dependency. It also presents a brief idea of the implementation of these models in the SMT system for English-Bhojpuri language pair.

Atul Kr. Ojha, Koel Dutta Chowdhury, Chao-Hong Liu et al.

This paper presents the system description of Machine Translation (MT) system(s) for Indic Languages Multilingual Task for the 2018 edition of the WAT Shared Task. In our experiments, we (the RGNLP team) explore both statistical and neural methods across all language pairs. (We further present an extensive comparison of language-related problems for both the approaches in the context of low-resourced settings.) Our PBSMT models were highest score on all automatic evaluation metrics in the English into Telugu, Hindi, Bengali, Tamil portion of the shared task.

Rajneesh Pandey, Atul Kr. Ojha, Girish Nath Jha

The demo proposal presents a Phrase-based Sanskrit-Hindi (SaHiT) Statistical Machine Translation system. The system has been developed on Moses. 43k sentences of Sanskrit-Hindi parallel corpus and 56k sentences of a monolingual corpus in the target language (Hindi) have been used. This system gives 57 BLEU score.

Priya Rani, Atul Kr. Ojha, Girish Nath Jha

Language identification has become a prerequisite for all kinds of automated text processing systems. In this paper, we present a rule-based language identifier tool for two closely related Indo-Aryan languages: Hindi and Magahi. This system has currently achieved an accuracy of approx 86.34%. We hope to improve this in the future. Automatic identification of languages will be significant in the accuracy of output of Web Crawlers.

Ritesh Kumar, Bornini Lahiri, Deepak Alok et al.

In this paper, we discuss an attempt to develop an automatic language identification system for 5 closely-related Indo-Aryan languages of India, Awadhi, Bhojpuri, Braj, Hindi and Magahi. We have compiled a comparable corpora of varying length for these languages from various resources. We discuss the method of creation of these corpora in detail. Using these corpora, a language identification system was developed, which currently gives state of the art accuracy of 96.48\%. We also used these corpora to study the similarity between the 5 languages at the lexical level, which is the first data-based study of the extent of closeness of these languages.