Dipti Misra Sharma

Akshat Gahoi, Jayant Duneja, Anshul Padhi et al.

Code-mixed machine translation has become an important task in multilingual communities and extending the task of machine translation to code mixed data has become a common task for these languages. In the shared tasks of WMT 2022, we try to tackle the same for both English + Hindi to Hinglish and Hinglish to English. The first task dealt with both Roman and Devanagari script as we had monolingual data in both English and Hindi whereas the second task only had data in Roman script. To our knowledge, we achieved one of the top ROUGE-L and WER scores for the first task of Monolingual to Code-Mixed machine translation. In this paper, we discuss the use of mBART with some special pre-processing and post-processing (transliteration from Devanagari to Roman) for the first task in detail and the experiments that we performed for the second task of translating code-mixed Hinglish to monolingual English.

Vandan Mujadia, Ashok Urlana, Yash Bhaskar et al.

Generative Large Language Models (LLMs) have achieved remarkable advancements in various NLP tasks. In this work, our aim is to explore the multilingual capabilities of large language models by using machine translation as a task involving English and 22 Indian languages. We first investigate the translation capabilities of raw large language models, followed by exploring the in-context learning capabilities of the same raw models. We fine-tune these large language models using parameter efficient fine-tuning methods such as LoRA and additionally with full fine-tuning. Through our study, we have identified the best performing large language model for the translation task involving LLMs, which is based on LLaMA. Our results demonstrate significant progress, with average BLEU scores of 13.42, 15.93, 12.13, 12.30, and 12.07, as well as CHRF scores of 43.98, 46.99, 42.55, 42.42, and 45.39, respectively, using 2-stage fine-tuned LLaMA-13b for English to Indian languages on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest, and newstest2019 testsets. Similarly, for Indian languages to English, we achieved average BLEU scores of 14.03, 16.65, 16.17, 15.35 and 12.55 along with chrF scores of 36.71, 40.44, 40.26, 39.51, and 36.20, respectively, using fine-tuned LLaMA-13b on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest, and newstest2019 testsets. Overall, our findings highlight the potential and strength of large language models for machine translation capabilities, including for languages that are currently underrepresented in LLMs.

Pruthwik Mishra, Dipti Misra Sharma

Shallow parsing is an essential task for many NLP applications like machine translation, summarization, sentiment analysis, aspect identification and many more. Quality annotated corpora is critical for building accurate shallow parsers. Many Indian languages are resource poor with respect to the availability of corpora in general. So, this paper is an attempt towards creating quality corpora for shallow parsers. The contribution of this paper is two folds: creation pos and chunk annotated corpora for Odia and development of baseline systems for pos tagging and chunking in Odia.

Nikhilesh Bhatnagar, Ashok Urlana, Vandan Mujadia et al.

Cross-lingual summarization involves the summarization of text written in one language to a different one. There is a body of research addressing cross-lingual summarization from English to other European languages. In this work, we aim to perform cross-lingual summarization from English to Hindi. We propose pairing up the coverage of newsworthy events in textual and video format can prove to be helpful for data acquisition for cross lingual summarization. We analyze the data and propose methods to match articles to video descriptions that serve as document and summary pairs. We also outline filtering methods over reasonable thresholds to ensure the correctness of the summaries. Further, we make available 28,583 mono and cross-lingual article-summary pairs https://github.com/tingc9/Cross-Sum-News-Aligned. We also build and analyze multiple baselines on the collected data and report error analysis.

Sankalp Bahad, Pruthwik Mishra, Karunesh Arora et al.

Named Entity Recognition (NER) is a useful component in Natural Language Processing (NLP) applications. It is used in various tasks such as Machine Translation, Summarization, Information Retrieval, and Question-Answering systems. The research on NER is centered around English and some other major languages, whereas limited attention has been given to Indian languages. We analyze the challenges and propose techniques that can be tailored for Multilingual Named Entity Recognition for Indian Languages. We present a human annotated named entity corpora of 40K sentences for 4 Indian languages from two of the major Indian language families. Additionally,we present a multilingual model fine-tuned on our dataset, which achieves an F1 score of 0.80 on our dataset on average. We achieve comparable performance on completely unseen benchmark datasets for Indian languages which affirms the usability of our model.

Vandan Mujadia, Dipti Misra Sharma

This paper focuses on developing translation models and related applications for 36 Indian languages, including Assamese, Awadhi, Bengali, Bhojpuri, Braj, Bodo, Dogri, English, Konkani, Gondi, Gujarati, Hindi, Hinglish, Ho, Kannada, Kangri, Kashmiri (Arabic and Devanagari), Khasi, Mizo, Magahi, Maithili, Malayalam, Marathi, Manipuri (Bengali and Meitei), Nepali, Oriya, Punjabi, Sanskrit, Santali, Sinhala, Sindhi (Arabic and Devanagari), Tamil, Tulu, Telugu, and Urdu. Achieving this requires parallel and other types of corpora for all 36 * 36 language pairs, addressing challenges like script variations, phonetic differences, and syntactic diversity. For instance, languages like Kashmiri and Sindhi, which use multiple scripts, demand script normalization for alignment, while low-resource languages such as Khasi and Santali require synthetic data augmentation to ensure sufficient coverage and quality. To address these challenges, this work proposes strategies for corpus creation by leveraging existing resources, developing parallel datasets, generating domain-specific corpora, and utilizing synthetic data techniques. Additionally, it evaluates machine translation across various dimensions, including standard and discourse-level translation, domain-specific translation, reference-based and reference-free evaluation, error analysis, and automatic post-editing. By integrating these elements, the study establishes a comprehensive framework to improve machine translation quality and enable better cross-lingual communication in India's linguistically diverse ecosystem.

Vandan Mujadia, Pruthwik Mishra, Arafat Ahsan et al.

With the primary focus on evaluating the effectiveness of large language models for automatic reference-less translation assessment, this work presents our experiments on mimicking human direct assessment to evaluate the quality of translations in English and Indian languages. We constructed a translation evaluation task where we performed zero-shot learning, in-context example-driven learning, and fine-tuning of large language models to provide 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 considered Indian language pairs.

Arafat Ahsan, Vandan Mujadia, Pruthwik Mishra et al.

Automatic evaluation of translation remains a challenging task owing to the orthographic, morphological, syntactic and semantic richness and divergence observed across languages. String-based metrics such as BLEU have previously been extensively used for automatic evaluation tasks, but their limitations are now increasingly recognized. Although learned neural metrics have helped mitigate some of the limitations of string-based approaches, they remain constrained by a paucity of gold evaluation data in most languages beyond the usual high-resource pairs. In this present work we address some of these gaps. We create a large human evaluation ratings dataset for 13 Indian languages covering 21 translation directions and then train a neural translation evaluation metric named Cross-lingual Optimized Metric for Translation Assessment of Indian Languages (COMTAIL) on this dataset. The best performing metric variants show significant performance gains over previous state-of-the-art when adjudging translation pairs with at least one Indian language. Furthermore, we conduct a series of ablation studies to highlight the sensitivities of such a metric to changes in domain, translation quality, and language groupings. We release both the COMTAIL dataset and the accompanying metric models.

Saketh Reddy Vemula, Sandipan Dandapat, Dipti Misra Sharma et al.

The relationship between tokenizer algorithm (e.g., Byte-Pair Encoding (BPE), Unigram), morphological alignment, tokenization quality (e.g., compression efficiency), and downstream performance remains largely unclear, particularly for languages with complex morphology. In this paper, we conduct a comprehensive evaluation of tokenizers using small-sized BERT models -- from pre-training through fine-tuning -- for Telugu (agglutinative), along with preliminary evaluation in Hindi (primarily fusional with some agglutination) and English (fusional). To evaluate morphological alignment of tokenizers in Telugu, we create a dataset containing gold morpheme segmentations of 600 derivational and 7000 inflectional word forms. Our experiments reveal two key findings for Telugu. First, the choice of tokenizer algorithm is the most significant factor influencing performance, with Unigram-based tokenizers consistently outperforming BPE across most settings. Second, while better morphological alignment shows a moderate, positive correlation with performance on text classification and structure prediction tasks, its impact is secondary to the tokenizer algorithm. Notably, hybrid approaches that use morphological information for pre-segmentation significantly boost the performance of BPE, though not Unigram. Our results further showcase the need for comprehensive intrinsic evaluation metrics for tokenizers that could explain downstream performance trends consistently.

Harshita Sharma, Pruthwik Mishra, Dipti Misra Sharma

Word problem Solving is a challenging NLP task that deals with solving mathematical problems described in natural language. Recently, there has been renewed interest in developing word problem solvers for Indian languages. As part of this paper, we have built a Hindi arithmetic word problem solver which makes use of verbs. Additionally, we have created verb categorization data for Hindi. Verbs are very important for solving word problems with addition/subtraction operations as they help us identify the set of operations required to solve the word problems. We propose a rule-based solver that uses verb categorisation to identify operations in a word problem and generate answers for it. To perform verb categorisation, we explore several approaches and present a comparative study.

Arafat Ahsan, Vandan Mujadia, Dipti Misra Sharma

We present findings from a first in-depth post-editing effort estimation study in the English-Hindi direction along multiple effort indicators. We conduct a controlled experiment involving professional translators, who complete assigned tasks alternately, in a translation from scratch and a post-edit condition. We find that post-editing reduces translation time (by 63%), utilizes fewer keystrokes (by 59%), and decreases the number of pauses (by 63%) when compared to translating from scratch. We further verify the quality of translations thus produced via a human evaluation task in which we do not detect any discernible quality differences.

Saujas Vaduguru, Aalok Sathe, Monojit Choudhury et al.

Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples. In this paper, we ask: Can we learn explicit rules that generalize well from only a few examples? We explore this question using program synthesis. We develop a synthesis model to learn phonology rules as programs in a domain-specific language. We test the ability of our models to generalize from few training examples using our new dataset of problems from the Linguistics Olympiad, a challenging set of tasks that require strong linguistic reasoning ability. In addition to being highly sample-efficient, our approach generates human-readable programs, and allows control over the generalizability of the learnt programs.

Riyaz Ahmad Bhat, Irshad Ahmad Bhat, Dipti Misra Sharma

We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new dataset containing 506 dependency trees for sentences from Bollywood (Hindi) movie scripts and Twitter posts of Hindi monolingual speakers. We show that a dependency parser trained on a newswire treebank is strongly biased towards the canonical structures and degrades when applied to conversational data. Inspired by Transformational Generative Grammar, we mitigate the sampling bias by generating all theoretically possible alternative word orders of a clause from the existing (kernel) structures in the treebank. Training our parser on canonical and transformed structures improves performance on conversational data by around 9% LAS over the baseline newswire parser.

Ketan Kumar Todi, Pruthwik Mishra, Dipti Misra Sharma

POS Tagging serves as a preliminary task for many NLP applications. Kannada is a relatively poor Indian language with very limited number of quality NLP tools available for use. An accurate and reliable POS Tagger is essential for many NLP tasks like shallow parsing, dependency parsing, sentiment analysis, named entity recognition. We present a statistical POS tagger for Kannada using different machine learning and neural network models. Our Kannada POS tagger outperforms the state-of-the-art Kannada POS tagger by 6%. Our contribution in this paper is three folds - building a generic POS Tagger, comparing the performances of different modeling techniques, exploring the use of character and word embeddings together for Kannada POS Tagging.

Pruthwik Mishra, Litton J Kurisinkel, Dipti Misra Sharma

Automatic Word problem solving has always posed a great challenge for the NLP community. Usually a word problem is a narrative comprising of a few sentences and a question is asked about a quantity referred in the sentences. Solving word problem involves reasoning across sentences, identification of operations, their order, relevant quantities and discarding irrelevant quantities. In this paper, we present a novel approach for automatic arithmetic word problem solving. Our approach starts with frame identification. Each frame can either be classified as a state or an action frame. The frame identification is dependent on the verb in a sentence. Every frame is unique and is identified by its slots. The slots are filled using dependency parsed output of a sentence. The slots are entity holder, entity, quantity of the entity, recipient, additional information like place, time. The slots and frames helps to identify the type of question asked and the entity referred. Action frames act on state frame(s) which causes a change in quantities of the state frames. The frames are then used to build a graph where any change in quantities can be propagated to the neighboring nodes. Most of the current solvers can only answer questions related to the quantity, while our system can answer different kinds of questions like `who', `what' other than the quantity related questions `how many'. There are three major contributions of this paper. 1. Frame Annotated Corpus (with a frame annotation tool) 2. Frame Identification Module 3. A new easily understandable Framework for word problem solving

Irshad Ahmad Bhat, Riyaz Ahmad Bhat, Manish Shrivastava et al.

Code-switching is a phenomenon of mixing grammatical structures of two or more languages under varied social constraints. The code-switching data differ so radically from the benchmark corpora used in NLP community that the application of standard technologies to these data degrades their performance sharply. Unlike standard corpora, these data often need to go through additional processes such as language identification, normalization and/or back-transliteration for their efficient processing. In this paper, we investigate these indispensable processes and other problems associated with syntactic parsing of code-switching data and propose methods to mitigate their effects. In particular, we study dependency parsing of code-switching data of Hindi and English multilingual speakers from Twitter. We present a treebank of Hindi-English code-switching tweets under Universal Dependencies scheme and propose a neural stacking model for parsing that efficiently leverages part-of-speech tag and syntactic tree annotations in the code-switching treebank and the preexisting Hindi and English treebanks. We also present normalization and back-transliteration models with a decoding process tailored for code-switching data. Results show that our neural stacking parser is 1.5% LAS points better than the augmented parsing model and our decoding process improves results by 3.8% LAS points over the first-best normalization and/or back-transliteration.

Irshad Ahmad Bhat, Riyaz Ahmad Bhat, Manish Shrivastava et al.

In this paper, we propose efficient and less resource-intensive strategies for parsing of code-mixed data. These strategies are not constrained by in-domain annotations, rather they leverage pre-existing monolingual annotated resources for training. We show that these methods can produce significantly better results as compared to an informed baseline. Besides, we also present a data set of 450 Hindi and English code-mixed tweets of Hindi multilingual speakers for evaluation. The data set is manually annotated with Universal Dependencies.