Mitodru Niyogi

Mitodru Niyogi, Arnab Bhattacharya

In this paper, we study whether domain specific pretraining of small generative language models (SLM) from scratch with domain specialized tokenizer and Chain-of-Thought (CoT) instruction fine-tuning results in competitive performance on mathematical reasoning compared to LLMs? Secondly, whether this approach is environmentally sustainable, highly cost efficient? To address these research questions, we present Paramanu-Ganita, a 208 million-parameter novel decoder-only Auto Regressive SLM on mathematics. We performed pretraining from scratch on 31.5 billion tokens for 170 A100 hours using a context size of 4096 on a mixed mathematical corpus consisting of web pages, source code, textbooks, CoT templatised StackOverflow QA pairs, and mathematical lecture notes in LaTeX curated by us. We also trained a math and code specialised BPE tokenizer. We proposed and performed CoT instruction fine-tuning of Paramanu-Ganita on the MetaMathQA dataset. Our model Paramanu-Ganita, despite being 34 times smaller than the 7B LLMs, outperforms generalist LLMs by approximately 30% points, and even math-specialised LLMs by 3-23% points in GSM8K test accuracy metric. On MATH benchmark, Paramanu-Ganita outperformed the various models by 6-8% points. On benchmarks like LogiQA, MMLU (high school, college level), and competitive exams level, AGIEVAL (AQuA-RAT, SAT-Math), Paramanu-Ganita outperformed others by 1-4%. Our model is available at https://huggingface.co/gyanai/paramanu-ganita-208M-hf .

Mitodru Niyogi, Arnab Bhattacharya

We present "Paramanu", a family of novel language models (LM) for Indian languages, consisting of auto-regressive monolingual, bilingual, and multilingual models pretrained from scratch. Currently, it covers 10 languages (Assamese, Bangla, Hindi, Konkani, Maithili, Marathi, Odia, Sanskrit, Tamil, Telugu) across 5 scripts (Bangla, Devanagari, Odia, Tamil, Telugu). The models are pretrained on a single GPU with context size of 1024 and vary in size from 13.29 million (M) to 367.5 M parameters. We proposed a RoPE embedding scaling method that enables us to pretrain language models from scratch at larger sequence length context size than typical GPU memory permits. We also introduced a novel efficient Indic tokenizer, "mBharat", using a combination of BPE and Unigram, achieving the least fertility score and the ability to tokenize unseen languages in both the same script & Roman script. We also proposed and performed language-specific tokenization for multilingual models & domain-specific tokenization for monolingual models. To address the "curse of multilinguality" in our mParamanu model, we pretrained on comparable corpora based on typological grouping within the same script. Our findings show a language transfer phenomenon from low-resource to high-resource languages within languages of the same script & typology. Human evaluations for open-ended text generation demonstrated that Paramanu models outperformed several LLMs, despite being 20 to 64 times smaller. We created instruction-tuning datasets & instruction-tuned our models on 23,000 instructions in respective languages. Comparisons with multilingual LLMs across various benchmarks for natural language (NL) understanding, NL inference, & reading comprehension highlight the advantages of our models; leads to the conclusion that high quality generative LM are possible without high amount of compute power & enormous number of parameters.

Mitodru Niyogi, Arnab Bhattacharya

In this paper, we present Paramanu-Ayn, a collection of legal language models trained exclusively on Indian legal case documents. This 97-million-parameter Auto-Regressive (AR) decoder-only model was pretrained from scratch with a context size of 8192 on a single GPU for just 185 hours, achieving an efficient MFU of 41.35. We also developed a legal domain specialized BPE tokenizer. We evaluated our model using perplexity and zero-shot tasks: case judgment prediction with explanation and abstractive case summarization. Paramanu-Ayn outperformed Llama-2 7B and Gemini-Pro in case judgment prediction with explanation task on test accuracy by nearly 2 percentage points, despite being 72 times smaller. In zero-shot abstractive summarization, it surpassed decoder-only LLMs generating fixed-length summaries (5000 tokens) by over 10 percentage points in BLEU and METEOR metrics, and by nearly 4 percentage points in BERTScore. Further evaluations on zero-shot commonsense and mathematical benchmarks showed that Paramanu-Ayn excelled despite being trained exclusively on legal documents, outperforming Llama-1, Llama-2, and Falcon on AGIEVAL-AQuA-RAT and AGIEVAL-SAT-Math tasks. We also instruction-tuned our model on 10,763 diverse legal tasks, including legal clause generation, legal drafting, case summarization, etc. The Paramanu-Ayn-instruct model scored above 8 out of 10 in clarity, relevance, completeness, and legal reasoning metrics by GPT-3.5-Turbo. We found that our models, were able to learn drafting knowledge and generalize to draft legal contracts and legal clauses with limited instruction-tuning. Hence, we conclude that for a strong domain-specialized generative language model (such as legal), domain specialized pretraining from scratch is more cost effective, environmentally friendly, and remains competitive with larger models or even better than adapting LLMs for legal domain tasks.

Mitodru Niyogi

Natural language (NL) to code suggestion systems assist developers in Integrated Development Environments (IDEs) by translating NL utterances into compilable code snippet. The current approaches mainly involve hard-coded, rule-based systems based on semantic parsing. These systems make heavy use of hand-crafted rules that map patterns in NL or elements in its syntax parse tree to various query constructs and can only work on a limited subset of NL with a restricted NL syntax. These systems are unable to extract semantic information from the coding intents of the developer, and often fail to infer types, names, and the context of the source code to get accurate system-level code suggestions. In this master thesis, we present sequence-to-sequence deep learning models and training paradigms to map NL to general-purpose programming languages that can assist users with suggestions of source code snippets, given a NL intent, and also extend auto-completion functionality of the source code to users while they are writing source code. The developed architecture incorporates contextual awareness into neural models which generate source code tokens directly instead of generating parse trees/abstract meaning representations from the source code and converting them back to source code. The proposed pretraining strategy and the data augmentation techniques improve the performance of the proposed architecture. The proposed architecture has been found to exceed the performance of a neural semantic parser, TranX, based on the BLEU-4 metric by 10.82%. Thereafter, a finer analysis for the parsable code translations from the NL intent for CoNaLA challenge was introduced. The proposed system is bidirectional as it can be also used to generate NL code documentation given source code. Lastly, a RoBERTa masked language model for Python was proposed to extend the developed system for code completion.

Mitodru Niyogi, Kripabandhu Ghosh, Arnab Bhattacharya

Cross-lingual information retrieval is a challenging task in the absence of aligned parallel corpora. In this paper, we address this problem by considering topically aligned corpora designed for evaluating an IR setup. To emphasize, we neither use any sentence-aligned corpora or document-aligned corpora, nor do we use any language specific resources such as dictionary, thesaurus, or grammar rules. Instead, we use an embedding into a common space and learn word correspondences directly from there. We test our proposed approach for bilingual IR on standard FIRE datasets for Bangla, Hindi and English. The proposed method is superior to the state-of-the-art method not only for IR evaluation measures but also in terms of time requirements. We extend our method successfully to the trilingual setting.

Mitodru Niyogi, Asim K. Pal

Social media platforms contain great wealth of information which provides us opportunities explore hidden patterns or unknown correlations, and understand people's satisfaction with what they are discussing. As one showcase, in this paper, we summarize the data set of Twitter messages related to recent demonetization of all Rs. 500 and Rs. 1000 notes in India and explore insights from Twitter's data. Our proposed system automatically extracts the popular latent topics in conversations regarding demonetization discussed in Twitter via the Latent Dirichlet Allocation (LDA) based topic model and also identifies the correlated topics across different categories. Additionally, it also discovers people's opinions expressed through their tweets related to the event under consideration via the emotion analyzer. The system also employs an intuitive and informative visualization to show the uncovered insight. Furthermore, we use an evaluation measure, Normalized Mutual Information (NMI), to select the best LDA models. The obtained LDA results show that the tool can be effectively used to extract discussion topics and summarize them for further manual analysis.