Revisiting CNN for Highly Inflected Bengali and Hindi Language Modeling

• URL: http://arxiv.org/abs/2110.13032v1
• Date: Mon, 25 Oct 2021 15:14:42 GMT
• Title: Revisiting CNN for Highly Inflected Bengali and Hindi Language Modeling
• Authors: Chowdhury Rafeed Rahman, MD. Hasibur Rahman, Mohammad Rafsan, Samiha Zakir, Mohammed Eunus Ali, Rafsanjani Muhammod
• Abstract summary: We propose an end to end trainable memory efficient CNN architecture named CoCNN to handle specific characteristics. In particular, we introduce two learnable convolutional sub-models at word and at sentence level that are end to end trainable. We show that state-of-the-art (SOTA) Transformer models including pretrained BERT do not necessarily yield the best performance for Bengali and Hindi.
• Score: 0.5382679710017696
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Though there has been a large body of recent works in language modeling (LM) for high resource languages such as English and Chinese, the area is still unexplored for low resource languages like Bengali and Hindi. We propose an end to end trainable memory efficient CNN architecture named CoCNN to handle specific characteristics such as high inflection, morphological richness, flexible word order and phonetical spelling errors of Bengali and Hindi. In particular, we introduce two learnable convolutional sub-models at word and at sentence level that are end to end trainable. We show that state-of-the-art (SOTA) Transformer models including pretrained BERT do not necessarily yield the best performance for Bengali and Hindi. CoCNN outperforms pretrained BERT with 16X less parameters, and it achieves much better performance than SOTA LSTM models on multiple real-world datasets. This is the first study on the effectiveness of different architectures drawn from three deep learning paradigms - Convolution, Recurrent, and Transformer neural nets for modeling two widely used languages, Bengali and Hindi.

Related papers

• mmBERT: A Modern Multilingual Encoder with Annealed Language Learning [57.58071656545661]
  mmBERT is an encoder-only language model pretrained on 3T tokens of multilingual text.<n>We add over 1700 low-resource languages to the data mix only during the decay phase.<n>We show that mmBERT significantly outperforms the previous generation of models on classification and retrieval tasks.
  arXiv  Detail & Related papers  (2025-09-08T17:08:42Z)
• HindiLLM: Large Language Model for Hindi [0.09363323206192666]
  We have pre-trained two autoregressive Large Language Model (LLM) models for the Hindi language. We use a two-step process comprising unsupervised pre-training and supervised fine-tuning. The evaluation shows that the HindiLLM-based fine-tuned models outperform several models in most of the language related tasks.
  arXiv  Detail & Related papers  (2024-12-29T05:28:15Z)
• YAYI 2: Multilingual Open-Source Large Language Models [53.92832054643197]
  We propose YAYI 2, including both base and chat models, with 30 billion parameters. YAYI 2 is pre-trained from scratch on a multilingual corpus which contains 2.65 trillion tokens filtered by our pre-training data processing pipeline. The base model is aligned with human values through supervised fine-tuning with millions of instructions and reinforcement learning from human feedback.
  arXiv  Detail & Related papers  (2023-12-22T17:34:47Z)
• Continual Learning in Multilingual NMT via Language-Specific Embeddings [92.91823064720232]
  It consists in replacing the shared vocabulary with a small language-specific vocabulary and fine-tuning the new embeddings on the new language's parallel data. Because the parameters of the original model are not modified, its performance on the initial languages does not degrade.
  arXiv  Detail & Related papers  (2021-10-20T10:38:57Z)
• Cross-lingual Transferring of Pre-trained Contextualized Language Models [73.97131976850424]
  We propose a novel cross-lingual model transferring framework for PrLMs: TreLM. To handle the symbol order and sequence length differences between languages, we propose an intermediate TRILayer" structure. We show the proposed framework significantly outperforms language models trained from scratch with limited data in both performance and efficiency.
  arXiv  Detail & Related papers  (2021-07-27T06:51:13Z)
• Neural Models for Offensive Language Detection [0.0]
  Offensive language detection is an ever-growing natural language processing (NLP) application. We believe contributing to improving and comparing different machine learning models to fight such harmful contents is an important and challenging goal for this thesis.
  arXiv  Detail & Related papers  (2021-05-30T13:02:45Z)
• Paraphrastic Representations at Scale [134.41025103489224]
  We release trained models for English, Arabic, German, French, Spanish, Russian, Turkish, and Chinese languages. We train these models on large amounts of data, achieving significantly improved performance from the original papers.
  arXiv  Detail & Related papers  (2021-04-30T16:55:28Z)
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
  Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages. We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
  arXiv  Detail & Related papers  (2020-12-31T11:37:28Z)
• Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages [0.8155575318208631]
  Language models based on the Transformer architecture have achieved state-of-the-art performance on a wide range of NLP tasks. However, this performance is usually tested and reported on high-resource languages, like English, French, Spanish, and German. Indian languages, on the other hand, are underrepresented in such benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T14:43:43Z)
• Towards Fully Bilingual Deep Language Modeling [1.3455090151301572]
  We consider whether it is possible to pre-train a bilingual model for two remotely related languages without compromising performance at either language. We create a Finnish-English bilingual BERT model and evaluate its performance on datasets used to evaluate the corresponding monolingual models. Our bilingual model performs on par with Google's original English BERT on GLUE and nearly matches the performance of monolingual Finnish BERT on a range of Finnish NLP tasks.
  arXiv  Detail & Related papers  (2020-10-22T12:22:50Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)
• ParsBERT: Transformer-based Model for Persian Language Understanding [0.7646713951724012]
  This paper proposes a monolingual BERT for the Persian language (ParsBERT) It shows its state-of-the-art performance compared to other architectures and multilingual models. ParsBERT obtains higher scores in all datasets, including existing ones as well as composed ones.
  arXiv  Detail & Related papers  (2020-05-26T05:05:32Z)
• A Continuous Space Neural Language Model for Bengali Language [0.4799822253865053]
  This paper proposes a continuous-space neural language model, or more specifically an ASGD weight dropped LSTM language model, along with techniques to efficiently train it for Bengali Language. The proposed architecture outperforms its counterparts by achieving an inference perplexity as low as 51.2 on the held out data set for Bengali.
  arXiv  Detail & Related papers  (2020-01-11T14:50:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.