paper-with-me

Papers

The Effect of Alignment Objectives on Code-Switching Translation

2023-09-10 · Mohamed Anwar

One of the things that need to change when it comes to machine translation is the models' ability to translate code-switching content, especially with the rise of social media and user-generated content. In this paper, we are proposing a way of training a single machine translation model that is able to translate monolingual sentences from one language to another, along with translating code-switched sentences to either language. This model can be considered a bilingual model in the human sense. For better use of parallel data, we generated synthetic code-switched (CSW) data along with an alignment loss on the encoder to align representations across languages. Using the WMT14 English-French (En-Fr) dataset, the trained model strongly outperforms bidirectional baselines on code-switched translation while maintaining quality for non-code-switched (monolingual) data.

📄 PDF Abstract BibTeX arXiv:2309.05044

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling

2025-05-19 · Aditeya Baral, Allen George Ajith, Roshan Nayak, Mrityunjay Abhijeet Bhanja

Code-mixed languages, characterized by frequent within-sentence language transitions, present structural challenges that standard language models fail to address. In this work, we propose CMLFormer, an enhanced multi-lay…

DecoderLanguage ModelingLanguage ModellingSentence

Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs

2025-10-07 · Haneul Yoo, Jiho Jin, Kyunghyun Cho, Alice Oh arxiv

While large language models (LLMs) have achieved notable progress in multilingual settings, their performance remains uneven across languages as LLMs often rely on English-centric latent representations. In this work, we…

Cross-Lingual Transfer

CSP:Code-Switching Pre-training for Neural Machine Translation

2020-11-01 · EMNLP 2020 11 · Zhen Yang, Bojie Hu, Ambyera Han, Shen Huang 외

This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP for short) for Neural Machine Translation (NMT). Unlike traditional pre-training method which randomly masks some fragments of the in…

DecoderMachine TranslationNMTSentence+1

Code-switching pre-training for neural machine translation

2020-09-17 · Zhen Yang, Bojie Hu, Ambyera Han, Shen Huang 외

This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP for short) for Neural Machine Translation (NMT). Unlike traditional pre-training method which randomly masks some fragments of the in…

DecoderMachine TranslationNMTSentence+1

IITP-MT at CALCS2021: English to Hinglish Neural Machine Translation using Unsupervised Synthetic Code-Mixed Parallel Corpus

2021-06-01 · NAACL (CALCS) 2021 6 · Ramakrishna Appicharla, Kamal Kumar Gupta, Asif Ekbal, Pushpak Bhattacharyya

This paper describes the system submitted by IITP-MT team to Computational Approaches to Linguistic Code-Switching (CALCS 2021) shared task on MT for English→Hinglish. We submit a neural machine translation (NMT) system …

Machine TranslationNMTTranslation