Related papers: Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?

Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?

URL: http://arxiv.org/abs/2210.11628v1
Date: Thu, 20 Oct 2022 23:13:54 GMT
Title: Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?
Authors: Thuy-Trang Vu, Shahram Khadivi, Xuanli He, Dinh Phung and Gholamreza Haffari
Abstract summary: This paper investigates whether the domain information can be transferred across languages on the composition of multi-domain and multilingual NMT. We find that multi-domain multilingual (MDML) NMT can boost zero-shot translation performance up to +10 gains on BLEU.
Score: 52.27798071809941
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Abstract: Previous works mostly focus on either multilingual or multi-domain aspects of neural machine translation (NMT). This paper investigates whether the domain information can be transferred across languages on the composition of multi-domain and multilingual NMT, particularly for the incomplete data condition where in-domain bitext is missing for some language pairs. Our results in the curated leave-one-domain-out experiments show that multi-domain multilingual (MDML) NMT can boost zero-shot translation performance up to +10 gains on BLEU, as well as aid the generalisation of multi-domain NMT to the missing domain. We also explore strategies for effective integration of multilingual and multi-domain NMT, including language and domain tag combination and auxiliary task training. We find that learning domain-aware representations and adding target-language tags to the encoder leads to effective MDML-NMT.

Related papers

Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning [55.107329995417786]
Large language models (LLMs) have demonstrated impressive general understanding and generation abilities. We establish a benchmark for multi-domain translation, featuring 25 German$Leftrightarrow$English and 22 Chinese$Leftrightarrow$English test sets. We propose a domain Chain of Thought (CoT) fine-tuning technique that utilizes the intrinsic multi-domain intelligence of LLMs to improve translation performance.
arXiv Detail & Related papers (2024-10-03T16:15:04Z)
Defining Boundaries: The Impact of Domain Specification on Cross-Language and Cross-Domain Transfer in Machine Translation [0.44601285466405083]
Cross-lingual transfer learning offers a promising solution for neural machine translation (NMT) This paper focuses on the impact of domain specification and linguistic factors on transfer effectiveness. We evaluate multiple target languages, including Portuguese, Italian, French, Czech, Polish, and Greek.
arXiv Detail & Related papers (2024-08-21T18:28:48Z)
$m^4Adapter$: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter [128.69723410769586]
Multilingual neural machine translation models (MNMT) yield state-of-the-art performance when evaluated on data from a domain and language pair. When a MNMT model is used to translate under domain shift or to a new language pair, performance drops dramatically. We propose $m4Adapter$, which combines domain and language knowledge using meta-learning with adapters.
arXiv Detail & Related papers (2022-10-21T12:25:05Z)
Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters [66.7986513246294]
We study the compositionality of language and domain adapters in the context of Machine Translation. We find that in the partial resource scenario a naive combination of domain-specific and language-specific adapters often results in catastrophic forgetting' of the missing languages.
arXiv Detail & Related papers (2021-10-18T18:55:23Z)
Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection [34.90952499734384]
We propose a cross-lingual data selection method to extract in-domain sentences in the missing language side from a large generic monolingual corpus. Our proposed method trains an adaptive layer on top of multilingual BERT by contrastive learning to align the representation between the source and target language. We evaluate our cross-lingual data selection method on NMT across five diverse domains in three language pairs, as well as a real-world scenario of translation for COVID-19.
arXiv Detail & Related papers (2021-09-09T14:12:12Z)
AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT [9.797319790710711]
AUGVIC is a novel data augmentation framework for low-resource NMT. It exploits the vicinal samples of the given bitext without using any extra monolingual data explicitly. We show that AUGVIC helps to attenuate the discrepancies between relevant and distant-domain monolingual data in traditional back-translation.
arXiv Detail & Related papers (2021-06-09T15:29:18Z)
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking [66.76141128555099]
We propose a novel cross-lingual biomedical entity linking task (XL-BEL) We first investigate the ability of standard knowledge-agnostic as well as knowledge-enhanced monolingual and multilingual LMs beyond the standard monolingual English BEL task. We then address the challenge of transferring domain-specific knowledge in resource-rich languages to resource-poor ones.
arXiv Detail & Related papers (2021-05-30T00:50:00Z)
FDMT: A Benchmark Dataset for Fine-grained Domain Adaptation in Machine Translation [53.87731008029645]
We present a real-world fine-grained domain adaptation task in machine translation (FDMT) The FDMT dataset consists of four sub-domains of information technology: autonomous vehicles, AI education, real-time networks and smart phone. We make quantitative experiments and deep analyses in this new setting, which benchmarks the fine-grained domain adaptation task.
arXiv Detail & Related papers (2020-12-31T17:15:09Z)

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