中文
相关论文

相关论文: Synthetic Data for Neural Machine Translation of S…

200 篇论文

This work aims to produce translations that convey source language content at a formality level that is appropriate for a particular audience. Framing this problem as a neural sequence-to-sequence task ideally requires training triplets…

计算与语言 · 计算机科学 2019-12-02 Xing Niu , Marine Carpuat

Simultaneous speech translation (SimulST) translates partial speech inputs incrementally. Although the monotonic correspondence between input and output is preferable for smaller latency, it is not the case for distant language pairs such…

计算与语言 · 计算机科学 2023-06-16 Yuka Ko , Ryo Fukuda , Yuta Nishikawa , Yasumasa Kano , Katsuhito Sudoh , Satoshi Nakamura

While prior work has established that the use of parallel data is conducive for cross-lingual learning, it is unclear if the improvements come from the data itself, or if it is the modeling of parallel interactions that matters. Exploring…

计算与语言 · 计算机科学 2022-12-21 Machel Reid , Mikel Artetxe

In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs. There have been several proposals to alleviate this issue…

计算与语言 · 计算机科学 2018-02-27 Mikel Artetxe , Gorka Labaka , Eneko Agirre , Kyunghyun Cho

We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover new languages by adapting…

计算与语言 · 计算机科学 2018-11-06 Surafel M. Lakew , Aliia Erofeeva , Matteo Negri , Marcello Federico , Marco Turchi

To support machine learning of cross-language prosodic mappings and other ways to improve speech-to-speech translation, we present a protocol for collecting closely matched pairs of utterances across languages, a description of the…

计算与语言 · 计算机科学 2023-07-17 Nigel G. Ward , Jonathan E. Avila , Emilia Rivas , Divette Marco

Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation. Combining backtranslated data from different sources has led to better results…

计算与语言 · 计算机科学 2020-05-04 Xabier Soto , Dimitar Shterionov , Alberto Poncelas , Andy Way

In machine translation, we often try to collect resources to improve performance. However, most of the language pairs, such as Korean-Arabic and Korean-Vietnamese, do not have enough resources to train machine translation systems. In this…

计算与语言 · 计算机科学 2018-02-15 Gyu-Hyeon Choi , Jong-Hun Shin , Young-Kil Kim

Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…

音频与语音处理 · 电气工程与系统科学 2025-09-01 Yanis Perrin , Gilles Boulianne

In this paper, we use the framework of neural machine translation to learn joint sentence representations across six very different languages. Our aim is that a representation which is independent of the language, is likely to capture the…

计算与语言 · 计算机科学 2017-08-09 Holger Schwenk , Matthijs Douze

Standard context-aware neural machine translation (NMT) typically relies on parallel document-level data, exploiting both source and target contexts. Concatenation-based approaches in particular, still a strong baseline for document-level…

计算与语言 · 计算机科学 2024-02-12 Harritxu Gete , Thierry Etchegoyhen

In this paper, we explore the possibility of speech synthesis from low quality found data using only limited number of samples of target speaker. We try to extract only the speaker embedding from found data of target speaker unlike previous…

音频与语音处理 · 电气工程与系统科学 2020-06-15 Sunghee Jung , Hoirin Kim

The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This has resulted a formidable challenge for the computational…

计算与语言 · 计算机科学 2024-05-01 Kartik Kartik , Sanjana Soni , Anoop Kunchukuttan , Tanmoy Chakraborty , Md Shad Akhtar

Multilingual semantic parsing is a cost-effective method that allows a single model to understand different languages. However, researchers face a great imbalance of availability of training data, with English being resource rich, and other…

计算与语言 · 计算机科学 2021-06-15 Menglin Xia , Emilio Monti

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…

计算与语言 · 计算机科学 2014-04-21 Karl Moritz Hermann , Phil Blunsom

Despite recent advances in large language models, building dependable and deployable NLP models typically requires abundant, high-quality training data. However, task-specific data is not available for many use cases, and manually curating…

计算与语言 · 计算机科学 2024-04-30 Saumya Gandhi , Ritu Gala , Vijay Viswanathan , Tongshuang Wu , Graham Neubig

Statistical machine translation models have made great progress in improving the translation quality. However, the existing models predict the target translation with only the source- and target-side local context information. In practice,…

计算与语言 · 计算机科学 2015-03-02 Jiajun Zhang

The use of synthetic speech as data augmentation is gaining increasing popularity in fields such as automatic speech recognition and speech classification tasks. Despite novel text-to-speech systems with voice cloning capabilities, that…

声音 · 计算机科学 2024-09-20 Sebastião Quintas , Isabelle Ferrané , Thomas Pellegrini

Cross-lingual transfer is an effective way to build syntactic analysis tools in low-resource languages. However, transfer is difficult when transferring to typologically distant languages, especially when neither annotated target data nor…

计算与语言 · 计算机科学 2021-04-30 Junxian He , Zhisong Zhang , Taylor Berg-Kirkpatrick , Graham Neubig

Neural machine translation (NMT) becomes a new state-of-the-art and achieves promising translation results using a simple encoder-decoder neural network. This neural network is trained once on the parallel corpus and the fixed network is…

计算与语言 · 计算机科学 2016-09-22 Xiaoqing Li , Jiajun Zhang , Chengqing Zong