Capturing document context inside sentence-level neural machine
translation models with self-training
- URL: http://arxiv.org/abs/2003.05259v1
- Date: Wed, 11 Mar 2020 12:36:17 GMT
- Title: Capturing document context inside sentence-level neural machine
translation models with self-training
- Authors: Elman Mansimov, G\'abor Melis, Lei Yu
- Abstract summary: Document-level neural machine translation has received less attention and lags behind its sentence-level counterpart.
We propose an approach that doesn't require training a specialized model on parallel document-level corpora.
Our approach reinforces the choices made by the model, thus making it more likely that the same choices will be made in other sentences in the document.
- Score: 5.129814362802968
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Neural machine translation (NMT) has arguably achieved human level parity
when trained and evaluated at the sentence-level. Document-level neural machine
translation has received less attention and lags behind its sentence-level
counterpart. The majority of the proposed document-level approaches investigate
ways of conditioning the model on several source or target sentences to capture
document context. These approaches require training a specialized NMT model
from scratch on parallel document-level corpora. We propose an approach that
doesn't require training a specialized model on parallel document-level corpora
and is applied to a trained sentence-level NMT model at decoding time. We
process the document from left to right multiple times and self-train the
sentence-level model on pairs of source sentences and generated translations.
Our approach reinforces the choices made by the model, thus making it more
likely that the same choices will be made in other sentences in the document.
We evaluate our approach on three document-level datasets: NIST
Chinese-English, WMT'19 Chinese-English and OpenSubtitles English-Russian. We
demonstrate that our approach has higher BLEU score and higher human preference
than the baseline. Qualitative analysis of our approach shows that choices made
by model are consistent across the document.
Related papers
- On Search Strategies for Document-Level Neural Machine Translation [51.359400776242786]
Document-level neural machine translation (NMT) models produce a more consistent output across a document.
In this work, we aim to answer the question how to best utilize a context-aware translation model in decoding.
arXiv Detail & Related papers (2023-06-08T11:30:43Z) - HanoiT: Enhancing Context-aware Translation via Selective Context [95.93730812799798]
Context-aware neural machine translation aims to use the document-level context to improve translation quality.
The irrelevant or trivial words may bring some noise and distract the model from learning the relationship between the current sentence and the auxiliary context.
We propose a novel end-to-end encoder-decoder model with a layer-wise selection mechanism to sift and refine the long document context.
arXiv Detail & Related papers (2023-01-17T12:07:13Z) - SMDT: Selective Memory-Augmented Neural Document Translation [53.4627288890316]
We propose a Selective Memory-augmented Neural Document Translation model to deal with documents containing large hypothesis space of context.
We retrieve similar bilingual sentence pairs from the training corpus to augment global context.
We extend the two-stream attention model with selective mechanism to capture local context and diverse global contexts.
arXiv Detail & Related papers (2022-01-05T14:23:30Z) - Divide and Rule: Training Context-Aware Multi-Encoder Translation Models
with Little Resources [20.057692375546356]
Multi-encoder models aim to improve translation quality by encoding document-level contextual information alongside the current sentence.
We show that training these parameters takes large amount of data, since the contextual training signal is sparse.
We propose an efficient alternative, based on splitting sentence pairs, that allows to enrich the training signal of a set of parallel sentences.
arXiv Detail & Related papers (2021-03-31T15:15:32Z) - Rethinking Document-level Neural Machine Translation [73.42052953710605]
We try to answer the question: Is the capacity of current models strong enough for document-level translation?
We observe that the original Transformer with appropriate training techniques can achieve strong results for document translation, even with a length of 2000 words.
arXiv Detail & Related papers (2020-10-18T11:18:29Z) - Learning Contextualized Sentence Representations for Document-Level
Neural Machine Translation [59.191079800436114]
Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence.
We propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence.
arXiv Detail & Related papers (2020-03-30T03:38:01Z) - Towards Making the Most of Context in Neural Machine Translation [112.9845226123306]
We argue that previous research did not make a clear use of the global context.
We propose a new document-level NMT framework that deliberately models the local context of each sentence.
arXiv Detail & Related papers (2020-02-19T03:30:00Z)
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.