Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTowards Modeling the Style of Translators in Neural Machine Translation
نحو نمذجة أسلوب المترجمين في الترجمة الآلية العصبية
331
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
عنصر رئيسي واحد من الترجمة الآلية العصبية هو استخدام مجموعات البيانات الكبيرة من المجالات والموارد المختلفة (E.G. Europarl، TED محادثات).تحتوي مجموعات البيانات هذه على مستندات مترجمة من قبل المترجمين المحترفين باستخدام أنماط الترجمة المختلفة ولكن ثابتة.على الرغم من ذلك، عادة ما يتم تدريب النموذج بطريقة لا يجسد صراحة مجموعة متنوعة من أنماط الترجمة الموجودة في البيانات ولا تترجم بيانات جديدة في أنماط مختلفة ويمكن التحكم فيها.في هذا العمل، نحقق في طرق زيادة حالة نموذج محول الفن مع معلومات المترجم المتوفرة جزئيا من بيانات التدريب.نظرا لأن نماذج الترجمة المعززة بأسلوبنا قادرة على التقاط الاختلافات النمط للمترجمين وإنشاء ترجمات مع أنماط مختلفة على البيانات الجديدة.في الواقع، تختلف الاختلافات التي تم إنشاؤها بشكل كبير، ما يصل إلى فرق النتيجة +4.5 بلو.على الرغم من ذلك، يؤكد التقييم البشري أن الترجمات من نفس النوعية.
One key ingredient of neural machine translation is the use of large datasets from different domains and resources (e.g. Europarl, TED talks). These datasets contain documents translated by professional translators using different but consistent translation styles. Despite that, the model is usually trained in a way that neither explicitly captures the variety of translation styles present in the data nor translates new data in different and controllable styles. In this work, we investigate methods to augment the state of the art Transformer model with translator information that is available in part of the training data. We show that our style-augmented translation models are able to capture the style variations of translators and to generate translations with different styles on new data. Indeed, the generated variations differ significantly, up to +4.5 BLEU score difference. Despite that, human evaluation confirms that the translations are of the same quality.
References used
https://aclanthology.org/
rate research
Read More
In this work, we study hallucinations in Neural Machine Translation (NMT), which lie at an extreme end on the spectrum of NMT pathologies. Firstly, we connect the phenomenon of hallucinations under source perturbation to the Long-Tail theory of Feldm
an, and present an empirically validated hypothesis that explains hallucinations under source perturbation. Secondly, we consider hallucinations under corpus-level noise (without any source perturbation) and demonstrate that two prominent types of natural hallucinations (detached and oscillatory outputs) could be generated and explained through specific corpus-level noise patterns. Finally, we elucidate the phenomenon of hallucination amplification in popular data-generation processes such as Backtranslation and sequence-level Knowledge Distillation. We have released the datasets and code to replicate our results.
We propose a straightforward vocabulary adaptation scheme to extend the language capacity of multilingual machine translation models, paving the way towards efficient continual learning for multilingual machine translation. Our approach is suitable f
or large-scale datasets, applies to distant languages with unseen scripts, incurs only minor degradation on the translation performance for the original language pairs and provides competitive performance even in the case where we only possess monolingual data for the new languages.
Terminological consistency is an essential requirement for industrial translation. High-quality, hand-crafted terminologies contain entries in their nominal forms. Integrating such a terminology into machine translation is not a trivial task. The MT
system must be able to disambiguate homographs on the source side and choose the correct wordform on the target side. In this work, we propose a simple but effective method for homograph disambiguation and a method of wordform selection by introducing multi-choice lexical constraints. We also propose a metric to measure the terminological consistency of the translation. Our results have a significant improvement over the current SOTA in terms of terminological consistency without any loss of the BLEU score. All the code used in this work will be published as open-source.
Many NLP models operate over sequences of subword tokens produced by hand-crafted tokenization rules and heuristic subword induction algorithms. A simple universal alternative is to represent every computerized text as a sequence of bytes via UTF-8,
obviating the need for an embedding layer since there are fewer token types (256) than dimensions. Surprisingly, replacing the ubiquitous embedding layer with one-hot representations of each byte does not hurt performance; experiments on byte-to-byte machine translation from English to 10 different languages show a consistent improvement in BLEU, rivaling character-level and even standard subword-level models. A deeper investigation reveals that the combination of embeddingless models with decoder-input dropout amounts to token dropout, which benefits byte-to-byte models in particular.
The paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language. In particular and we introduce a method and based on constrained decoding and which handles the inflected forms of lexical ent
ries and does not require any modification to the training data or model architecture. To evaluate its effectiveness and we carry out experiments in two different scenarios: general and domain-specific. We compare our method with baseline translation and i.e. translation without lexical constraints and in terms of translation speed and translation quality. To evaluate how well the method handles the constraints and we propose new evaluation metrics which take into account the presence and placement and duplication and inflectional correctness of lexical terms in the output sentence.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
