Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSometimes We Want Ungrammatical Translations
في بعض الأحيان نريد ترجمة غير تعليمية
240
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تركز التقدم السريع في أنظمة الترجمة الآلية العصبية على مدى السنوات القليلة الماضية بشكل أساسي على تحسين جودة الترجمة، وكتركيز ثانوي، وتحسين متانة للاضطرات (على سبيل المثال الإملاء). في حين أن الأداء والقوة هي أهداف مهمة، من خلال التركيز على هذه، فإننا نخاطر بتوقيف الخصائص المهمة الأخرى. في هذه الورقة، نلفت الانتباه إلى حقيقة أنه بالنسبة لبعض التطبيقات، فإن الإخلاص النص الأصلي (الإدخال) مهم للحفاظ عليه، حتى لو كان ذلك يعني إدخال أنماط لغة غير عادية في الترجمة (الإخراج). نقترح طريقة بسيطة رواية لتحديد ما إذا كان نظام NMT يعرض متزايدا أو إخلاصا، من خلال التركيز على حالة اضطراب ترتيب الكلمات. نستكشف مجموعة من الوظائف لإشراض ترتيب الكلمات من الجمل المصدر دون حذف أو حقن الرموز، وقياس آثارها على الجانب المستهدف. عبر العديد من الحالات التجريبية، نلاحظ ميلا قويا نحو متانة بدلا من الإخلاص. تتيح لنا هذه النتائج أن نفهم المفاضلة بشكل أفضل بين الإخلاص والمتانة في NMT، ويفتح إمكانية تطوير النظم التي يكون فيها المستخدمون لديهم المزيد من الحكم الذاتي والتحكم في اختيار العقار الأفضل من الأنسب لحالة استخدامها.
Rapid progress in Neural Machine Translation (NMT) systems over the last few years has focused primarily on improving translation quality, and as a secondary focus, improving robustness to perturbations (e.g. spelling). While performance and robustness are important objectives, by over-focusing on these, we risk overlooking other important properties. In this paper, we draw attention to the fact that for some applications, faithfulness to the original (input) text is important to preserve, even if it means introducing unusual language patterns in the (output) translation. We propose a simple, novel way to quantify whether an NMT system exhibits robustness or faithfulness, by focusing on the case of word-order perturbations. We explore a suite of functions to perturb the word order of source sentences without deleting or injecting tokens, and measure their effects on the target side. Across several experimental conditions, we observe a strong tendency towards robustness rather than faithfulness. These results allow us to better understand the trade-off between faithfulness and robustness in NMT, and opens up the possibility of developing systems where users have more autonomy and control in selecting which property is best suited for their use case.
References used
https://aclanthology.org/
rate research
Read More
Acquisition of multilingual training data continues to be a challenge in word sense disambiguation (WSD). To address this problem, unsupervised approaches have been proposed to automatically generate sense annotations for training supervised WSD syst
ems. We present three new methods for creating sense-annotated corpora which leverage translations, parallel bitexts, lexical resources, as well as contextual and synset embeddings. Our semi-supervised method applies machine translation to transfer existing sense annotations to other languages. Our two unsupervised methods refine sense annotations produced by a knowledge-based WSD system via lexical translations in a parallel corpus. We obtain state-of-the-art results on standard WSD benchmarks.
Understanding when a text snippet does not provide a sought after information is an essential part of natural language utnderstanding. Recent work (SQuAD 2.0; Rajpurkar et al., 2018) has attempted to make some progress in this direction by enriching
the SQuAD dataset for the Extractive QA task with unanswerable questions. However, as we show, the performance of a top system trained on SQuAD 2.0 drops considerably in out-of-domain scenarios, limiting its use in practical situations. In order to study this we build an out-of-domain corpus, focusing on simple event-based questions and distinguish between two types of IDK questions: competitive questions, where the context includes an entity of the same type as the expected answer, and simpler, non-competitive questions where there is no entity of the same type in the context. We find that SQuAD 2.0-based models fail even in the case of the simpler questions. We then analyze the similarities and differences between the IDK phenomenon in Extractive QA and the Recognizing Textual Entailments task (RTE; Dagan et al., 2013) and investigate the extent to which the latter can be used to improve the performance.
Most of the recent Natural Language Processing(NLP) studies are based on the Pretrain-Finetuning Approach (PFA), but in small and medium-sized enterprises or companies with insufficient hardware there are many limitations to servicing NLP application
software using such technology due to slow speed and insufficient memory. The latest PFA technologies require large amounts of data, especially for low-resource languages, making them much more difficult to work with. We propose a new tokenization method, ONE-Piece, to address this limitation that combines the morphology-considered subword tokenization method and the vocabulary method used after probing for an existing method that has not been carefully considered before. Our proposed method can also be used without modifying the model structure. We experiment by applying ONE-Piece to Korean, a morphologically-rich and low-resource language. We derive an optimal subword tokenization result for Korean-English machine translation by conducting a case study that combines the subword tokenization method, morphological segmentation, and vocabulary method. Through comparative experiments with all the tokenization methods currently used in NLP research, ONE-Piece achieves performance comparable to the current Korean-English machine translation state-of-the-art model.
Non-autoregressive Transformer is a promising text generation model. However, current non-autoregressive models still fall behind their autoregressive counterparts in translation quality. We attribute this accuracy gap to the lack of dependency model
ing among decoder inputs. In this paper, we propose CNAT, which learns implicitly categorical codes as latent variables into the non-autoregressive decoding. The interaction among these categorical codes remedies the missing dependencies and improves the model capacity. Experiment results show that our model achieves comparable or better performance in machine translation tasks than several strong baselines.
This paper describes the ESPnet-ST group's IWSLT 2021 submission in the offline speech translation track. This year we made various efforts on training data, architecture, and audio segmentation. On the data side, we investigated sequence-level knowl
edge distillation (SeqKD) for end-to-end (E2E) speech translation. Specifically, we used multi-referenced SeqKD from multiple teachers trained on different amounts of bitext. On the architecture side, we adopted the Conformer encoder and the Multi-Decoder architecture, which equips dedicated decoders for speech recognition and translation tasks in a unified encoder-decoder model and enables search in both source and target language spaces during inference. We also significantly improved audio segmentation by using the pyannote.audio toolkit and merging multiple short segments for long context modeling. Experimental evaluations showed that each of them contributed to large improvements in translation performance. Our best E2E system combined all the above techniques with model ensembling and achieved 31.4 BLEU on the 2-ref of tst2021 and 21.2 BLEU and 19.3 BLEU on the two single references of tst2021.
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
