Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDon't Go Far Off: An Empirical Study on Neural Poetry Translation
لا تذهب بعيدا: دراسة تجريبية عن الترجمة العصبية
381
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
على الرغم من التحسينات المستمرة في جودة الترجمة الآلية، تظل الترجمة التلقائية الشعر مشكلة صعبة بسبب عدم وجود شاعرية موازية مفتوحة، وبالنسبة إلى التعقيدات الجوهرية المعنية في الحفاظ على الدلالات والأناقة والطبيعة المجازية للشعر. نقدم إجراءات تجريبية لترجمة الشعر على طول عدة أبعاد: 1) حجم وأسلوب بيانات التدريب (Poetic vs. غير شعري)، بما في ذلك إعداد الصفر بالرصاص؛ 2) ثنائي اللغة مقابل التعلم متعدد اللغات؛ و 3) نماذج لغة خاصة للعائلة مقابل نماذج عائلية مختلطة. لإنجاز ذلك، نساهم في مجموعة بيانات متوازية من ترجمات الشعر لعدة أزواج اللغة. تبين نتائجنا أن ضبط التركيب المتعدد اللغات على النص الشعري يتفوق بشكل كبير على النص المتعدد اللغوي على النص غير الشعري الذي هو 35X أكبر في الحجم، كلاهما من حيث المقاييس التلقائية (BLEU، Bertscore، المذنب) ومقاييس التقييم البشري مثل الإخلاص ( معنى والأناقة الشعرية). علاوة على ذلك، فإن ضبط التردد متعدد اللغات على البيانات الشعرية تتفوق على ضبط ثنائي اللغة على البيانات الشعرية.
Despite constant improvements in machine translation quality, automatic poetry translation remains a challenging problem due to the lack of open-sourced parallel poetic corpora, and to the intrinsic complexities involved in preserving the semantics, style and figurative nature of poetry. We present an empirical investigation for poetry translation along several dimensions: 1) size and style of training data (poetic vs. non-poetic), including a zero-shot setup; 2) bilingual vs. multilingual learning; and 3) language-family-specific models vs. mixed-language-family models. To accomplish this, we contribute a parallel dataset of poetry translations for several language pairs. Our results show that multilingual fine-tuning on poetic text significantly outperforms multilingual fine-tuning on non-poetic text that is 35X larger in size, both in terms of automatic metrics (BLEU, BERTScore, COMET) and human evaluation metrics such as faithfulness (meaning and poetic style). Moreover, multilingual fine-tuning on poetic data outperforms bilingual fine-tuning on poetic data.
References used
https://aclanthology.org/
rate research
Read More
Recent years have seen a flourishing of neural keyphrase generation (KPG) works, including the release of several large-scale datasets and a host of new models to tackle them. Model performance on KPG tasks has increased significantly with evolving d
eep learning research. However, there lacks a comprehensive comparison among different model designs, and a thorough investigation on related factors that may affect a KPG system's generalization performance. In this empirical study, we aim to fill this gap by providing extensive experimental results and analyzing the most crucial factors impacting the generalizability of KPG models. We hope this study can help clarify some of the uncertainties surrounding the KPG task and facilitate future research on this topic.
Sequential information, a.k.a., orders, is assumed to be essential for processing a sequence with recurrent neural network or convolutional neural network based encoders. However, is it possible to encode natural languages without orders? Given a bag
of words from a disordered sentence, humans may still be able to understand what those words mean by reordering or reconstructing them. Inspired by such an intuition, in this paper, we perform a study to investigate how order'' information takes effects in natural language learning. By running comprehensive comparisons, we quantitatively compare the ability of several representative neural models to organize sentences from a bag of words under three typical scenarios, and summarize some empirical findings and challenges, which can shed light on future research on this line of work.
In simultaneous machine translation, finding an agent with the optimal action sequence of reads and writes that maintain a high level of translation quality while minimizing the average lag in producing target tokens remains an extremely challenging
problem. We propose a novel supervised learning approach for training an agent that can detect the minimum number of reads required for generating each target token by comparing simultaneous translations against full-sentence translations during training to generate oracle action sequences. These oracle sequences can then be used to train a supervised model for action generation at inference time. Our approach provides an alternative to current heuristic methods in simultaneous translation by introducing a new training objective, which is easier to train than previous attempts at training the agent using reinforcement learning techniques for this task. Our experimental results show that our novel training method for action generation produces much higher quality translations while minimizing the average lag in simultaneous translation.
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
