Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNoisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models
الترجمة UGC صاخبة على مستوى الطابع: إعادة النظر في قدرات المفردات المفتوحة وأغاني النماذج المستندة إلى Char
341
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يستكشف هذا العمل قدرات الترجمة الآلية العصبية القائمة على الأحرف لترجمة المحتوى الناتج عن المستخدم الصاخب (UGC) مع التركيز القوي على استكشاف حدود هذه الأساليب للتعامل مع ظواهر UGC الإنتاجية، والتي بحكم تعريفها تقريبا، لا يمكن رؤيتها في وقت التدريبوبعدضمن سيناريو صاروخي صاروخي بالرصاص، نقوم أولا بدراسة التأثير الضار على أداء الترجمة من مختلف ظواهر المحتوى التي تم إنشاؤها من قبل المستخدم على مجموعة بيانات صغيرة مشروحة، وظهرت بعد ذلك أن هذه النماذج غير قادرة بالفعل على التعامل مع الحروف غير المعروفة، مما يؤدي إلى ترجمة كارثيةالفشل بمجرد مواجهة هذه الشخصيات.نحن نؤكد مزيدا من السلوك بتجربة مهمة بسيطة ولكنها ثاقبة وتسليط الضوء على أهمية تقليل حجم المفردات Hyper-Parameter لزيادة متانة النماذج القائمة على الأحرف للترجمة الآلية.
This work explores the capacities of character-based Neural Machine Translation to translate noisy User-Generated Content (UGC) with a strong focus on exploring the limits of such approaches to handle productive UGC phenomena, which almost by definition, cannot be seen at training time. Within a strict zero-shot scenario, we first study the detrimental impact on translation performance of various user-generated content phenomena on a small annotated dataset we developed and then show that such models are indeed incapable of handling unknown letters, which leads to catastrophic translation failure once such characters are encountered. We further confirm this behavior with a simple, yet insightful, copy task experiment and highlight the importance of reducing the vocabulary size hyper-parameter to increase the robustness of character-based models for machine translation.
References used
https://aclanthology.org/
rate research
Read More
Paraphrases refer to texts that convey the same meaning with different expression forms. Pivot-based methods, also known as the round-trip translation, have shown promising results in generating high-quality paraphrases. However, existing pivot-based
methods all rely on language as the pivot, where large-scale, high-quality parallel bilingual texts are required. In this paper, we explore the feasibility of using semantic and syntactic representations as the pivot for paraphrase generation. Concretely, we transform a sentence into a variety of different semantic or syntactic representations (including AMR, UD, and latent semantic representation), and then decode the sentence back from the semantic representations. We further explore a pretraining-based approach to compress the pipeline process into an end-to-end framework. We conduct experiments comparing different approaches with different kinds of pivots. Experimental results show that taking AMR as pivot can obtain paraphrases with better quality than taking language as the pivot. The end-to-end framework can reduce semantic shift when language is used as the pivot. Besides, several unsupervised pivot-based methods can generate paraphrases with similar quality as the supervised sequence-to-sequence model, which indicates that parallel data of paraphrases may not be necessary for paraphrase generation.
This work takes a critical look at the evaluation of user-generated content automatic translation, the well-known specificities of which raise many challenges for MT. Our analyses show that measuring the average-case performance using a standard metr
ic on a UGC test set falls far short of giving a reliable image of the UGC translation quality. That is why we introduce a new data set for the evaluation of UGC translation in which UGC specificities have been manually annotated using a fine-grained typology. Using this data set, we conduct several experiments to measure the impact of different kinds of UGC specificities on translation quality, more precisely than previously possible.
Policy gradient algorithms have found wide adoption in NLP, but have recently become subject to criticism, doubting their suitability for NMT. Choshen et al. (2020) identify multiple weaknesses and suspect that their success is determined by the shap
e of output distributions rather than the reward. In this paper, we revisit these claims and study them under a wider range of configurations. Our experiments on in-domain and cross-domain adaptation reveal the importance of exploration and reward scaling, and provide empirical counter-evidence to these claims.
When building machine translation systems, one often needs to make the best out of heterogeneous sets of parallel data in training, and to robustly handle inputs from unexpected domains in testing. This multi-domain scenario has attracted a lot of re
cent work that fall under the general umbrella of transfer learning. In this study, we revisit multi-domain machine translation, with the aim to formulate the motivations for developing such systems and the associated expectations with respect to performance. Our experiments with a large sample of multi-domain systems show that most of these expectations are hardly met and suggest that further work is needed to better analyze the current behaviour of multi-domain systems and to make them fully hold their promises.
Recent progress in language modeling has been driven not only by advances in neural architectures, but also through hardware and optimization improvements. In this paper, we revisit the neural probabilistic language model (NPLM) of Bengio et al. (200
3), which simply concatenates word embeddings within a fixed window and passes the result through a feed-forward network to predict the next word. When scaled up to modern hardware, this model (despite its many limitations) performs much better than expected on word-level language model benchmarks. Our analysis reveals that the NPLM achieves lower perplexity than a baseline Transformer with short input contexts but struggles to handle long-term dependencies. Inspired by this result, we modify the Transformer by replacing its first self-attention layer with the NPLM's local concatenation layer, which results in small but consistent perplexity decreases across three word-level language modeling datasets.
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
