Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSyntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data
إعادة صياغة غير مخالفة غير مستنيرة مع البيانات غير الموازية
312
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعمل السابقة على جيل إعادة صياغة صياغة يتم التحكم فيها بشكل كبير على بيانات إعادة صياغة مباشرة على نطاق واسع غير متوفرة بسهولة للعديد من اللغات والمجالات. في هذه الورقة، نأخذ هذا الاتجاه البحثي إلى أقصى الحدود والتحقيق فيما إذا كان من الممكن تعلم توليد الصياغة التي يتم التحكم فيها بموجبها مع بيانات غير صلبية. نقترح نموذج إعادة صياغة غير مدهش من غير المستنير عليه بناء على التشفير التلقائي الشرطي (VAE) يمكن أن تولد نصوص في بنية نصنية محددة. خاصة، نقوم بتصميم طريقة تعليمية من مرحلتين لتدريب النموذج بفعالية باستخدام البيانات غير الموازية. يتم تدريب VAE الشرطية على إعادة بناء جملة الإدخال وفقا للإدخال المحدد والهيكل النحامي. علاوة على ذلك، لتحسين قابلية التحكم في النحوية والاتساق الدلالي لشركة VAE الشرطية المدربة مسبقا، نحن نغتنمها باستخدام أهداف التعلم السيطرة على بناء الجملة وإعادة إعمار دورة إعادة إعمار، وتوظيف Gumbel-Softmax الجمع بين أهداف التعلم الجديدة هذه. توضح نتائج التجربة أن النموذج المقترح المدرب فقط على البيانات غير الموازية قادر على توليد صیر متنوعة مع بنية نصنية محددة. بالإضافة إلى ذلك، نحن نقوم بالتحقق من صحة فعالية طريقتنا لتوليد أمثلة خصومة النحوية على مهمة تحليل المعنويات.
Previous works on syntactically controlled paraphrase generation heavily rely on large-scale parallel paraphrase data that is not easily available for many languages and domains. In this paper, we take this research direction to the extreme and investigate whether it is possible to learn syntactically controlled paraphrase generation with nonparallel data. We propose a syntactically-informed unsupervised paraphrasing model based on conditional variational auto-encoder (VAE) which can generate texts in a specified syntactic structure. Particularly, we design a two-stage learning method to effectively train the model using non-parallel data. The conditional VAE is trained to reconstruct the input sentence according to the given input and its syntactic structure. Furthermore, to improve the syntactic controllability and semantic consistency of the pre-trained conditional VAE, we fine-tune it using syntax controlling and cycle reconstruction learning objectives, and employ Gumbel-Softmax to combine these new learning objectives. Experiment results demonstrate that the proposed model trained only on non-parallel data is capable of generating diverse paraphrases with specified syntactic structure. Additionally, we validate the effectiveness of our method for generating syntactically adversarial examples on the sentiment analysis task.
References used
https://aclanthology.org/
rate research
Read More
Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of labeled d
ata that is costly to collect. To address this drawback, we adopt a transfer learning approach and propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking (DB). To enforce a surface form dissimilar from the input, whenever the language model emits a token contained in the source sequence, DB prevents the model from outputting the subsequent source token for the next generation step. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair (QQP) and the ParaNMT datasets and is robust to domain shift between the two datasets of distinct distributions. We also demonstrate that our model transfers to paraphrasing in other languages without any additional finetuning.
The quality and quantity of parallel sentences are known as very important training data for constructing neural machine translation (NMT) systems. However, these resources are not available for many low-resource language pairs. Many existing methods
need strong supervision are not suitable. Although several attempts at developing unsupervised models, they ignore the language-invariant between languages. In this paper, we propose an approach based on transfer learning to mine parallel sentences in the unsupervised setting.With the help of bilingual corpora of rich-resource language pairs, we can mine parallel sentences without bilingual supervision of low-resource language pairs. Experiments show that our approach improves the performance of mined parallel sentences compared with previous methods. In particular, we achieve excellent results at two real-world low-resource language pairs.
We present a novel technique for zero-shot paraphrase generation. The key contribution is an end-to-end multilingual paraphrasing model that is trained using translated parallel corpora to generate paraphrases into meaning spaces'' -- replacing the f
inal softmax layer with word embeddings. This architectural modification, plus a training procedure that incorporates an autoencoding objective, enables effective parameter sharing across languages for more fluent monolingual rewriting, and facilitates fluency and diversity in the generated outputs. Our continuous-output paraphrase generation models outperform zero-shot paraphrasing baselines when evaluated on two languages using a battery of computational metrics as well as in human assessment.
Unsupervised Data Augmentation (UDA) is a semisupervised technique that applies a consistency loss to penalize differences between a model's predictions on (a) observed (unlabeled) examples; and (b) corresponding noised' examples produced via data au
gmentation. While UDA has gained popularity for text classification, open questions linger over which design decisions are necessary and how to extend the method to sequence labeling tasks. In this paper, we re-examine UDA and demonstrate its efficacy on several sequential tasks. Our main contribution is an empirical study of UDA to establish which components of the algorithm confer benefits in NLP. Notably, although prior work has emphasized the use of clever augmentation techniques including back-translation, we find that enforcing consistency between predictions assigned to observed and randomly substituted words often yields comparable (or greater) benefits compared to these more complex perturbation models. Furthermore, we find that applying UDA's consistency loss affords meaningful gains without any unlabeled data at all, i.e., in a standard supervised setting. In short, UDA need not be unsupervised to realize much of its noted benefits, and does not require complex data augmentation to be effective.
Unsupervised consistency training is a way of semi-supervised learning that encourages consistency in model predictions between the original and augmented data. For Named Entity Recognition (NER), existing approaches augment the input sequence with t
oken replacement, assuming annotations on the replaced positions unchanged. In this paper, we explore the use of paraphrasing as a more principled data augmentation scheme for NER unsupervised consistency training. Specifically, we convert Conditional Random Field (CRF) into a multi-label classification module and encourage consistency on the entity appearance between the original and paraphrased sequences. Experiments show that our method is especially effective when annotations are limited.
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
