Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning and Analyzing Generation Order for Undirected Sequence Models
تعلم وتحليل ترتيب الجيل لنماذج التسلسل غير المعروض
290
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
حققت نماذج التسلسل العصبي غير المعروضة أداء تنافسية مع نماذج التسلسل الموجهة للحكومة الموجهة التي تولد رتيبا من اليسار إلى اليمين في مهام الترجمة الآلية. في هذا العمل، ندرب السياسة التي تتعلم طلب الجيل لنموذج الترجمة المدربة مسبقا مسبقا، عبر التعلم التعزيز. نظا على أن الترجمات التي تركتها أوامرنا المستفادة تحقق درجات بلو أعلى من النواتج المشفرة من اليسار إلى اليمين أو فك شفرة من قبل النظام المستفيد من منصيموف وآخرون. (2019) على مهمة الترجمة الألمانية والإنجليزية WMT'14. فيما يتعلق بالأمثلة بأقصى قدر من المصدر والمستهدف لمدة 30 من المهام الإنجليزية من DE-en و WMT'16 الإنجليزية الرومانية، فإن أمرنا المستفيد يتفوق على جميع أوامر الجيل المجهرية على ثلاثة من أربع أزواج لغوية. نقوم بالتحليل بعناية أنماط الطلب المستفادة من خلال التحليل النوعي والكمي. نظهر أن سياستنا تتبع عموما طلبا خارجيا إلى داخلي، توقع أكثر الأيسر والأيمن - معظم المناصب أولا، ثم تتحرك نحو المنتصف أثناء تخطي الكلمات الأقل أهمية في البداية. علاوة على ذلك، فإن السياسة تتوقع عادة مواقع لهيكل مؤسس بنزلي واحد في خطوات متتالية. نعتقد أن نتائجنا قد توفر المزيد من الأفكار حول آلية نماذج الجيل غير المعردة وتشجيع المزيد من البحث في هذا الاتجاه.
Undirected neural sequence models have achieved performance competitive with the state-of-the-art directed sequence models that generate monotonically from left to right in machine translation tasks. In this work, we train a policy that learns the generation order for a pre-trained, undirected translation model via reinforcement learning. We show that the translations decoded by our learned orders achieve higher BLEU scores than the outputs decoded from left to right or decoded by the learned order from Mansimov et al. (2019) on the WMT'14 German-English translation task. On examples with a maximum source and target length of 30 from De-En and WMT'16 English-Romanian tasks, our learned order outperforms all heuristic generation orders on three out of four language pairs. We next carefully analyze the learned order patterns via qualitative and quantitative analysis. We show that our policy generally follows an outer-to-inner order, predicting the left-most and right-most positions first, and then moving toward the middle while skipping less important words at the beginning. Furthermore, the policy usually predicts positions for a single syntactic constituent structure in consecutive steps. We believe our findings could provide more insights on the mechanism of undirected generation models and encourage further research in this direction.
References used
https://aclanthology.org/
rate research
Read More
Natural language (NL) explanations of model predictions are gaining popularity as a means to understand and verify decisions made by large black-box pre-trained models, for tasks such as Question Answering (QA) and Fact Verification. Recently, pre-tr
ained sequence to sequence (seq2seq) models have proven to be very effective in jointly making predictions, as well as generating NL explanations. However, these models have many shortcomings; they can fabricate explanations even for incorrect predictions, they are difficult to adapt to long input documents, and their training requires a large amount of labeled data. In this paper, we develop FiD-Ex, which addresses these shortcomings for seq2seq models by: 1) introducing sentence markers to eliminate explanation fabrication by encouraging extractive generation, 2) using the fusion-in-decoder architecture to handle long input contexts, and 3) intermediate fine-tuning on re-structured open domain QA datasets to improve few-shot performance. FiD-Ex significantly improves over prior work in terms of explanation metrics and task accuracy on five tasks from the ERASER explainability benchmark in both fully supervised and few-shot settings.
Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models. However,cascaded models are known to be prone to error propagation and model discrepancy problems. Furthermore, there is no p
ossibility of using end-to-end training data in conventional cascaded systems, meaning that the training data most suited for the task cannot be used.Previous studies suggested several approaches for integrated end-to-end training to overcome those problems, however they mostly rely on(synthetic or natural) three-way data. We propose a cascaded model based on the non-autoregressive Transformer that enables end-to-end training without the need for an explicit intermediate representation. This new architecture (i) avoids unnecessary early decisions that can cause errors which are then propagated throughout the cascaded models and (ii) utilizes the end-to-end training data directly. We conduct an evaluation on two pivot-based machine translation tasks, namely French→German and German→Czech. Our experimental results show that the proposed architecture yields an improvement of more than 2 BLEU for French→German over the cascaded baseline.
Variational autoencoders (VAEs) are widely used for latent variable modeling of text. We focus on variations that learn expressive prior distributions over the latent variable. We find that existing training strategies are not effective for learning
rich priors, so we propose adding the importance-sampled log marginal likelihood as a second term to the standard VAE objective to help when learning the prior. Doing so improves results for all priors evaluated, including a novel choice for sentence VAEs based on normalizing flows (NF). Priors parameterized with NF are no longer constrained to a specific distribution family, allowing a more flexible way to encode the data distribution. Our model, which we call FlowPrior, shows a substantial improvement in language modeling tasks compared to strong baselines. We demonstrate that FlowPrior learns an expressive prior with analysis and several forms of evaluation involving generation.
Paraphrase generation is a longstanding NLP task that has diverse applications on downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised endeavors have be
en proposed to alleviate this issue, they may fail to generate meaningful paraphrases due to the lack of supervision signals. In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with data of weak supervision. Specifically, we tackle the weakly-supervised paraphrase generation problem by: (1) obtaining abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion; and (2) developing a meta-learning framework to progressively select valuable samples for fine-tuning a pre-trained language model BART on the sentential paraphrasing task. We demonstrate that our approach achieves significant improvements over existing unsupervised approaches, and is even comparable in performance with supervised state-of-the-arts.
Robust sequence-to-sequence modelling is an essential task in the real world where the inputs are often noisy. Both user-generated and machine generated inputs contain various kinds of noises in the form of spelling mistakes, grammatical errors, char
acter recognition errors, all of which impact downstream tasks and affect interpretability of texts. In this work, we devise a novel sequence-to-sequence architecture for detecting and correcting different real world and artificial noises (adversarial attacks) from English texts. Towards that we propose a modified Transformer-based encoder-decoder architecture that uses a gating mechanism to detect types of corrections required and accordingly corrects texts. Experimental results show that our gated architecture with pre-trained language models perform significantly better that the non-gated counterparts and other state-of-the-art error correction models in correcting spelling and grammatical errors. Extrinsic evaluation of our model on Machine Translation (MT) and Summarization tasks show the competitive performance of the model against other generative sequence-to-sequence models under noisy inputs.
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
