تستفيد نماذج اللغة الكبيرة من التدريب بكمية كبيرة من النص غير المسبق، مما يمنحهم قدرات توليد بطلاقة ومتنوعة بشكل متزايد.ومع ذلك، فإن استخدام هذه النماذج لتوليد النص الذي يأخذ في الاعتبار السمات المستهدفة، مثل قطبية المعالم أو مواضيع محددة، لا يزال يمثل تحديا.نقترح طريقة بسيطة ومرنة للسيطرة على جيل النص عن طريق محاذاة تمثيلات سمة Deventangled.على النقيض من الجهود الأخيرة التي يبذلها الجهود المبينة في تدريب تمييزي على توزيع مستوى الرمز المميز لسمة، نستخدم نفس البيانات لتعلم وظيفة المحاذاة لتوجيه نموذج اللغة غير المستخدمة مسبقا وغير الخاضعة للرقابة لإنشاء نصوص مع سمة الهدف دون تغييرالمعلمات نموذج اللغة الأصلية.نقوم بتقييم طريقتنا على توليد المعنويات والموضوع، وإظهار مكاسب أداء كبيرة على الطرق السابقة مع الاحتفاظ بالطلاقة والتنوع.
Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities. However, using these models for text generation that takes into account target attributes, such as sentiment polarity or specific topics, remains a challenge. We propose a simple and flexible method for controlling text generation by aligning disentangled attribute representations. In contrast to recent efforts on training a discriminator to perturb the token level distribution for an attribute, we use the same data to learn an alignment function to guide the pre-trained, non-controlled language model to generate texts with the target attribute without changing the original language model parameters. We evaluate our method on sentiment- and topic-controlled generation, and show large performance gains over previous methods while retaining fluency and diversity.
References used
https://aclanthology.org/
In this study, we propose a self-supervised learning method that distils representations of word meaning in context from a pre-trained masked language model. Word representations are the basis for context-aware lexical semantics and unsupervised sema
Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words i
Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent long passag
As it has been unveiled that pre-trained language models (PLMs) are to some extent capable of recognizing syntactic concepts in natural language, much effort has been made to develop a method for extracting complete (binary) parses from PLMs without
Pretrained language models (PTLMs) yield state-of-the-art performance on many natural language processing tasks, including syntax, semantics and commonsense. In this paper, we focus on identifying to what extent do PTLMs capture semantic attributes a