Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models
ugpt: المهام المساعدة وتعزيز البيانات لحوار نهاية إلى نهاية مع نماذج اللغة المدربة مسبقا
285
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أثارت نماذج اللغة المدربة مسبقا مقرها الانتباه مثل GPT-2 تقدما كبيرا لنمذجة حوار نهاية إلى نهاية.ومع ذلك، فإنهم يقدمون أيضا مخاطر كبيرة للحوار الموجهة إلى المهام، مثل عدم وجود أسس المعرفة أو التنوع.لمعالجة هذه القضايا، نقدم أهداف تدريبية معدلة لنموذج اللغة Finetuning، ونحن نوظف تكبير بيانات ضخمة عبر الترجمة الخلفي لزيادة تنوع بيانات التدريب.ندرس إمكانيات الجمع بين البيانات من مصادر مضاعفات تحسين الأداء على مجموعة البيانات المستهدفة.نحن نقيم بعناية مساهماتنا مع كل من الأساليب البشرية والآلية.يتفوق نموذجنا بشكل كبير على خط الأساس على بيانات MultiWoz ويظهر أداء تنافسي مع حالة الفن في كل من التقييم التلقائي والإنساني.
Attention-based pre-trained language models such as GPT-2 brought considerable progress to end-to-end dialogue modelling. However, they also present considerable risks for task-oriented dialogue, such as lack of knowledge grounding or diversity. To address these issues, we introduce modified training objectives for language model finetuning, and we employ massive data augmentation via back-translation to increase the diversity of the training data. We further examine the possibilities of combining data from multiples sources to improve performance on the target dataset. We carefully evaluate our contributions with both human and automatic methods. Our model substantially outperforms the baseline on the MultiWOZ data and shows competitive performance with state of the art in both automatic and human evaluation.
References used
https://aclanthology.org/
rate research
Read More
End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the compositional
ity of cascaded systems simplifies learning and enables sophisticated search capabilities. In this work, we present an end-to-end framework that exploits compositionality to learn searchable hidden representations at intermediate stages of a sequence model using decomposed sub-tasks. These hidden intermediates can be improved using beam search to enhance the overall performance and can also incorporate external models at intermediate stages of the network to re-score or adapt towards out-of-domain data. One instance of the proposed framework is a Multi-Decoder model for speech translation that extracts the searchable hidden intermediates from a speech recognition sub-task. The model demonstrates the aforementioned benefits and outperforms the previous state-of-the-art by around +6 and +3 BLEU on the two test sets of Fisher-CallHome and by around +3 and +4 BLEU on the English-German and English-French test sets of MuST-C.
This tutorial surveys the latest technical progress of syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks, in which semantic role labeling (SRL) and machine translation (MT) are the representative NLP tasks
that have always been beneficial from informative syntactic clues since a long time ago, though the advance from end-to-end deep learning models shows new results. In this tutorial, we will first introduce the background and the latest progress of syntactic parsing and SRL/NMT. Then, we will summarize the key evidence about the syntactic impacts over these two concerning tasks, and explore the behind reasons from both computational and linguistic backgrounds.
Modern transformer-based language models are revolutionizing NLP. However, existing studies into language modelling with BERT have been mostly limited to English-language material and do not pay enough attention to the implicit knowledge of language,
such as semantic roles, presupposition and negations, that can be acquired by the model during training. Thus, the aim of this study is to examine behavior of the model BERT in the task of masked language modelling and to provide linguistic interpretation to the unexpected effects and errors produced by the model. For this purpose, we used a new Russian-language dataset based on educational texts for learners of Russian and annotated with the help of the National Corpus of the Russian language. In terms of quality metrics (the proportion of words, semantically related to the target word), the multilingual BERT is recognized as the best model. Generally, each model has distinct strengths in relation to a certain linguistic phenomenon. These observations have meaningful implications for research into applied linguistics and pedagogy, contribute to dialogue system development, automatic exercise making, text generation and potentially could improve the quality of existing linguistic technologies
Recent years has witnessed the remarkable success in end-to-end task-oriented dialog system, especially when incorporating external knowledge information. However, the quality of most existing models' generated response is still limited, mainly due t
o their lack of fine-grained reasoning on deterministic knowledge (w.r.t. conceptual tokens), which makes them difficult to capture the concept shifts and identify user's real intention in cross-task scenarios. To address these issues, we propose a novel intention mechanism to better model deterministic entity knowledge. Based on such a mechanism, we further propose an intention reasoning network (IR-Net), which consists of joint and multi-hop reasoning, to obtain intention-aware representations of conceptual tokens that can be used to capture the concept shifts involved in task-oriented conversations, so as to effectively identify user's intention and generate more accurate responses. Experimental results verify the effectiveness of IR-Net, showing that it achieves the state-of-the-art performance on two representative multi-domain dialog datasets.
Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers. However, building such systems from scratch faces real word challenges from both imperfect product schema/knowle
dge and lack of training dialog data. In this work we first propose ConvSearch, an end-to-end conversational search system that deeply combines the dialog system with search. It leverages the text profile to retrieve products, which is more robust against imperfect product schema/knowledge compared with using product attributes alone. We then address the lack of data challenges by proposing an utterance transfer approach that generates dialogue utterances by using existing dialog from other domains, and leveraging the search behavior data from e-commerce retailer. With utterance transfer, we introduce a new conversational search dataset for online shopping. Experiments show that our utterance transfer method can significantly improve the availability of training dialogue data without crowd-sourcing, and the conversational search system significantly outperformed the best tested baseline.
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
