Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMulti-Modal Open-Domain Dialogue
الحوار متعدد الوسائط مفتوح
390
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
لقد أثبت العمل الحديث في وكلاء المحادثة المفتوحة على أن التحسينات الكبيرة في الإنسانية وتفضيل المستخدم يمكن تحقيقها عبر التحجيم الضخم في كل من بيانات التدريب المسبق وحجم النموذج (Adiwardana et al.، 2020؛ الأسطوانة وآخرون، 2020). ومع ذلك، إذا كنا نريد بناء عملاء مع قدرات تشبه الإنسان، يجب علينا توسيع نطاق التعامل مع النص فقط. موضوع مهم للغاية هو القدرة على رؤية الصور والتواصل حول ما ينظر إليه. بهدف الحصول على البشر للانخراط في حوار متعدد الوسائط، نحقق في مجمع المكونات من وكلاء حوار الوكالة المفتوحة للحكومة من بين الفنون من نماذج الرؤية الحديثة. نحن ندرس دمج مخططات مختلفة من صور الصور واستراتيجيات التدريب المسبق على نطاق واسع على المجال وضبط النطاق، وتظهر أن طرازنا الأفضل الناتج يفوق النماذج الحالية القوية في حوار متعدد الوسائط أثناء التنفيذ في وقت واحد وكذلك سلفها (النص فقط) (الأسطوانة وآخرون، 2020) في محادثة قائمة على النص. إننا كذلك تحقيق وإدماج مكونات السلامة في نموذجنا النهائي، وإظهار أن هذه الجهود لا تقلل من الأداء النموذجي فيما يتعلق بتفضيل الإنسان.
Recent work in open-domain conversational agents has demonstrated that significant improvements in humanness and user preference can be achieved via massive scaling in both pre-training data and model size (Adiwardana et al., 2020; Roller et al., 2020). However, if we want to build agents with human-like abilities, we must expand beyond handling just text. A particularly important topic is the ability to see images and communicate about what is perceived. With the goal of getting humans to engage in multi-modal dialogue, we investigate combining components from state-of-the-art open-domain dialogue agents with those from state-of-the-art vision models. We study incorporating different image fusion schemes and domain-adaptive pre-training and fine-tuning strategies, and show that our best resulting model outperforms strong existing models in multi-modal dialogue while simultaneously performing as well as its predecessor (text-only) BlenderBot (Roller et al., 2020) in text-based conversation. We additionally investigate and incorporate safety components in our final model, and show that such efforts do not diminish model performance with respect to human preference.
References used
https://aclanthology.org/
rate research
Read More
Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research. The existing literature on open-domain knowledge selection is limited and makes certain brittle assumptions on knowledge
sources to simplify the overall task, such as the existence of a single relevant knowledge sentence per context. In this work, we evaluate the existing state of open-domain conversation knowledge selection, showing where the existing methodologies regarding data and evaluation are flawed. We then improve on them by proposing a new framework for collecting relevant knowledge, and create an augmented dataset based on the Wizard of Wikipedia (WOW) corpus, which we call WOW++. WOW++ averages 8 relevant knowledge sentences per dialogue context, embracing the inherent ambiguity of open-domain dialogue knowledge selection. We then benchmark various knowledge ranking algorithms on this augmented dataset with both intrinsic evaluation and extrinsic measures of response quality, showing that neural rerankers that use WOW++ can outperform rankers trained on standard datasets.
Despite achieving remarkable performance, previous knowledge-enhanced works usually only use a single-source homogeneous knowledge base of limited knowledge coverage. Thus, they often degenerate into traditional methods because not all dialogues can
be linked with knowledge entries. This paper proposes a novel dialogue generation model, MSKE-Dialog, to solve this issue with three unique advantages: (1) Rather than only one, MSKE-Dialog can simultaneously leverage multiple heterogeneous knowledge sources (it includes but is not limited to commonsense knowledge facts, text knowledge, infobox knowledge) to improve the knowledge coverage; (2) To avoid the topic conflict among the context and different knowledge sources, we propose a Multi-Reference Selection to better select context/knowledge; (3) We propose a Multi-Reference Generation to generate informative responses by referring to multiple generation references at the same time. Extensive evaluations on a Chinese dataset show the superior performance of this work against various state-of-the-art approaches. To our best knowledge, this work is the first to use the multi-source heterogeneous knowledge in the open-domain knowledge-enhanced dialogue generation.
Transformer-based pre-trained language models boost the performance of open-domain dialogue systems. Prior works leverage Transformer-based pre-trained language models to generate texts with desired attributes in two general approaches: (1) gradient-
based methods: updating all latent representations of pre-trained models with gradients from attribute models; (2) weighted-decoding methods: re-ranking beam candidates from pre-trained models with attribute functions. However, gradient-based methods lead to high computation cost and can easily get overfitted on small training sets, while weighted-decoding methods are inherently constrained by the low-variance high-bias pre-trained model. In this work, we propose a novel approach to control the generation of Transformer-based pre-trained language models: the SideControl framework, which leverages a novel control attributes loss to incorporate useful control signals, and is shown to perform well with very limited training samples. We evaluate our proposed method on two benchmark open-domain dialogue datasets, and results show that the SideControl framework has better controllability, higher generation quality and better sample-efficiency than existing gradient-based and weighted-decoding baselines.
Recent advances in using retrieval components over external knowledge sources have shown impressive results for a variety of downstream tasks in natural language processing. Here, we explore the use of unstructured external knowledge sources of image
s and their corresponding captions for improving visual question answering (VQA). First, we train a novel alignment model for embedding images and captions in the same space, which achieves substantial improvement in performance on image-caption retrieval w.r.t. similar methods. Second, we show that retrieval-augmented multi-modal transformers using the trained alignment model improve results on VQA over strong baselines. We further conduct extensive experiments to establish the promise of this approach, and examine novel applications for inference time such as hot-swapping indices.
Research on open-domain dialogue systems that allow free topics is challenging in the field of natural language processing (NLP). The performance of the dialogue system has been improved recently by the method utilizing dialogue-related knowledge; ho
wever, non-English dialogue systems suffer from reproducing the performance of English dialogue systems because securing knowledge in the same language with the dialogue system is relatively difficult. Through experiments with a Korean dialogue system, this paper proves that the performance of a non-English dialogue system can be improved by utilizing English knowledge, highlighting the system uses cross-lingual knowledge. For the experiments, we 1) constructed a Korean version of the Wizard of Wikipedia dataset, 2) built Korean-English T5 (KE-T5), a language model pre-trained with Korean and English corpus, and 3) developed a knowledge-grounded Korean dialogue model based on KE-T5. We observed the performance improvement in the open-domain Korean dialogue model even only English knowledge was given. The experimental results showed that the knowledge inherent in cross-lingual language models can be helpful for generating responses in open dialogue systems.
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
