Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMulti-Sentence Knowledge Selection in Open-Domain Dialogue
اختيار المعرفة متعددة الجملة في الحوار مفتوح المجال
672
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إن دمج مصادر المعرفة الخارجية بفعالية في المحادثات هي مشكلة طويلة الأمد في أبحاث الحوار مفتوح المجال. إن الأدبيات الموجودة على اختيار المعرفة المفتوحة للمجال محدود ويقتصر بعض الافتراضات الهشة على مصادر المعرفة لتبسيط المهمة الشاملة، مثل وجود عقوبة معرفة واحدة ذات صلة لكل سياق. في هذا العمل، نقوم بتقييم حالة اختيار معرفة محادثة المحادثة مفتوحة للمجموعات، حيث تظهر المنهجيات الحالية المتعلقة بالبيانات والتقييم معيبة. ثم نحسنها من خلال اقتراح إطار جديد لجمع المعرفة ذات الصلة، وإنشاء مجموعة بيانات معدنية بناء على معالج كوربوس ويكيبيديا (WOW)، والتي نسميها نجاح باهر ++. WOW ++ المتوسطات 8 جمل المعرفة ذات الصلة لكل سياق حوار، واحتضان الغموض المتأصل من اختيار معرفة حوار المجال المفتوح. بعد ذلك، نقدر خوارزميات تصنيف المعرفة المختلفة على هذه البيانات المعززة مع كل من التقييم الجوهري وتدابير خارجية لجودة الاستجابة، والتي تبين أن Rerankers العصبية التي تستخدم WOW ++ يمكن أن تفوق المهاحين المدربين على مجموعات البيانات القياسية.
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.
References used
https://aclanthology.org/
rate research
Read More
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.
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., 202
0). 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.
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.
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.
Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response. However, current dialogue models with the seq2seq framework lack the ability to effectively manage concept transitions and can hardly
introduce multiple concepts to responses in a sequential decoding manner. To facilitate a controllable and coherent dialogue, in this work, we devise a concept-guided non-autoregressive model (CG-nAR) for open-domain dialogue generation. The proposed model comprises a multi-concept planning module that learns to identify multiple associated concepts from a concept graph and a customized Insertion Transformer that performs concept-guided non-autoregressive generation to complete a response. The experimental results on two public datasets show that CG-nAR can produce diverse and coherent responses, outperforming state-of-the-art baselines in both automatic and human evaluations with substantially faster inference speed.
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
