Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDistilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation
تقطير معرفة النماذج الإدارية واسعة النطاق في نماذج استرجاع لمحادثة المجال المفتوحة الفعالة
276
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
على الرغم من الأداء الرائع للنماذج التوليدية واسعة النطاق في محادثة مفتوحة، من المعروف أنها أقل عملية لبناء أنظمة محادثة في الوقت الفعلي بسبب ارتفاع الكمون. من ناحية أخرى، يمكن أن تعيد نماذج استرجاع الردود بأشياء أقل بكثير ولكنها تظهر أداء أدنى للنماذج الإدارية على نطاق واسع لأن جودة المحادثة تحدها مجموعة استجابة محددة مسبقا. للاستفادة من كلتا النهجين، نقترح طريقة تدريب جديدة تسمى G2R (التقطير الاسترجلي من الاسترجاع) التي تحافظ على كفاءة نموذج استرجاع مع الاستفادة من القدرة على التحدث نموذجا إيديا واسع النطاق عن طريق غرس المعرفة بالتوليد نموذج في نموذج الاسترجاع. تتكون G2R من تقنيتين متميزتين من التقطير: يعزز G2R على مستوى البيانات مجموعة بيانات الحوار مع ردود إضافية النموذج المولد النطاق، وينقل G2R على مستوى النموذج درجة جودة الاستجابة التي تم تقييمها بواسطة نموذج التوليد إلى درجة نموذج الاسترجاع عن طريق فقدان المعرفة في التقطير. من خلال تجارب واسعة بما في ذلك التقييم البشري، نوضح أن نظام المحادثة المستندة إلى استرجاعنا المدربين مع G2R يدل على أداء محسن بشكل كبير مقارنة بنموذج استرجاع الأساس أثناء إظهار زمن الاستدلال الأساسي بشكل كبير من النماذج الإدارية على نطاق واسع.
Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due to high latency. On the other hand, retrieval models could return responses with much lower latency but show inferior performance to the large-scale generative models since the conversation quality is bounded by the pre-defined response set. To take advantage of both approaches, we propose a new training method called G2R (Generative-to-Retrieval distillation) that preserves the efficiency of a retrieval model while leveraging the conversational ability of a large-scale generative model by infusing the knowledge of the generative model into the retrieval model. G2R consists of two distinct techniques of distillation: the data-level G2R augments the dialogue dataset with additional responses generated by the large-scale generative model, and the model-level G2R transfers the response quality score assessed by the generative model to the score of the retrieval model by the knowledge distillation loss. Through extensive experiments including human evaluation, we demonstrate that our retrieval-based conversation system trained with G2R shows a substantially improved performance compared to the baseline retrieval model while showing significantly lower inference latency than the large-scale generative models.
References used
https://aclanthology.org/
rate research
Read More
Large-scale language models such as GPT-3 are excellent few-shot learners, allowing them to be controlled via natural text prompts. Recent studies report that prompt-based direct classification eliminates the need for fine-tuning but lacks data and i
nference scalability. This paper proposes a novel data augmentation technique that leverages large-scale language models to generate realistic text samples from a mixture of real samples. We also propose utilizing soft-labels predicted by the language models, effectively distilling knowledge from the large-scale language models and creating textual perturbations simultaneously. We perform data augmentation experiments on diverse classification tasks and show that our method hugely outperforms existing text augmentation methods. We also conduct experiments on our newly proposed benchmark to show that the augmentation effect is not only attributed to memorization. Further ablation studies and a qualitative analysis provide more insights into our approach.
GPT-3 shows remarkable in-context learning ability of large-scale language models (LMs) trained on hundreds of billion scale data. Here we address some remaining issues less reported by the GPT-3 paper, such as a non-English LM, the performances of d
ifferent sized models, and the effect of recently introduced prompt optimization on in-context learning. To achieve this, we introduce HyperCLOVA, a Korean variant of 82B GPT-3 trained on a Korean-centric corpus of 560B tokens. Enhanced by our Korean-specific tokenization, HyperCLOVA with our training configuration shows state-of-the-art in-context zero-shot and few-shot learning performances on various downstream tasks in Korean. Also, we show the performance benefits of prompt-based learning and demonstrate how it can be integrated into the prompt engineering pipeline. Then we discuss the possibility of materializing the No Code AI paradigm by providing AI prototyping capabilities to non-experts of ML by introducing HyperCLOVA studio, an interactive prompt engineering interface. Lastly, we demonstrate the potential of our methods with three successful in-house applications.
The key challenge of question answering over knowledge bases (KBQA) is the inconsistency between the natural language questions and the reasoning paths in the knowledge base (KB). Recent graph-based KBQA methods are good at grasping the topological s
tructure of the graph but often ignore the textual information carried by the nodes and edges. Meanwhile, pre-trained language models learn massive open-world knowledge from the large corpus, but it is in the natural language form and not structured. To bridge the gap between the natural language and the structured KB, we propose three relation learning tasks for BERT-based KBQA, including relation extraction, relation matching, and relation reasoning. By relation-augmented training, the model learns to align the natural language expressions to the relations in the KB as well as reason over the missing connections in the KB. Experiments on WebQSP show that our method consistently outperforms other baselines, especially when the KB is incomplete.
We introduce SPARTA, a novel neural retrieval method that shows great promise in performance, generalization, and interpretability for open-domain question answering. Unlike many neural ranking methods that use dense vector nearest neighbor search, S
PARTA learns a sparse representation that can be efficiently implemented as an Inverted Index. The resulting representation enables scalable neural retrieval that does not require expensive approximate vector search and leads to better performance than its dense counterpart. We validated our approaches on 4 open-domain question answering (OpenQA) tasks and 11 retrieval question answering (ReQA) tasks. SPARTA achieves new state-of-the-art results across a variety of open-domain question answering tasks in both English and Chinese datasets, including open SQuAD, CMRC and etc. Analysis also confirms that the proposed method creates human interpretable representation and allows flexible control over the trade-off between performance and efficiency.
The embedding-based large-scale query-document retrieval problem is a hot topic in the information retrieval (IR) field. Considering that pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, we present a Q
uadrupletBERT model for effective and efficient retrieval in this paper. Unlike most existing BERT-style retrieval models, which only focus on the ranking phase in retrieval systems, our model makes considerable improvements to the retrieval phase and leverages the distances between simple negative and hard negative instances to obtaining better embeddings. Experimental results demonstrate that our QuadrupletBERT achieves state-of-the-art results in embedding-based large-scale retrieval tasks.
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
