Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning
إيرل: توليد محادثة محادثة المعرفة المعرفة مع التعلم التمثيل اللاإرادي
268
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
توليد الاستجابات الإعلامية والمناسبة صعبة ولكنها مهمة لبناء أنظمة الحوار يشبه الإنسان. على الرغم من أن نماذج المحادثة المختلفة المعرفة قد اقترحت، إلا أن هذه النماذج لها قيود في الاستفادة من المعرفة التي تحدث بشكل غير منتظم في بيانات التدريب، ناهيك عن دمج المعرفة غير المرئية في جيل المحادثة. في هذه الورقة، نقترح طريقة تعلم التمثيل المتعصب للكيان (EARL) لإدخال الرسوم البيانية المعرفة لتوليد المحادثة بالمعلومات. على عكس الأساليب التقليدية التي تقترب المعلمة التمثيل المحدد لكل كيان، فإن إيرل يستخدم سياق المحادثات والهيكل العلائقي لرسوم البيان البيئية لمعرفة تمثيل الفئة للكيانات، المعمم لإدماج كيانات غير مرئية في الرسوم البيانية المعرفة في جيل المحادثة. التقييمات التلقائية واليدوية توضح أن طرازنا يمكن أن يولد ردود أكثر إعلامية ومتماسكة وغير طبيعية من النماذج الأساسية.
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems. Although various knowledge-grounded conversation models have been proposed, these models have limitations in utilizing knowledge that infrequently occurs in the training data, not to mention integrating unseen knowledge into conversation generation. In this paper, we propose an Entity-Agnostic Representation Learning (EARL) method to introduce knowledge graphs to informative conversation generation. Unlike traditional approaches that parameterize the specific representation for each entity, EARL utilizes the context of conversations and the relational structure of knowledge graphs to learn the category representation for entities, which is generalized to incorporating unseen entities in knowledge graphs into conversation generation. Automatic and manual evaluations demonstrate that our model can generate more informative, coherent, and natural responses than baseline models.
References used
https://aclanthology.org/
rate research
Read More
Large-scale conversation models are turning to leveraging external knowledge to improve the factual accuracy in response generation. Considering the infeasibility to annotate the external knowledge for large-scale dialogue corpora, it is desirable to
learn the knowledge selection and response generation in an unsupervised manner. In this paper, we propose PLATO-KAG (Knowledge-Augmented Generation), an unsupervised learning approach for end-to-end knowledge-grounded conversation modeling. For each dialogue context, the top-k relevant knowledge elements are selected and then employed in knowledge-grounded response generation. The two components of knowledge selection and response generation are optimized jointly and effectively under a balanced objective. Experimental results on two publicly available datasets validate the superiority of PLATO-KAG.
Knowledge data are massive and widespread in the real-world, which can serve as good external sources to enrich conversations. However, in knowledge-grounded conversations, current models still lack the fine-grained control over knowledge selection a
nd integration with dialogues, which finally leads to the knowledge-irrelevant response generation problems: 1) knowledge selection merely relies on the dialogue context, ignoring the inherent knowledge transitions along with conversation flows; 2) the models often over-fit during training, resulting with incoherent response by referring to unrelated tokens from specific knowledge content in the testing phase; 3) although response is generated upon the dialogue history and knowledge, the models often tend to overlook the selected knowledge, and hence generates knowledge-irrelevant response. To address these problems, we proposed to explicitly model the knowledge transition in sequential multi-turn conversations by abstracting knowledge into topic tags. Besides, to fully utilizing the selected knowledge in generative process, we propose pre-training a knowledge-aware response generator to pay more attention on the selected knowledge. In particular, a sequential knowledge transition model equipped with a pre-trained knowledge-aware response generator (SKT-KG) formulates the high-level knowledge transition and fully utilizes the limited knowledge data. Experimental results on both structured and unstructured knowledge-grounded dialogue benchmarks indicate that our model achieves better performance over baseline models.
Technologies for enhancing well-being, healthcare vigilance and monitoring are on the rise. However, despite patient interest, such technologies suffer from low adoption. One hypothesis for this limited adoption is loss of human interaction that is c
entral to doctor-patient encounters. In this paper we seek to address this limitation via a conversational agent that adopts one aspect of in-person doctor-patient interactions: A human avatar to facilitate medical grounded question answering. This is akin to the in-person scenario where the doctor may point to the human body or the patient may point to their own body to express their conditions. Additionally, our agent has multiple interaction modes, that may give more options for the patient to use the agent, not just for medical question answering, but also to engage in conversations about general topics and current events. Both the avatar, and the multiple interaction modes could help improve adherence. We present a high level overview of the design of our agent, Marie Bot Wellbeing. We also report implementation details of our early prototype , and present preliminary results.
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method with the goal
of learning a better representation of the style and the content. This method is mainly motivated by the recent success of contrastive learning which has demonstrated its power in unsupervised feature extraction tasks. The idea is to design two contrastive losses with respect to the content and the style by considering two problem characteristics during training. One characteristic is that the target sentence shares the same content with the source sentence, and the second characteristic is that the target sentence shares the same style with the exemplar. These two contrastive losses are incorporated into the general encoder-decoder paradigm. Experiments on two datasets, namely QQP-Pos and ParaNMT, demonstrate the effectiveness of our proposed constrastive losses.
Abstractive summarization quality had large improvements since recent language pretraining techniques. However, currently there is a lack of datasets for the growing needs of conversation summarization applications. Thus we collected ForumSum, a dive
rse and high-quality conversation summarization dataset with human written summaries. The conversations in ForumSum dataset are collected from a wide variety of internet forums. To make the dataset easily expandable, we also release the process of dataset creation. Our experiments show that models trained on ForumSum have better zero-shot and few-shot transferability to other datasets than the existing large chat summarization dataset SAMSum. We also show that using a conversational corpus for pre-training improves the quality of the chat summarization model.
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
