Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling
أفلاطون كاج: محادثة المعرفة غير المعرفة عبر النمذجة المشتركة
342
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تتحول نماذج المحادثة واسعة النطاق إلى الاستفادة من المعرفة الخارجية لتحسين الدقة الواقعية في توليد الاستجابة.بالنظر إلى عدم التعليق على المعرفة الخارجية لعوريا الحوار واسعة النطاق، من المستحسن معرفة اختيار المعرفة وتوليد الاستجابة بطريقة غير منشأة.في هذه الورقة، نقترح أفلاطون كاج (توليد المعرفة المعزز)، ونهج تعليمي غير مخطط له لنمذجة المحادثة المحفوظة على المعرفة الطرفية.لكل سياق حوار، يتم اختيار عناصر المعرفة ذات الصلة من الأعلى وبعد ذلك في توليد الاستجابة المدرجة في المعرفة.يتم تحسين مكونين اختيار المعرفة وتوليد الاستجابة بشكل مشترك وفعال تحت هدف متوازن.النتائج التجريبية على اثنين من مجموعات البيانات المتاحة للجمهور التحقق من تفوق أفلاطون كاج.
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.
References used
https://aclanthology.org/
rate research
Read More
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 t
hat 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.
Conversation disentanglement aims to separate intermingled messages into detached sessions, which is a fundamental task in understanding multi-party conversations. Existing work on conversation disentanglement relies heavily upon human-annotated data
sets, which is expensive to obtain in practice. In this work, we explore training a conversation disentanglement model without referencing any human annotations. Our method is built upon the deep co-training algorithm, which consists of two neural networks: a message-pair classifier and a session classifier. The former is responsible of retrieving local relations between two messages while the latter categorizes a message to a session by capturing context-aware information. Both the two networks are initialized respectively with pseudo data built from the unannotated corpus. During the deep co-training process, we use the session classifier as a reinforcement learning component to learn a session assigning policy by maximizing the local rewards given by the message-pair classifier. For the message-pair classifier, we enrich its training data by retrieving message pairs with high confidence from the disentangled sessions predicted by the session classifier. Experimental results on the large Movie Dialogue Dataset demonstrate that our proposed approach achieves competitive performance compared to previous supervised methods. Further experiments show that the predicted disentangled conversations can promote the performance on the downstream task of multi-party response selection.
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.
We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors - facilitating t
he detection of global patterns. We represent the relation between two nodes as the length of the shortest path between them. Graformer learns to weight these node-node relations differently for different attention heads, thus virtually learning differently connected views of the input graph. We evaluate Graformer on two popular graph-to-text generation benchmarks, AGENDA and WebNLG, where it achieves strong performance while using many fewer parameters than other approaches.
The nature of no word delimiter or inflection that can indicate segment boundaries or word semantics increases the difficulty of Chinese text understanding, and also intensifies the demand for word-level semantic knowledge to accomplish the tagging g
oal in Chinese segmenting and labeling tasks. However, for unsupervised Chinese cross-domain segmenting and labeling tasks, the model trained on the source domain frequently suffers from the deficient word-level semantic knowledge of the target domain. To address this issue, we propose a novel paradigm based on attention augmentation to introduce crucial cross-domain knowledge via a translation system. The proposed paradigm enables the model attention to draw cross-domain knowledge indicated by the implicit word-level cross-lingual alignment between the input and its corresponding translation. Aside from the model requiring cross-lingual input, we also establish an off-the-shelf model which eludes the dependency on cross-lingual translations. Experiments demonstrate that our proposal significantly advances the state-of-the-art results of cross-domain Chinese segmenting and labeling 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
