Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSyntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation
شبكة مخدرة متنوعة من أجل توليد المحادثة المحادثة
233
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تميل أنظمة المحادثة التوليدية إلى إنتاج ردود لا معنى لها والأجنحة، والتي تقلل بشكل كبير من تجربة المستخدم. من أجل توليد ردود مفيدة ومتنوعة، اقترحت الدراسات الحديثة المعرفة لتحسين المعلوماتية وتعتمد المتغيرات الكامنة لتعزيز التنوع. ومع ذلك، فإن الاستفادة من المتغيرات الكامنة ستؤدي إلى عدم دقة المعرفة في الاستجابات، ونشر المعرفة الخاطئة ستضلل المسؤولون. لمعالجة هذه المشكلة، نقترح شبكة مخدرة متنوعة من الناحية النحوية (SDAN) لنموذج المحادثة المدرجة المعرفة. يحتوي SDAN على شبكة دلالات هرمية ذات خصومة للحفاظ على التماسك الدلالي، وهي شبكة مدركة للمعرفة لحضور المعرفة الأكثر متعلقة بتحسين المعلومات والشبكة المتغيرة الكامنة النحوية لتوليد ردود متنوعة من الناحية النحوية. بالإضافة إلى ذلك، من أجل زيادة إمكانية التحكم في بناء الجملة، نعتمد التعلم الخصم لإزالة التمثيلات الدلالية والمنظمات. تظهر النتائج التجريبية أن طرازنا لا يمكن أن يؤدي فقط إلى تحقيق استجابات متنوعة ومتنوعة من المعرفة فقط ولكنها تحقق أيضا التوازن بين تحسين التنوع النحوي والحفاظ على دقة المعرفة.
Generative conversation systems tend to produce meaningless and generic responses, which significantly reduce the user experience. In order to generate informative and diverse responses, recent studies proposed to fuse knowledge to improve informativeness and adopt latent variables to enhance the diversity. However, utilizing latent variables will lead to the inaccuracy of knowledge in the responses, and the dissemination of wrong knowledge will mislead the communicators. To address this problem, we propose a Syntactically Diverse Adversarial Network (SDAN) for knowledge-grounded conversation model. SDAN contains an adversarial hierarchical semantic network to keep the semantic coherence, a knowledge-aware network to attend more related knowledge for improving the informativeness and a syntactic latent variable network to generate syntactically diverse responses. Additionally, in order to increase the controllability of syntax, we adopt adversarial learning to decouple semantic and syntactic representations. Experimental results show that our model can not only generate syntactically diverse and knowledge-accurate responses but also significantly achieve the balance between improving the syntactic diversity and maintaining the knowledge accuracy.
References used
https://aclanthology.org/
rate research
Read More
Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to handle conversational structural information. In this paper, we present a
simple and effective architecture for CSRL which aims to address this problem. Our model is based on a conversational structure aware graph network which explicitly encodes the speaker dependent information. We also propose a multi-task learning method to further improve the model. Experimental results on benchmark datasets show that our model with our proposed training objectives significantly outperforms previous baselines.
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.
Online conversations can sometimes take a turn for the worse, either due to systematic cultural differences, accidental misunderstandings, or mere malice. Automatically forecasting derailment in public online conversations provides an opportunity to
take early action to moderate it. Previous work in this space is limited, and we extend it in several ways. We apply a pretrained language encoder to the task, which outperforms earlier approaches. We further experiment with shifting the training paradigm for the task from a static to a dynamic one to increase the forecast horizon. This approach shows mixed results: in a high-quality data setting, a longer average forecast horizon can be achieved at the cost of a small drop in F1; in a low-quality data setting, however, dynamic training propagates the noise and is highly detrimental to performance.
Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation problem admits a range of acceptable textual outputs, exhibiting lexical, sy
ntactic and semantic variation. To address this disconnect, we present two main contributions. First, we propose a stochastic graph-to-text model, incorporating a latent variable in an encoder-decoder model, and its use in an ensemble. Second, to assess the diversity of the generated sentences, we propose a new automatic evaluation metric which jointly evaluates output diversity and quality in a multi-reference setting. We evaluate the models on WebNLG datasets in English and Russian, and show an ensemble of stochastic models produces diverse sets of generated sentences while, retaining similar quality to state-of-the-art models.
Despite showing increasingly human-like conversational abilities, state-of-the-art dialogue models often suffer from factual incorrectness and hallucination of knowledge (Roller et al., 2020). In this work we explore the use of neural-retrieval-in-th
e-loop architectures - recently shown to be effective in open-domain QA (Lewis et al., 2020b; Izacard and Grave, 2020) - for knowledge-grounded dialogue, a task that is arguably more challenging as it requires querying based on complex multi-turn dialogue context and generating conversationally coherent responses. We study various types of architectures with multiple components - retrievers, rankers, and encoder-decoders - with the goal of maximizing knowledgeability while retaining conversational ability. We demonstrate that our best models obtain state-of-the-art performance on two knowledge-grounded conversational tasks. The models exhibit open-domain conversational capabilities, generalize effectively to scenarios not within the training data, and, as verified by human evaluations, substantially reduce the well-known problem of knowledge hallucination in state-of-the-art chatbots.
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
