Despite the great advances in generative dialogue systems, existing dialogue generation models are still unsatisfactory in maintaining persona consistency. In order to make the dialogue generation model generate more ...Despite the great advances in generative dialogue systems, existing dialogue generation models are still unsatisfactory in maintaining persona consistency. In order to make the dialogue generation model generate more persona-consistent responses, this paper proposes a model named BERT-HCM (Personalized Dialogue Generation Model Based on BERT and Hierarchical Copy Mechanism). The model uses an encoder based on BERT initialization to encode persona information and dialogue queries and subsequently uses a Transformer decoder incorporating a hierarchical copy mechanism to dynamically copy the input-side content to guide the model in generating responses. The experimental results show that the proposed model improves on both automatic and human evaluation metrics compared to the baseline model and is able to generate more fluent, relevant and persona-consistent responses.展开更多
As the dual task of question answering,question generation(QG)is a significant and challenging task that aims to generate valid and fluent questions from a given paragraph.The QG task is of great significance to quest...As the dual task of question answering,question generation(QG)is a significant and challenging task that aims to generate valid and fluent questions from a given paragraph.The QG task is of great significance to question answering systems,conversational systems,and machine reading comprehension systems.Recent sequence to sequence neural models have achieved outstanding performance in English and Chinese QG tasks.However,the task of Tibetan QG is rarely mentioned.The key factor impeding its development is the lack of a public Tibetan QG dataset.Faced with this challenge,the present paper first collects 425 articles from the Tibetan Wikipedia website and constructs 7,234 question–answer pairs through crowdsourcing.Next,we propose a Tibetan QG model based on the sequence to sequence framework to generate Tibetan questions from given paragraphs.Secondly,in order to generate answer-aware questions,we introduce an attention mechanism that can capture the key semantic information related to the answer.Meanwhile,we adopt a copy mechanism to copy some words in the paragraph to avoid generating unknown or rare words in the question.Finally,experiments show that our model achieves higher performance than baseline models.We also further explore the attention and copy mechanisms,and prove their effectiveness through experiments.展开更多
文摘Despite the great advances in generative dialogue systems, existing dialogue generation models are still unsatisfactory in maintaining persona consistency. In order to make the dialogue generation model generate more persona-consistent responses, this paper proposes a model named BERT-HCM (Personalized Dialogue Generation Model Based on BERT and Hierarchical Copy Mechanism). The model uses an encoder based on BERT initialization to encode persona information and dialogue queries and subsequently uses a Transformer decoder incorporating a hierarchical copy mechanism to dynamically copy the input-side content to guide the model in generating responses. The experimental results show that the proposed model improves on both automatic and human evaluation metrics compared to the baseline model and is able to generate more fluent, relevant and persona-consistent responses.
基金This work is supported by the National Nature Science Foundation(No.61972436).
文摘As the dual task of question answering,question generation(QG)is a significant and challenging task that aims to generate valid and fluent questions from a given paragraph.The QG task is of great significance to question answering systems,conversational systems,and machine reading comprehension systems.Recent sequence to sequence neural models have achieved outstanding performance in English and Chinese QG tasks.However,the task of Tibetan QG is rarely mentioned.The key factor impeding its development is the lack of a public Tibetan QG dataset.Faced with this challenge,the present paper first collects 425 articles from the Tibetan Wikipedia website and constructs 7,234 question–answer pairs through crowdsourcing.Next,we propose a Tibetan QG model based on the sequence to sequence framework to generate Tibetan questions from given paragraphs.Secondly,in order to generate answer-aware questions,we introduce an attention mechanism that can capture the key semantic information related to the answer.Meanwhile,we adopt a copy mechanism to copy some words in the paragraph to avoid generating unknown or rare words in the question.Finally,experiments show that our model achieves higher performance than baseline models.We also further explore the attention and copy mechanisms,and prove their effectiveness through experiments.
