CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation

Shen, Lei; Feng, Yang

doi:10.18653/v1/2020.acl-main.52

Cited by 66 publications

(41 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For I, an action is the identification from sentence to relation, a state is denoted by the representation of input event pair and its sentence, a policy is defined by the parameters of identifier. Inspired by Shen and Feng (2020), we utilize a probability distribution over actions given states to represent the policys, i.e., the probability distribution of the generation of G and identification of I. As aforementioned, we introduce two rewards, causality (R c ) and semantic alignment (R s ) rewards, which encourage G to generate taskrelated sentences with the feedback from identifier, while further optimize I with the feedback from generator.…”

Section: Architecture Of Learnable Dual Augmentationmentioning

confidence: 99%

LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification

Zuo¹,

Cao²,

Chen³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Modern models for event causality identification (ECI) are mainly based on supervised learning, which are prone to the data lacking problem. Unfortunately, the existing NLPrelated augmentation methods cannot directly produce available data required for this task. To solve the data lacking problem, we introduce a new approach to augment training data for event causality identification, by iteratively generating new examples and classifying event causality in a dual learning framework. On the one hand, our approach is knowledge guided, which can leverage existing knowledge bases to generate well-formed new sentences. On the other hand, our approach employs a dual mechanism, which is a learnable augmentation framework, and can interactively adjust the generation process to generate task-related sentences. Experimental results on two benchmarks EventStoryLine and Causal-TimeBank show that 1) our method can augment suitable task-related training data for ECI; 2) our method outperforms previous methods on EventStoryLine and Causal-TimeBank (+2.5 and +2.1 points on F1 value respectively).

show abstract

Section: Architecture Of Learnable Dual Augmentationmentioning

confidence: 99%

LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification

Zuo¹,

Cao²,

Chen³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

show abstract

“…Recently, dialogue systems have gained more attention in both research community (Vougiouklis et al, 2016;Liu et al, 2018;Shen et al, 2019;Shen and Feng, 2020) and industry (Xu et al, 2020;, because of its practicality in the real application, such as chatbot and customer services Shen et al, 2021;Zhang et al, 2020). With external knowledge sources, dialogue systems can generate more specific and informative response, which has great potential to resolve the common response problem (Zhang et al, 2018b;Ren et al, 2020 knowledge-grounded dialogue generation task into two sub-problems: knowledge selection and response selection.…”

Section: Related Workmentioning

confidence: 99%

Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition

Zhan¹,

Zhang²,

Chen³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

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 and 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 pretraining a knowledge-aware response generator to pay more attention on the selected knowledge. In particular, a sequential knowledge transition model equipped with a pretrained 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 knowledgegrounded dialogue benchmarks indicate that our model achieves better performance over baseline models.

show abstract

“…In our model, we use an MLP to predict question types during inference, which is different from the conditional training (CT) methods (Li et al, 2016b;Shen and Feng, 2020) that provide the controllable feature, i.e., question types, in advance for inference. Therefore, we do not consider CT-based models as comparable ones.…”

Section: Baselinesmentioning

confidence: 99%

GTM: A Generative Triple-wise Model for Conversational Question Generation

Shen

Meng

Zhang

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

Generating some appealing questions in opendomain conversations is an effective way to improve human-machine interactions and lead the topic to a broader or deeper direction. To avoid dull or deviated questions, some researchers tried to utilize answer, the "future" information, to guide question generation. However, they separate a post-questionanswer (PQA) triple into two parts: postquestion (PQ) and question-answer (QA) pairs, which may hurt the overall coherence. Besides, the QA relationship is modeled as a one-to-one mapping that is not reasonable in open-domain conversations. To tackle these problems, we propose a generative triple-wise model with hierarchical variations for open-domain conversational question generation (CQG). Latent variables in three hierarchies are used to represent the shared background of a triple and one-to-many semantic mappings in both PQ and QA pairs. Experimental results on a largescale CQG dataset show that our method significantly improves the quality of questions in terms of fluency, coherence and diversity over competitive baselines.

show abstract

CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation

Cited by 66 publications

References 40 publications

LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification

LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification

Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition

GTM: A Generative Triple-wise Model for Conversational Question Generation

Contact Info

Product

Resources

About