Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 41–52 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 41 Generating Informative Conversational Response using Recurrent Knowledge-Interaction and Knowledge-Copy Xiexiong Lin Weiyu Jian Jianshan He Taifeng Wang Wei Chu Ant Financial Services Group {xiexiong.lxx,weiyu.jwy,yebai.hjs}@antfin.com {taifeng.wang,weichu.cw}@alibaba-inc.com Abstract Knowledge-driven conversation approaches have achieved remarkable research attention recently. However, generating an informa- tive response with multiple relevant knowl- edge without losing fluency and coherence is still one of the main challenges. To address this issue, this paper proposes a method that uses recurrent knowledge interaction among response decoding steps to incorporate ap- propriate knowledge. Furthermore, we in- troduce a knowledge copy mechanism using a knowledge-aware pointer network to copy words from external knowledge according to knowledge attention distribution. Our joint neural conversation model which integrates recurrent Knowledge-Interaction and knowl- edge Copy (KIC) performs well on gener- ating informative responses. Experiments demonstrate that our model with fewer pa- rameters yields significant improvements over competitive baselines on two datasets Wizard- of-Wikipedia(average Bleu +87%; abs.:0.034) and DuConv(average Bleu +20%; abs.:0.047) with different knowledge formats (textual & structured) and different languages (English & Chinese). 1 Introduction Dialogue systems have attracted much research attention in recent years. Various end-to-end neu- ral generative models based on the sequence-to- sequence framework (Sutskever et al., 2014) have been applied to the open-domain conversation and achieved impressive success in generating fluent dialog responses (Shang et al., 2015; Vinyals and Le, 2015; Serban et al., 2016). However, many neu- ral generative approaches from the last few years confined within utterances and responses, suffering from generating uninformative and inappropriate responses. To make responses more meaningful and expressive, several works on the dialogue sys- tem exploiting external knowledge. Knowledge- driven methods focus on generating more infor- mative and meaningful responses via incorporating structured knowledge consists of triplets (Zhu et al., 2017; Zhou et al., 2018; Young et al., 2018; Liu et al., 2018) or unstructured knowledge like docu- ments (Long et al., 2017; Parthasarathi and Pineau, 2018; Ghazvininejad et al., 2018; Ye et al., 2019). Knowledge-based dialogue generation mainly has two methods: a pipeline way that deals with knowl- edge selection and generation successively (Lian et al., 2019), and a joint way that integrates knowl- edge selection into the generation process, for ex- ample, several works use Memory Network archi- tectures (Sukhbaatar et al., 2015) to integrate the knowledge selection and generation jointly (Dinan et al., 2018; Dodge et al., 2015; Parthasarathi and Pineau, 2018; Madotto et al., 2018; Ghazvinine- jad et al., 2018). The pipeline approaches sepa- rate knowledge selection from generation, result- ing in an insufficient fusion between knowledge and generator. When integrating various knowl- edge, pipeline approaches lack flexibility. The joint method with the memory module usually uses knowledge information statically. The con- fidence of knowledge attention decreasing at de- coding steps, which has the potential to produce inappropriate collocation of knowledge words. To generate informative dialogue response that inte- grates various relevant knowledge without losing fluency …

Content truncated to 500 words