HamNoSyS2SiGML: Translating HamNoSys Into SiGML

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 581–589 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 581 Getting To Know You: User Attribute Extraction from Dialogues Chien-Sheng Wu†, Andrea Madotto, Zhaojiang Lin, Peng Xu, Pascale Fung Center for Artificial Intelligence Research (CAiRE) The Hong Kong University of Science and Technology † Salesforce Research wu.jason@salesforce.com, [amadotto,zlinao,pxuab]@connect.ust.hk, pascale@ece.ust.hk Abstract User attributes provide rich and useful information for user understanding, yet structured and easy-to-use attributes are often sparsely populated. In this paper, we leverage dialogues with conversational agents, which contain strong suggestions of user information, to automatically extract user attributes. Since no existing dataset is available for this purpose, we apply distant supervision to train our proposed two-stage attribute extractor, which surpasses several retrieval and generation baselines on human evaluation. Meanwhile, we discuss potential applications (e.g., personalized recommendation and dialogue systems) of such extracted user attributes, and point out current limitations to cast light on future work. Keywords: Dialogue Systems, Personalization, Information Extraction, Natural Language Processing 1. Introduction User attributes are explicit representations of a person’s identity and characteristics in a structured format. They provide a rich repository of personal information for bet- ter user understanding in many applications. High-quality user attributes are, however, hard to obtain since the infor- mation in social networks such as Facebook and Twitter is often sparsely populated (Li et al., 2014). Therefore, ex- ploiting unstructured data sources to obtain structured user attributes is a challenging research direction. Meanwhile, there is an increasing reliance on dialogue agents to assist, inform, and entertain humans, for ex- ample, keeping the elderly company and providing cus- tomer service. Conversational data between users and sys- tems is informative and abundant, and most of the exist- ing deep learning approaches are trained on these large crowd-sourced corpora or scraped conversations. These models, given the current dialogue context (e.g., few pre- vious turns), are focused on either generating good re- sponses (Serban et al., 2015), or incorporating “system attributes” to generate consistent responses (Zhang et al., 2018; Mazare et al., 2018). However, the whole dialogue history of the same person is ignored, implying that these systems are not gradually getting to know their users by extracting user information through conversations. In this paper, we demonstrate that it is feasible to automat- ically extract user attributes from dialogues. Given a user utterance, our goal is to predict user information that can be represented as a (Subject, Predicate, Object) triplet format, which is available for any downstream application. For ex- ample, in Table 1, (I, live in, Florida) is extracted from the second user utterance. Meanwhile, not every utterance has useful information, and some have multiple attributes. For instance, “How are you doing today?” does not have any user-specific information, but from the fourth user utterance in Table 1, we can conclude that the user has a son, likes to go to church, and has a Ford car. Additionally, unlike standard information extraction tasks, where …

Content truncated to 500 words