Matrix Factorization with Knowledge Graph Propagation for Unsupervised Spoken Language Understanding

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 483–494, Beijing, China, July 26-31, 2015. c⃝2015 Association for Computational Linguistics Matrix Factorization with Knowledge Graph Propagation for Unsupervised Spoken Language Understanding Yun-Nung Chen, William Yang Wang, Anatole Gershman, and Alexander I. Rudnicky School of Computer Science, Carnegie Mellon University 5000 Forbes Aveue, Pittsburgh, PA 15213-3891, USA {yvchen, yww, anatoleg, air}@cs.cmu.edu Abstract Spoken dialogue systems (SDS) typically require a predefined semantic ontology to train a spoken language understanding (SLU) module. In addition to the anno- tation cost, a key challenge for design- ing such an ontology is to define a coher- ent slot set while considering their com- plex relations. This paper introduces a novel matrix factorization (MF) approach to learn latent feature vectors for utter- ances and semantic elements without the need of corpus annotations. Specifically, our model learns the semantic slots for a domain-specific SDS in an unsupervised fashion, and carries out semantic pars- ing using latent MF techniques. To fur- ther consider the global semantic struc- ture, such as inter-word and inter-slot re- lations, we augment the latent MF-based model with a knowledge graph propaga- tion model based on a slot-based seman- tic graph and a word-based lexical graph. Our experiments show that the proposed MF approaches produce better SLU mod- els that are able to predict semantic slots and word patterns taking into account their relations and domain-specificity in a joint manner. 1 Introduction A key component of a spoken dialogue sys- tem (SDS) is the spoken language understand- ing (SLU) module—it parses the users’ utterances into semantic representations; for example, the ut- terance “find a cheap restaurant” can be parsed into (price=cheap, target=restaurant) (Pieraccini et al., 1992). To design the SLU module of a SDS, most previous studies relied on predefined slots1 for training the decoder (Seneff, 1992; Dowding 1A slot is defined as a basic semantic unit in SLU, such as “price” and “target” in the example. et al., 1993; Gupta et al., 2006; Bohus and Rud- nicky, 2009). However, these predefined semantic slots may bias the subsequent data collection pro- cess, and the cost of manually labeling utterances for updating the ontology is expensive (Wang et al., 2012). In recent years, this problem led to the devel- opment of unsupervised SLU techniques (Heck and Hakkani-T¨ur, 2012; Heck et al., 2013; Chen et al., 2013b; Chen et al., 2014b). In particular, Chen et al. (2013b) proposed a frame-semantics based framework for automatically inducing se- mantic slots given raw audios. However, these ap- proaches generally do not explicitly learn the la- tent factor representations to model the measure- ment errors (Skrondal and Rabe-Hesketh, 2004), nor do they jointly consider the complex lexical, syntactic, and semantic relations among words, slots, and utterances. Another challenge of SLU is the inference of the hidden semantics. Considering the user utter- ance “can i have a cheap restaurant”, from its sur- face patterns, we can see that …

Content truncated to 500 words