Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4407–4417 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 4407 Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data Moonsu Han1∗ Minki Kang1∗ Hyunwoo Jung1 Sung Ju Hwang1,2 KAIST1, Daejeon, South Korea AITRICS2, Seoul, South Korea {mshan92, zzxc1133, hyunwooj, sjhwang82}@kaist.ac.kr Abstract We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, which is difficult to solve with existing QA methods due to their lack of scal- ability. To tackle this problem, we propose a novel end-to-end deep network model for reading comprehension, which we refer to as Episodic Memory Reader (EMR) that sequen- tially reads the input contexts into an exter- nal memory, while replacing memories that are less important for answering unseen ques- tions. Specifically, we train an RL agent to replace a memory entry when the memory is full, in order to maximize its QA accuracy at a future timepoint, while encoding the ex- ternal memory using either the GRU or the Transformer architecture to learn representa- tions that considers relative importance be- tween the memory entries. We validate our model on a synthetic dataset (bAbI) as well as real-world large-scale textual QA (TriviaQA) and video QA (TVQA) datasets, on which it achieves significant improvements over rule- based memory scheduling policies or an RL- based baseline that independently learns the query-specific importance of each memory. 1 Introduction Question answering (QA) problem is one of the most important challenges in Natural Language Understanding (NLU). In recent years, there has been drastic progress on the topic, owing to the success of deep learning based QA mod- els (Sukhbaatar et al., 2015; Seo et al., 2016; Xiong et al., 2016; Hu et al., 2018; Back et al., 2018; Devlin et al., 2018). On certain tasks such as machine reading comprehension (MRC), where * Equal contribution the problem is to find the span of the answer within a given paragraph (Rajpurkar et al., 2016), the deep-learning based QA models have even sur- passed human-level performances. Despite such impressive achievements, it is still challenging to model question answering with document-level context (Joshi et al., 2017), where the context may include a long document with a large number of paragraphs, due to problems such as difficulty in modeling long-term depen- dency and computational cost. To overcome such scalability problems, researchers have proposed pipelining or confidence based selection methods that combine paragraph-level models to obtain a document-level model (Joshi et al., 2017; Chen et al., 2017; Clark and Gardner, 2018; Wang et al., 2018b). Yet, such models are applicable only when questions are given beforehand and all sen- tences in the document can be stored in memory. However, in realistic settings, the amount of context may be too large to fit into the system memory. We may consider query-based context selection methods such …

Content truncated to 500 words