I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning

Proceedings of the 28th International Conference on Computational Linguistics, pages 2459–2471 Barcelona, Spain (Online), December 8-13, 2020 2459 I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning Jungwoo Lim∗, Dongsuk Oh∗, Yoonna Jang, Kisu Yang, Heuiseok Lim† Computer Science and Engineering, Korea University Republic of Korea {wjddn803,inow3555,morelychee,willow4,limhseok}@korea.ac.kr Abstract CommonsenseQA is a task in which a correct answer is predicted through commonsense reason- ing with pre-defined knowledge. Most previous works have aimed to improve the performance with distributed representation without considering the process of predicting the answer from the semantic representation of the question. To shed light upon the semantic interpretation of the question, we propose an AMR-ConceptNet-Pruned (ACP) graph. The ACP graph is pruned from a full integrated graph encompassing Abstract Meaning Representation (AMR) graph generated from input questions and an external commonsense knowledge graph, ConceptNet (CN). Then the ACP graph is exploited to interpret the reasoning path as well as to predict the correct an- swer on the CommonsenseQA task. This paper presents the manner in which the commonsense reasoning process can be interpreted with the relations and concepts provided by the ACP graph. Moreover, ACP-based models are shown to outperform the baselines. 1 Introduction Commonsense is the knowledge shared by the majority of people in society and acquired naturally in everyday life. Commonsense reasoning is the process of logical inference by using commonsense infor- mation. Commonsense to answer the questions that is “Blowfish requires what specific thing to live?” in Figure 1 is depicted as: “Blowfish is fish”, “Fish lives in the water”, and “Water includes seas and rivers.” An enormous amount of pre-defined com- monsense knowledge is available and people can make inferences using this commonsense such as in the following example: “Blowfish is fish.” → “Fish lives in the water.” → “Water includes seas and rivers.” ⇒ “Blowfish lives in the sea.” This chain of com- monsense reasoning is naturally deduced by humans without substantial difficulty. Whereas people acquire commonsense in their lives, machines cannot learn this knowledge without any assistance. A large amount of external knowledge and several reasoning steps are required for machines to learn com- monsense. In recent years, various datasets (Zellers et al., 2018; Sap et al., 2019; Zellers et al., 2019) have been constructed to enable machines to reason commonsense. CommonsenseQA (Talmor et al., 2019) is one of the most widely researched datasets and is presented in Figure 1 (a). The studies of commonsense reasoning based on this dataset can be categorized into two mainstream approaches. The first approach uses pre-trained language models with distributed represen- tations, which exhibit high performances on most Natural Language Processing (NLP) tasks. However, despite their high performance, these models must be trained with an excessive number of parameters and cannot explain the process of commonsense reasoning. The second approach is reasoning with a commonsense knowledge graph. The generally used commonsense knowledge graph is ConceptNet 5.5 (Speer et al., 2017), which includes parsed representation from Open Mind Commonsense (OMCS) and other different …

Content truncated to 500 words