tailieunhanh - Báo cáo khoa học: "Spoken Interactive ODQA System: SPIQA"

We have been investigating an interactive approach for Open-domain QA (ODQA) and have constructed a spoken interactive ODQA system, SPIQA. The system derives disambiguating queries (DQs) that draw out additional information. To test the efficiency of additional information requested by the DQs, the system reconstructs the user’s initial question by combining the addition information with question. The combination is then used for answer extraction. Experimental results revealed the potential of the generated DQs. . | Spoken Interactive ODQA System SPIQA Chiori Hori Takaaki Hori Hajime Tsukada Hideki Isozaki Yutaka Sasaki and Eisaku Maeda NTT Communication Science Laboratories Nippon Telegraph and Telephone Corporation 2-4 Hikaridai Seika-cho Soraku-gun Kyoto Japan Abstract We have been investigating an interactive approach for Open-domain QA ODQA and have constructed a spoken interactive ODQA system SPIQA. The system derives disambiguating queries DQs that draw out additional information. To test the efficiency of additional information requested by the DQs the system reconstructs the user s initial question by combining the addition information with question. The combination is then used for answer extraction. Experimental results revealed the potential of the generated DQs. 1 Introduction Open-domain QA ODQA which extracts answers from large text corpora such as newspaper texts has been intensively investigated in the Text REtrieval Conference TREC . ODQA systems return an actual answer in response to a question written in a natural language. However the information in the first question input by a user is not usually sufficient to yield the desired answer. Interactions for collecting additional information to accomplish QA are needed. To construct more precise and user-friendly ODQA systems a speech interface is used for the interaction between human beings and machines. Our goal is to construct a spoken interactive ODQA system that includes an automatic speech recognition ASR system and an ODQA system. To clarify the problems presented in building such a system the QA systems constructed so far have been classified into a number of groups depending on their target domains interfaces and interactions to draw out additional information from users to accomplish set tasks as is shown in Table 1. In this table text and speech denote text input and speech input respectively. The term addition represents additional information queried by the QA systems. This additional information