Augmentation of Human Memory: Anticipating Topics that Continue in the Next Meeting. Seyed Ali Bahrainian and Fabio Crestani.The Philips automatic train timetable information system. Harald Aust, Martin Oerder, Frank Seide, and Volker Steinbiss.Target Apps Selection: Towards a Unified Search Framework for Mobile Devices. Mohammad Aliannejadi, Hamed Zamani, Fabio Crestani, and W.In Situ and Context-Aware Target Apps Selection for Unified Mobile Search. Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data. Mohammad Aliannejadi, Masoud Kiaeeha, Shahram Khadivi, and Saeed Shiry Ghidary.
To foster research in this area, we have made Qulac publicly available. Our model significantly outperforms competitive baselines. In particular, our question selection model takes into account the original query and previous question-answer interactions while selecting the next question. We further propose a retrieval framework consisting of three components: question retrieval, question selection, and document retrieval. Our experiments on an oracle model demonstrate that asking only one good question leads to over 170% retrieval performance improvement in terms of, which clearly demonstrates the potential impact of the task. Our dataset is built on top of the TREC Web Track 2009-2012 data and consists of over 10K question-answer pairs for 198 TREC topics with 762 facets.
CLARIFY QUESTIONS OFFLINE
To this end, we propose an offline evaluation methodology for the task and collect a dataset, called Qulac, through crowdsourcing. In this paper, we formulate the task of asking clarifying questions in open-domain information-seeking conversational systems. Asking clarifying questions is especially important in conversational systems since they can only return a limited number of (often only one) result(s).
Alternatively, systems can improve user satisfaction by proactively asking questions of the users to clarify their information needs. As a consequence, they may need to scan multiple result pages or reformulate their queries, which may be a frustrating experience. Users often fail to formulate their complex information needs in a single query.
0 kommentar(er)
