ABSTRACT
The Bloomberg Terminal has been a leading source of financial data and analytics for over 30 years. Through its thousands of functions, the Terminal allows its users to query and run analytics over a large array of data sources, including structured, semi-structured, and unstructured data; as well as plot charts, set up event-driven alerts and triggers, create interactive maps, exchange information via email and instant messaging, and so on. To improve user experience, we have been building question answering systems that can understand a wide range of natural language constructs for various domains that are of fundamental interest to our users. Such natural language interfaces, while exceedingly helpful to users, introduce a number of usability challenges of their own. We tackle some of these challenges through auto-completion. A distinguishing mark of our auto-complete systems is that they are based on and guided by corresponding semantic parsing systems. We describe the auto-complete problem as it arises in this setting, the novel algorithms that we use to solve it, and report on the quality of the results and the efficiency of our approach.
- B. Aditya, Gaurav Bhalotia, Soumen Chakrabarti, Arvind Hulgeri, Charuta Nakhe, Parag, and S. Sudarshan. 2002. BANKS: Browsing and Keyword Searching in Relational Databases. In VLDB. 1083--1086.Google Scholar
- Hannah Bast and Bjö rn Buchhold. 2017. QLever: A Query Engine for Efficient SPARQLGoogle Scholar
- Text Search. In CIKM. 647--656.Google Scholar
- Hannah Bast and Elmar Haussmann. 2015. More Accurate Question Answering on Freebase. In CIKM 2015. 299--304.Google Scholar
- H. Bast and Ingmar Weber. 2006. Type Less, Find More: Fast Autocompletion Search with a Succinct Index. In SIGIR. 364--371.Google Scholar
- Sumit Bhatia, Debapriyo Majumdar, and Prasenjit Mitra. 2011. Query Suggestions in the Absence of Query Logs . In SIGIR. 795--804.Google Scholar
- Sourav S. Bhowmick, Byron Choi, and Curtis E. Dyreson. 2016. Data-driven Visual Graph Query Interface Construction and Maintenance: Challenges and Opportunities . PVLDB , Vol. 9, 12 (2016), 984--992.Google ScholarDigital Library
- Fei Cai and Maarten de Rijke. 2016. A Survey of Query Auto Completion in Information Retrieval. Foundations and Trends in Information Retrieval , Vol. 10, 4 (2016), 273--363.Google ScholarDigital Library
- Mia Xu Chen et al. 2019. Gmail Smart Compose: Real-Time Assisted Writing . In KDD. 2287--2295.Google Scholar
- Martin G. Helander, Thomas K. Landauer, and Prasad V. Prabhu (Eds.). 1997. Handbook of Human-Computer Interaction 2nd ed.). Elsevier Science Inc., New York, NY, USA.Google Scholar
- Michal Horovitz, Liane Lewin-Eytan, Alex Libov, Yoelle Maarek, and Ariel Raviv. 2017. Mailbox-Based vs. Log-Based Query Completion for Mail Search. In SIGIR . 937--940.Google Scholar
- Mandar Joshi, Uma Sawant, and Soumen Chakrabarti. 2014. Knowledge Graph and Corpus Driven Segmentation and Answer Inference for Telegraphic Entity-seeking Queries. In EMNLP. 1104--1114.Google Scholar
- Aishwarya Kamath and Rajarshi Das. 2018. A Survey on Semantic Parsing. CoRR , Vol. abs/1812.00978 (2018). arxiv: 1812.00978 http://arxiv.org/abs/1812.00978Google Scholar
- Nodira Khoussainova, YongChul Kwon, Magdalena Balazinska, and Dan Suciu. 2010. SnipSuggest: Context-Aware Autocompletion for SQL . PVLDB , Vol. 4, 1 (2010), 22--33.Google ScholarDigital Library
- Georgia Koutrika, Alkis Simitsis, and Yannis E. Ioannidis. 2010. Explaining Structured Queries in Natural Language. In ICDE. 333--344.Google Scholar
- Fei Li and H. V. Jagadish. 2012. Usability, Databases, and HCI . IEEE Data Engineering Bulletin , Vol. 35, 3 (2012), 37--45.Google Scholar
- Fei Li and H. V. Jagadish. 2016. Understanding Natural Language Queries over Relational Databases . SIGMOD Record , Vol. 45, 1 (2016), 6--13.Google ScholarDigital Library
- Marco Damonte, Rahul Goel, and Tagyoung Chung. 2019. Practical Semantic Parsing for Spoken Language Understanding. In NAACL, Volume 2 (Industry Papers). ACL, 16--23.Google ScholarCross Ref
- Robert B. Miller. 1968. Response Time in Man-Computer Conversational Transactions. In AFIPS. 267--277.Google Scholar
- Bhaskar Mitra and Nick Craswell. 2015. Query Auto-Completion for Rare Prefixes. In CIKM. 1755--1758.Google Scholar
- Axel-Cyrille Ngonga Ngomo, Lorenz Bü hmann, Christina Unger, Jens Lehmann, and Daniel Gerber. 2013. Sorry, I Don't Speak SPARQL: Translating SPARQL Queries into Natural Language. In WWW. 977--988.Google Scholar
- Dae Hoon Park and Rikio Chiba. 2017. A Neural Language Model for Query Auto-Completion. In SIGIR. 1189--1192.Google Scholar
- Denis Savenkov and Eugene Agichtein. 2017. EviNets: Neural Networks for Combining Evidence Signals for Factoid Question Answering. In ACL. 299--304.Google Scholar
- Milad Shokouhi. 2013. Learning to Personalize Query Auto-Completion . In SIGIR 2013. 103--112.Google ScholarDigital Library
- Po-Wei Wang, Huan Zhang, Vijai Mohan, Inderjit S. Dhillon, and J. Zico Kolter. 2018. Realtime Query Completion via Deep Language Models. In The SIGIR 2018 Workshop On eCommerce, Michigan, USA .Google Scholar
- Sam Wiseman, Stuart M. Shieber, and Alexander M. Rush. 2018. Learning Neural Templates for Text Generation . In EMNLP. 3174--3187.Google Scholar
- W. Woods, R. Kaplan, and B. Nash-Webber. 1974. The Lunar Sciences Natural Language Information System. Technical Report. BBN Inc.Google Scholar
- William A. Woods. 1970. Transition Network Grammars for Natural Language Analysis . Commun. ACM , Vol. 13, 10 (1970), 591--606.Google ScholarDigital Library
- Cong Yu and H. V. Jagadish. 2007. Querying Complex Structured Databases. In VLDB. 1010--1021.Google Scholar
Index Terms
- Semantically Driven Auto-completion
Recommendations
Auto-completion for Question Answering Systems at Bloomberg
SIGIR '18: The 41st International ACM SIGIR Conference on Research & Development in Information RetrievalThe Bloomberg Terminal is the leading source of information and news in the finance industry. Through hundreds of functions that provide access to a vast wealth of structured and semi-structured data, the terminal is able to satisfy a wide range of ...
Diversifying Query Auto-Completion
Query auto-completion assists web search users in formulating queries with a few keystrokes, helping them to avoid spelling mistakes and to produce clear query expressions, and so on. Previous work on query auto-completion mainly centers around ...
Learning from homologous queries and semantically related terms for query auto completion
We propose a learning to rank based query auto completion model (L2R-QAC) that exploits contributions from so-called homologous queries for a QAC candidate, in which two kinds of homologous queries are taken into account.We propose semantic features for ...
Comments