ABSTRACT
Question answering (QA) over a large-scale knowledge base (KB) such as Freebase is an important natural language processing application. There are linguistically oriented semantic parsing techniques and machine learning motivated statistical methods. Both of these approaches face a key challenge on how to handle diverse ways natural questions can be expressed about predicates and entities in the KB. This paper is to investigate how to combine these two approaches. We frame the problem from a proof-theoretic perspective, and formulate it as a proof tree search problem that seamlessly unifies semantic parsing, logic reasoning, and answer ranking. We combine our word entity joint embedding learned from web-scale data with other surface-form features to further boost accuracy improvements. Our real-time system on the Freebase QA task achieved a very high F1 score (47.2) on the standard Stanford WebQuestions benchmark test data.
- G. Andrew and J. Gao. 2010. Scalable training of L1-regularized log-linear models. In Proceedings of the 24th International Conference on Machine Learning, pages 33--40. Google ScholarDigital Library
- J. Bao, N. Duan, M. Zhou, T. Zhao. 2014. Knowledge-Based Question Answering as Machine Translation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 967--976.Google ScholarCross Ref
- J. Berant, A. Chou, R. Frostig, and P. Liang. 2013. Semantic parsing on Freebase from question-answer pairs. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1533--1544.Google Scholar
- J. Berant and P. Liang. 2014. Semantic Parsing via Paraphrasing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 1415--1425.Google Scholar
- K. Bollacker, C. Evans, P. Paritosh, T. Sturge, and J. Taylor. 2008. Freebase: A Collaboratively Created Graph Database for Structuring Human Knowledge. In Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, pages 1247--1249. Google ScholarDigital Library
- A. Bordes, J. Weston, and N. Usunier. 2014a. Open Question Answering with Weakly Supervised Embedding Models. In Proceedings of the 7th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD'14), pages 165--180. Google ScholarDigital Library
- A. Bordes, S. Chopra, and J. Weston. 2014b. Question Answering with Subgraph Embeddings. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 615--620.Google Scholar
- Q. Cai. and A. Yates. 2013. Large-Scale Semantic Parsing via Schema Matching and Lexicon Extension. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 423--433.Google Scholar
- Z. Chen, J. Sun, and X. Huang. 2014. Web Information at Your Fingertips: Paper as an Interaction Metaphor. In Computer, pages 62--66. Google ScholarDigital Library
- A. Fader, L. Zettlemoyer, and O. Etzioni. 2013. Paraphrase-driven learning for open question answering. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 1608--1618.Google Scholar
- X. Huang, J. Baker, and R. Reddy. 2014. A Historical Perspective of Speech Recognition. In Communications of the ACM, 57 (1), pages 94--103. Google ScholarDigital Library
- O. Kolomiyets and M.-F. Moens. 2011. A survey on question answering technology from an information retrieval perspective. In Information Sciences, 181(24), pages 5412--5434. Google ScholarDigital Library
- T. Kwiatkowski, E. Choi, Y. Artzi, and L. Zettlemoyer. 2013. Scaling semantic parsers with on-the-fly ontology matching. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1545--1556.Google Scholar
- R. Mooney. 2014. Semantic Parsing, Past, Present and Future, In ACL 2014 Workshop on Semantic Parsing, Invited Talk.Google Scholar
- J. R. Pierce. 1980. An Introduction to Information Theory: Symbols, Signals and Noise, Dover Books on Mathematics, Dover Publications.Google Scholar
- M. Steedman. 2014. Robust Semantics of Semantic Parsing, In ACL 2014 Workshop on Semantic Parsing, Invited Talk.Google Scholar
- S. Wan, M. Dras, R. Dale, and C. Paris. 2006. Using dependency-based features to take the "para-farce" out of paraphrase. In Australasian Language Technology Workshop.Google Scholar
- Z. Wang, S. Yang, H. Wang, and X. Huang. 2014. An Overview of Microsoft Deep QA System on Stanford WebQuestions Benchmark. Microsoft Research Technical Report MSR-TR-2014-121Google Scholar
- X. Yao and B. Van Durme. 2014a. Information Extraction over Structured Data: Question Answering with Freebase. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 956--966.Google Scholar
- X. Yao, J. Berant, and B. Van Durme. 2014b. Freebase QA: Information Extraction or Semantic Parsing? In Proceedings of the ACL 2014 Workshop on Semantic Parsing, pages 82--86.Google Scholar
- L. Zettlemoyer and M. Collins. 2005. Learning to map sentences to logical form: structured classification with probabilistic categorial grammars. In Proceedings of the Twenty First Conference on Uncertainty in Artificial Intelligence, pages 658--666.Google Scholar
Index Terms
- Large-Scale Question Answering with Joint Embedding and Proof Tree Decoding
Recommendations
Quality-aware collaborative question answering: methods and evaluation
WSDM '09: Proceedings of the Second ACM International Conference on Web Search and Data MiningCommunity Question Answering (QA) portals contain questions and answers contributed by hundreds of millions of users. These databases of questions and answers are of great value if they can be used directly to answer questions from any user. In this ...
Knowledge-based question answering using the semantic embedding space
We extract semantic links of words and logical properties from unstructured data.We jointly encode semantics of words and logical properties into an embedding space.Embedding space provides semantic similarities between word and logical ...
Knowledge Graph Embedding Based Question Answering
WSDM '19: Proceedings of the Twelfth ACM International Conference on Web Search and Data MiningQuestion answering over knowledge graph (QA-KG) aims to use facts in the knowledge graph (KG) to answer natural language questions. It helps end users more efficiently and more easily access the substantial and valuable knowledge in the KG, without ...
Comments