Please wait a minute...
Big Data Mining and Analytics  2019, Vol. 2 Issue (4): 217-239    DOI: 10.26599/BDMA.2019.9020011
    
Statistical Learning for Semantic Parsing: A Survey
Qile Zhu, Xiyao Ma, Xiaolin Li*
Qile Zhu, Xiyao Ma, and Xiaolin Li are with National Science Foundation Center for Big Learning, University of Florida, Gainesville, FL 32608, USA. E-mail: valder@ufl.edu; maxiy@ufl.edu.
Download: PDF (1740 KB)      HTML  
Export: BibTeX | EndNote (RIS)      

Abstract  

A long-term goal of Artificial Intelligence (AI) is to provide machines with the capability of understanding natural language. Understanding natural language may be referred as the system must produce a correct response to the received input order. This response can be a robot move, an answer to a question, etc. One way to achieve this goal is semantic parsing. It parses utterances into semantic representations called logical form, a representation of many important linguistic phenomena that can be understood by machines. Semantic parsing is a fundamental problem in natural language understanding area. In recent years, researchers have made tremendous progress in this field. In this paper, we review recent algorithms for semantic parsing including both conventional machine learning approaches and deep learning approaches. We first give an overview of a semantic parsing system, then we summary a general way to do semantic parsing in statistical learning. With the rise of deep learning, we will pay more attention on the deep learning based semantic parsing, especially for the application of Knowledge Base Question Answering (KBQA). At last, we survey several benchmarks for KBQA.



Key wordsdeep learning      semantic parsing      Knowledge Base Question Answering (KBQA)     
Received: 17 September 2018      Published: 06 January 2020
Corresponding Authors: Xiaolin Li   
About author:

? Jiangcheng Zhu and Shuang Hu contribute equally to this paper. This work was done when they were visiting researchers in Data Science Institute, Imperial College London, London SW7 2AZ, UK.

Cite this article:

Qile Zhu, Xiyao Ma, Xiaolin Li. Statistical Learning for Semantic Parsing: A Survey. Big Data Mining and Analytics, 2019, 2(4): 217-239.

URL:

http://bigdata.tsinghuajournals.com/10.26599/BDMA.2019.9020011     OR     http://bigdata.tsinghuajournals.com/Y2019/V2/I4/217

UtteranceAction
What is the largest prime less than 10?7
What is the highest mountain in the world?Mount Everest
Call the number 1234567Open the phone APP and make a call
Table 1 Examples for utterance-action pairs.
Fig. 1 Semantic parsing taxonomies by supervisory signal and techniques (names are corresponding to Section 4.1).
Entity in utteranceEntity in knowledge base
NataliePortmanNatalie Portman
Star WarsStar Wars Episode I: The Phantom Menace
Table 2 Examples of entity linking.
49]. To narrow down the space of logical predicates, they use (1) course alignment based on Freebase and a text corpus and (2) a bridging operation that generates predicates compatible with neighboring predicates.">
Fig. 2 An example to answer a question through a knowledge base<sup>[<xref ref-type="bibr" rid="R49">49</xref>]</sup>. To narrow down the space of logical predicates, they use (1) course alignment based on Freebase and a text corpus and (2) a bridging operation that generates predicates compatible with neighboring predicates.
50]. For each candidate logical form (red), it generated canonical utterances (purple). The model is trained to paraphrase the input utterance (green) into the canonical utterances associated with the correct denotation (blue).">
Fig. 3 An example of paraphrasing for semantic parsing<sup>[<xref ref-type="bibr" rid="R50">50</xref>]</sup>. For each candidate logical form (red), it generated canonical utterances (purple). The model is trained to paraphrase the input utterance (green) into the canonical utterances associated with the correct denotation (blue).
60].">
Fig. 4 Query graph of question "who first voiced Meg on Family Guy" <sup>[<xref ref-type="bibr" rid="R60">60</xref>]</sup>.
60].">
Fig. 5 Legitimate actions to grow a query graph<sup>[<xref ref-type="bibr" rid="R60">60</xref>]</sup>.
70].">
Fig. 6 A SEQ2TREE decoding example for the logical form "<i>AB</i>(<i>C</i>)" <sup>[<xref ref-type="bibr" rid="R70">70</xref>]</sup>.
and are defined on numbers and dates[71]. 𝕂 is the knowledge base and ε denotes a set of entities.">
Fig. 7 Interpreter functions of the NSM. <i>r</i> represents a variable, <i>p</i> is a predicate in Freebase. <inline-formula><math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="MA223"><mml:mo mathvariant="bold">⩽</mml:mo></math></inline-formula> and <inline-formula><math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="MA224"><mml:mo mathvariant="bold">⩾</mml:mo></math></inline-formula> are defined on numbers and dates<sup>[<xref ref-type="bibr" rid="R71">71</xref>]</sup>. 𝕂 is the knowledge base and <i>ε</i> denotes a set of entities.
R𝟏" ). The memory bridges these two steps to achieve compositionality[71].">
Fig. 8 Semantic parsing with NSM. A special token "GO" indicates the start of decoding, and "Return" indicates the end of decoding. Due to the fact that the decoding model never sees the values in the encoder ( "US" ) here, so it only references them with the name of the variable ( "<inline-formula><math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="MA225"><mml:msub><mml:mi mathvariant="bold-italic">R</mml:mi><mml:mtext>𝟏</mml:mtext></mml:msub></math></inline-formula>" ). The memory bridges these two steps to achieve compositionality<sup>[<xref ref-type="bibr" rid="R71">71</xref>]</sup>.
PredicateUsageSub-category
AnswerDenotation wrapper-
TypeEntity type checkingStateid, cityid riverid, etc.
AllQuerying for an entire set of entities-
AggregationOne-argument meta predicates for setsCount, largest, smallest, etc.
Logical connectivesTwo-argument meta predicates for setsIntersect, union, exclude
Table 3 List of domain-general predicates[73].
73].">
Fig. 9 Actions taken by the transition system for generating the ungrounded meaning representation of the example. Symbols in red indicate domain-general predicates<sup>[<xref ref-type="bibr" rid="R73">73</xref>]</sup>.
79].">
Fig. 10 Framework of semantic parsing via paraphrasing. Firstly, the logical forms are converted deterministically into canonical utterance in natural language. Combing canonical utterance with input utterance as the input, paraphrase model is trained to learn and transfer from the source-domain to the target-domain. External language resources are applied to facilitate domain adaptation<sup>[<xref ref-type="bibr" rid="R79">79</xref>]</sup>.
InitializationL2 normMicro varianceCosine similarity
Random17.3 ± 0.451.00 ± 0.050.00 ± 0.06
WORD2VEC2.04 ± 1.080.02 ± 0.020.13 ± 0.11
WORD2VEC+ES17.3 ± 0.051.00 ± 0.000.13 ± 0.11
WORD2VEC+FS16.0 ± 8.471.09 ± 1.310.12 ± 0.10
WORD2VEC+EN1.00 ± 0.000.01 ± 0.000.13 ± 0.11
Table 4 Comparison between different word embedding initializations. ES: per-example standardization. FS: per-feature standardization. EN: per-example normalization. Cosine similarity is computed on a randomly selected.
Dataset nameTraining set numberDevelopment set numberTest set numberBest result (%)Supervision form
JOBS500-14090.0[70]Supervision
Geo880880--91.1[6]Supervision
ATIS-35418--84.6[31]Supervision
Regexp824824--65.6[13]Supervision
Free917917--68[13]Supervision
WebQuestions5810--58.8[60]Weak Supervision
WebQuestionSP3098-163963.9[60,82]Weak Supervision
SPADES93 319--39.9[83]Weak Supervision
SimpleQuestion75 91010 84521 68778.7[82]Weak Supervision
WikiTableQuestions22 033--37.1[84]Weak Supervision
OVERNIGHT13 682--80.6[79]Supervision
IFTTT77 4955171429474.2[70]Supervision
Table 5 An overview of all datasets ( "-" means there is not official split for this dataset).
[1]   Pasupat P. and Liang P., Compositional semantic parsing on semi-structured tables, in Proc. 53rd Ann. Meeting of the Association for Computational Linguistics and the 7th Int. Joint Conf. Natural Language Processing, Beijing, China, 2015.
[2]   Liang P., Learning executable semantic parsers for natural language understanding, Commun. ACM, vol. 59, no. 9, pp. 68-76, 2016.
[3]   Woods W., Kaplan R., and Webber B., The Lunar Sciences Natural Language Information System: Final Report. Cambridge, MA, USA: Bolt Beranek and Newman Inc., 1972.
[4]   Winograd T., Understanding Natural Language. New York, NY, USA: Academic Press, 1972.
[5]   Clarke J., Goldwasser D., Chang M. W., and Roth D., Driving semantic parsing from the world’s response, in Proc. 14th Conf. Computational Natural Language Learning, Uppsala, Sweden, 2010, pp. 18-27.
[6]   Liang P., Jordan M. I., and Klein D., Learning dependency-based compositional semantics, in Proc. 49th Ann. Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1, Portland, OR, USA, 2011, pp. 590-599.
[7]   Bollacker K., Evans C., Paritosh P., Sturge T., and Taylor J., Freebase: A collaboratively created graph database for structuring human knowledge, in Proc. 2008 ACM SIGMOD Int. Conf. Management of Data, Vancouver, Canada, 2008, pp. 1247-1250.
[8]   Vrandecic D. and Kr?tzsch M., Wikidata: A free collaborative knowledgebase, Commun. ACM, vol. 57, no. 10, pp. 78-85, 2014.
[9]   Tellex S., Kollar T., Dickerson S., Walter M. R., Banerjee A. G., Teller S., and Roy N., Understanding natural language commands for robotic navigation and mobile manipulation, in Proc. 25th AAAI Conf. Artificial Intelligence, San Francisco, CA, USA, 2011.
[10]   Artzi Y. and Zettlemoyer L., Weakly supervised learning of semantic parsers for mapping instructions to actions, Trans. Assoc. Comput. Linguist., vol. 1, pp. 49-62, 2013.
[11]   Matuszek C., FitzGerald N., Zettlemoyer L., Bo L., and Fox D., A joint model of language and perception for grounded attribute learning, in Proc. 29th Int. Conf. Machine Learning, Edinburgh, UK, 2012.
[12]   Krishnamurthy J. and Kollar T., Jointly learning to parse and perceive: Connecting natural language to the physical world, Trans. Assoc. Comput. Linguist., vol. 1, pp. 193-206, 2013.
[13]   Kushman N. and Barzilay R., Using semantic unification to generate regular expressions from natural language, in Proc. 2013 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Atlanta, GA, USA, 2013.
[14]   LeCun Y., Bengio Y., and Hinton G., Deep learning, Nature, vol. 521, no. 7553, pp. 436-444, 2015.
[15]   Hinton G., Deng L., Yu D., Dahl G. E., Mohamed A.R., Jaitly N., Senior A., Vanhoucke V., Nguyen P., Sainath T. N., et al., Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups, IEEE Signal Process. Mag., vol. 29, no. 6, pp. 82-97, 2012.
[16]   He K. M., Zhang X. Y., Ren S. Q., and Sun J., Deep residual learning for image recognition, in Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 770-778.
[17]   Li Y., Qi H. Z., Dai J. F., Ji X. Y., and Wei Y. C., Fully convolutional instance-aware semantic segmentation, in Proc. 2017 IEEE Conf. Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017.
[18]   Ma X. Z. and Hovy E., End-to-end sequence labeling via Bi-directional LSTM-CNNs-CRF, arXiv preprint arXiv:1603.01354, 2016.
[19]   Lample G., Ballesteros M., Subramanian S., Kawakami K., and Dyer C., Neural architectures for named entity recognition, in Proc. 2016 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, CA, USA, 2016.
[20]   Zhu Q. L., Li X. L., Conesa A., and Cecile P., GRAM-CNN: A deep learning approach with local context for named entity recognition in biomedical text, Bioinformatics, vol. 34, no. 9, pp. 1547-1554, 2018.
[21]   Sun R. M., Yuan X. Y., He P., Zhu Q. L., Chen A. K., Gregio A., Oliveira D., and Li X. L., Learning fast and slow: Propaedeutica for real-time malware detection, arXiv preprint arXiv:1712.01145, 2017.
[22]   Collobert R., Weston J., Bottou L., Karlen M., Kavukcuoglu K., and Kuksa P., Natural language processing (almost) from scratch, J. Mach. Learn. Res., vol. 12, pp. 2493-2537, 2011.
[23]   Sang E. F. T. K. and De Meulder F., Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition, in Proc. 7th Conf. Natural Language Learning at HLT-NAACL 2003-Volume 4, Edmonton, Canada, 2003, pp. 142-147.
[24]   Marcus M. P., Marcinkiewicz M. A., and Santorini B., Building a large annotated corpus of English: The Penn Treebank, Comput. Linguist., vol. 19, no. 2, pp. 313-330, 1993.
[25]   Misra D. K. and Artzi Y., Neural shift-reduce CCG semantic parsing, in Proc. 2016 Conf. Empirical Methods in Natural Language Processing, Austin, TX, USA, 2016, pp. 1775-1786.
[26]   Zelle J. M. and Mooney R. J., Learning to parse database queries using inductive logic programming, in Proc. 13th National Conf. Artificial Intelligence, Portland, OR, USA, 1996, pp. 1050-1055.
[27]   Wong Y. W. and Mooney R. J., Learning for semantic parsing with statistical machine translation, in Proc. Main Conf. Human Language Technology Conf. North American Chapter of the Association of Computational Linguistics, New York, NY, USA, 2006, pp. 439-446.
[28]   Zettlemoyer L. S. and Collins M., Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars, in Proc. 21st Conf. Uncertainty in Artificial Intelligence, Edinburgh, UK, 2005.
[29]   Steedman M., The Syntactic Process. Cambridge, MA, USA: MIT Press, 2000.
[30]   Artzi Y., Lee K., and Zettlemoyer L., Broad-coverage CCG semantic parsing with AMR, in Proc. 2015 Conf. Empirical Methods in Natural Language Processing, Lisbon, Portugal, 2015, pp. 1699-1710.
[31]   Zettlemoyer L. S. and Collins M., Online learning of relaxed CCG grammars for parsing to logical form, in Proc. Joint Conf. Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Prague, Czech Republic, 2007, pp. 678-687.
[32]   Kwiatkowski T., Zettlemoyer L., Goldwater S., and Steedman M., Inducing probabilistic CCG grammars from logical form with higher-order unification, in Proc. 2010 Conf. Empirical Methods in Natural Language Processing, Cambridge, MA, USA, 2010, pp. 1223-1233.
[33]   Liang P., Lambda dependency-based compositional semantics, arXiv preprint arXiv:1309.4408, 2013.
[34]   Zheng Z. C., Li F. T., Huang M. L., and Zhu X. Y., Learning to link entities with knowledge base, in Human Language Technologies: The 2010 Ann. Conf. North American Chapter of the Association for Computational Linguistics, Los Angeles, CA, USA, 2010, pp. 483-491.
[35]   Yang Y. and Chang M. W., S-mart: Novel tree-based structured learning algorithms applied to tweet entity linking, in Proc. Association for Computational Linguistics, Beijing, China, 2015.
[36]   Schank R. C. and Tesler L., A conceptual dependency parser for natural language, in Proc. 1969 Conf. Computational Linguistics, S?ng-S?by, Sweden, 1969, pp. 1-3.
[37]   Zhao K. and Huang L., Type-driven incremental semantic parsing with polymorphism, in Proc. Human Language Technologies: The Ann. Conf. North American Chapter of the ACL, Denver, CO, USA, 2015.
[38]   Sutton R. S. and Barto A. G., Reinforcement Learning: An Introduction. Cambridge, MA, USA: MIT Press, 1998.
[39]   Collins M., Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms, in Proc. ACL-02 Conf. Empirical Methods in Natural Language Processing-Volume 10, Stroudsburg, PA, USA, 2002, pp. 1-8.
[40]   Rosenblatt F., The Perceptron: A Perceiving and Recognizing Automation. Buffalo, NY, USA: Cornell Aeronautical Laboratory, 1957.
[41]   Freund Y. and Schapire R. E., Large margin classification using the perceptron algorithm, Mach. Learn., vol. 37, no. 3, pp. 277-296, 1999.
[42]   Zhao K., Structured Prediction with Perceptron: Theory and Algorithms, New York, NY, USA: The City University of New York, 2014.
[43]   Liang P., Bouchard-C?té A., Klein D., and Taskar B., An end-to-end discriminative approach to machine translation, in Proc. 21st Int. Conf. Computational Linguistics and the 44th Ann. Meeting of the Association for Computational Linguistics, Sydney, Australia, 2006, pp. 761-768.
[44]   Singh-Miller N. and Collins M., Trigger-based language modeling using a loss-sensitive perceptron algorithm, in Proc. 2007 IEEE Int. Conf. Acoustics, Speech and Signal Processing, Honolulu, HI, USA, 2007, pp. 25-28.
[45]   Artzi Y. and Zettlemoyer L., Bootstrapping semantic parsers from conversations, in Proc. 2011 Conf. Empirical Methods in Natural Language Processing, Edinburgh, UK, 2011, pp. 421-432.
[46]   Chen D. L. and Mooney R. J., Learning to interpret natural language navigation instructions from observations, in Proc. 25th AAAI Conf. Artificial Intelligence, San Francisco, CA, USA, 2011, pp. 859-865.
[47]   Cai Q. Q. and Yates A., Large-scale semantic parsing via schema matching and lexicon extension, in Proc. 51st Ann. Meeting of the Association for Computational Linguistics, Sofia, Bulgaria, 2013, pp. 423-433.
[48]   Kwiatkowski T., Choi E., Artzi Y., and Zettlemoyer L., Scaling semantic parsers with on-the-fly ontology matching, in Proc. 2013 Conf. Empirical Methods in Natural Language Processing, Seattle, WA, USA, 2013.
[49]   Berant J., Chou A., Frostig R., and Liang P., Semantic parsing on freebase from question-answer pairs, in Proc. 2013 Conf. Empirical Methods in Natural Language Processing, Seattle, WA, USA, 2013.
[50]   Berant J. and Liang P., Semantic parsing via paraphrasing, in Proc. 52nd Ann. Meeting of the Association for Computational Linguistics, Baltimore, MA, USA, 2014, pp. 1415-1425.
[51]   Mikolov T., Sutskever I., Chen K., Corrado G., and Dean J., Distributed representations of words and phrases and their compositionality, in Proc. 26th Int. Conf. Neural Information Processing Systems, Lake Tahoe, NV, USA, 2013, pp. 3111-3119.
[52]   LeCun Y., Boser B., Denker J. S., Henderson D., Howard R. E., Hubbard W., and Jackel L. D., Backpropagation applied to handwritten zip code recognition, Neural Comput., vol. 1, no. 4, pp. 541-551, 1989.
[53]   Goodfellow I., Bengio Y., and Courville A., Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
[54]   Zhou Y. T., Chellappa R., Vaid A., and Jenkins B. K., Image restoration using a neural network, IEEE Trans. Acoust. Speech Signal Process., vol. 36, no. 7, pp. 1141-1151, 1988.
[55]   Schuster M. and Paliwal K. K., Bidirectional recurrent neural networks, IEEE Trans. Signal Process., vol. 45, no. 11, pp. 2673-2681, 1997.
[56]   Hochreiter S., Untersuchungen zu dynamischen neuronalen netzen, Master dissertation, Technische Universitaet München, Munich, Germany, 1991.
[57]   Bengio Y., Simard P., and Frasconi P., Learning long-term dependencies with gradient descent is difficult, IEEE Trans. Neural Netw., vol. 5, no. 2, pp. 157-166, 1994.
[58]   Hochreiter S. and Schmidhuber J., Long short-term memory, Neural Comput., vol. 9, no. 8, pp. 1735-1780, 1997.
[59]   Cho K., van Merri?nboer B., Gulcehre C., Bahdanau D., Bougares F., Schwenk H., and Bengio Y., Learning phrase representations using RNN encoder-decoder for statistical machine translation, in Proc. 2014 Conf. Empirical Methods in Natural Language Processing, Doha, Qatar, 2014.
[60]   Yih S. W. T., Chang M. W., He X. D., and Gao J. F., Semantic parsing via staged query graph generation: Question answering with knowledge base, in Proc. 53rd Ann. Meeting of the Association for Computational Linguistics and the 7th Int. Joint Conf. Natural Language Processing, Beijing, China, 2015, pp. 1321-1331.
[61]   Bordes A., Chopra S., and Weston J., Question answering with subgraph embeddings, in Proc. 2014 Conf. Empirical Methods in Natural Language Processing, Doha, Qatar, 2014.
[62]   Bao J., Duan N., Zhou M., and Zhao T., Knowledge-based question answering as machine translation, in Proc. 52nd Ann. Meeting of the Association for Computational Linguistics, Baltimore, MD, USA, 2014.
[63]   Bromley J., Guyon I., LeCun Y., S?ckinger E., and Shah R., Signature verification using a "siamese" time delay neural network, in Proc. 6th Int. Conf. Neural Information Processing Systems, Denver, CO, USA, 1993, pp. 737-744.
[64]   Jia R. and Liang P., Data recombination for neural semantic parsing, in Proc. 54th Ann. Meeting of the Association for Computational Linguistics, Berlin, Germany, 2016, pp. 12-22.
[65]   Bahdanau D., Cho K., and Bengio Y., Neural machine translation by jointly learning to align and translate, in Proc. Int. Conf. Learning Representations, San Diego, CA, USA, 2015.
[66]   Luong M. T., Pham H., and Manning C. D., Effective approaches to attention-based neural machine translation, in Proc. 2015 Conf. Empirical Methods in Natural Language Processing, Lisbon, Portugal, 2015.
[67]   Vinyals O., Fortunato M., and Jaitly N., Pointer networks, in Proc. 28th Int. Conf. Neural Information Processing Systems, Montreal, Canada, 2015, pp. 2692-2700.
[68]   Krizhevsky A., Sutskever I., and Hinton G. E., Imagenet classification with deep convolutional neural networks, in Proc. 25th Int. Conf. Neural Information Processing Systems, Lake Tahoe, NV, USA, 2012, pp. 1097-1105.
[69]   Jaitly N. and Hinton G. E., Vocal Tract Length Perturbation (VTLP) improves speech recognition, in Proc. 30th Int. Conf. Machine Learning, Atlanta, GA, USA, 2013.
[70]   Dong L. and Lapata M., Language to logical form with neural attention, in Proc. 54th Ann. Meeting of the Association for Computational Linguistics, Berlin, Germany, 2016.
[71]   Liang C., Berant J., Le Q., Forbus K. D., and Lao N., Neural symbolic machines: Learning semantic parsers on freebase with weak supervision, in Proc. 55th Ann. Meeting of the Association for Computational Linguistics, Vancouver, Canada, 2017, pp. 23-33.
[72]   Williams R. J., Simple statistical gradient-following algorithms for connectionist reinforcement learning, Mach. Learn., vol. 8, nos. 3&4, pp. 229-256, 1992.
[73]   Cheng J. P., Reddy S., Saraswat V., and Lapata M., Learning structured natural language representations for semantic parsing, in Proc. 55th Ann. Meeting of the Association for Computational Linguistics, Vancouver, Canada, 2017, pp. 44-55.
[74]   Reddy S., Lapata M., and Steedman M., Large-scale semantic parsing without question-answer pairs, Trans. Assoc. Comput. Linguist., vol. 2, pp. 377-392, 2014.
[75]   Reddy S., T?ckstr?m O., Collins M., Kwiatkowski T., Das D., Steedman M., and Lapata M., Transforming dependency structures to logical forms for semantic parsing, Trans. Assoc. Comput. Linguist., vol. 4, pp. 127-140, 2016.
[76]   Kate R. J., Wong Y. W., and Mooney R. J., Learning to transform natural to formal languages, in Proc. 20th National Conf. Artificial Intelligence, Pittsburgh, PA, USA, 2005, pp. 1062-1068.
[77]   Dyer C., Kuncoro A., Ballesteros M., and Smith N. A., Recurrent neural network grammars, in Proc. NAACL-HLT, San Diego, CA, USA, 2016.
[78]   Dyer C., Ballesteros M., Ling W., Matthews A., and Smith N. A., Transition-based dependency parsing with stack long short-term memory, in Proc. 53rd Ann. Meeting of the Association for Computational Linguistics and the 7th Int. Joint Conf. Natural Language Processing, Beijing, China, 2015.
[79]   Su Y. and Yan X. F., Cross-domain semantic parsing via paraphrasing, in Proc. 2017 Conf. Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 2017.
[80]   Herzig J. and Berant J., Neural semantic parsing over multiple knowledge-bases, in Proc. 55th Ann. Meeting of the Association for Computational Linguistics, Vancouver, Canada, 2017.
[81]   Johnson M., Schuster M., Le Q. V., Krikun M., Wu Y. H., Chen Z. F., Thorat N., Viégas F., Wattenberg M., Corrado G., et al., Google’s multilingual neural machine translation system: Enabling zero-shot translation, Trans. Assoc. Comput. Linguist., vol. 5, pp. 339-351, 2017.
[82]   Yu M., Yin W. P., Hasan K. S., dos Santos C., Xiang B., and Zhou B. W., Improved neural relation detection for knowledge base question answering, in Proc. 55th Ann. Meeting of the Association for Computational Linguistics, Vancouver, Canada, 2017, pp. 571-581.
[83]   Das R., Zaheer M., Reddy S., and McCallum A., Question answering on knowledge bases and text using universal schema and memory networks, in Proc. 55th Ann. Meeting of the Association for Computational Linguistics, Vancouver, Canada, 2017.
[84]   Andreas J., Rohrbach M., Darrell T., and Klein D., Learning to compose neural networks for question answering, in Proc. NAACL-HLT, San Diego, CA, USA, 2016.
[85]   Tang L. R. and Mooney R. J., Using multiple clause constructors in inductive logic programming for semantic parsing, in Proc. 12th European Conf. Machine Learning, Freiburg, Germany, 2001, pp. 466-477.
[86]   Yih W. T., Richardson M., Meek C., Chang M. W., and Suh J., The value of semantic parse labeling for knowledge base question answering, in Proc. 54th Ann. Meeting of the Association for Computational Linguistics, 2016, pp. 201-206.
[87]   Bisk Y., Reddy S., Blitzer J., Hockenmaier J., and Steedman M., Evaluating induced CCG parsers on grounded semantic parsing, in Proc. 2016 Conf. Empirical Methods in Natural Language Processing, Austin, TX, USA, 2016.
[88]   Gabrilovich E., Ringgaard M., and Subramanya A., Facc1: Freebase Annotation of ClueWeb Corpora. Google Inc., 2013.
[89]   Bordes A., Usunier N., Chopra S., and Weston J., Large-scale simple question answering with memory networks, arXiv preprint arXiv:1506.02075, 2015.
[90]   Wang Y. S., Berant J., and Liang P., Building a semantic parser overnight, in Proc. 53rd Ann. Meeting of the Association for Computational Linguistics and the 7th Int. Joint Conf. Natural Language Processing, Beijing, China, 2015, pp. 1332-1342.
[91]   Quirk C., Mooney R., and Galley M., Language to code: Learning semantic parsers for if-this-then-that recipes, in Proc. 53rd Ann. Meeting of the Association for Computational Linguistics and the 7th Int. Joint Conf. Natural Language Processing, Beijing, China, 2015, pp. 878-888.
[92]   Bapna A., Tür G., Hakkani-Tür D., and Heck L., Towards zero-shot frame semantic parsing for domain scaling, in Proc. INTERSPEECH, Stockholm, Sweden, 2017.
[93]   Hakkani-Tür D., Tür G., Celikyilmaz A., Chen Y. N. V., Gao J. F., Deng L., and Wang Y. Y., Multi-domain joint semantic frame parsing using bi-directional RNN-LSTM, in Proc. 17th Ann. Meeting of the Int. Speech Communication Association, San Francisco, CA, USA, 2016, pp. 715-719.
[94]   Jaech A., Heck L., and Ostendorf M., Domain adaptation of recurrent neural networks for natural language understanding, in Proc. 17th Ann. Meeting of the Int. Speech Communication Association, San Francisco, CA, USA, 2016.
[95]   Fan X., Monti E., Mathias L., and Dreyer M., Transfer learning for neural semantic parsing, in Proc. 2nd Workshop on Representation Learning for NLP, Vancouver, Canada, 2017.
[96]   Silver D. L., Yang Q., and Li L. H., Lifelong machine learning systems: Beyond learning algorithms, in AAAI Spring Symp.: Lifelong Machine Learning, Palo Alto, CA, USA, 2013, p. 5.
[97]   Dauphin Y. N., Tür G., Hakkani-Tür D., and Heck L. P., Zero-shot learning and clustering for semantic utterance classification, in Proc. 2nd Int. Conf. Learning Representations, Banff, Canada, 2014.
[98]   Finn C., Abbeel P., and Levine S., Model-agnostic meta-learning for fast adaptation of deep networks, in Proc. 34th Int. Conf. Machine Learning, Sydney, Australia, 2017, pp. 1126-1135.
[99]   Huang P. S., Wang C. L., Singh R., Yih W. T., and He X. D., Natural language to structured query generation via meta-learning, in Proc. NAACL-HLT 2018, New Orleans, LA, USA, 2018.
[1] Zhenxing Guo, Shihua Zhang. Sparse Deep Nonnegative Matrix Factorization[J]. Big Data Mining and Analytics, 2020, 03(01): 13-28.
[2] Ying Yu, Min Li, Liangliang Liu, Yaohang Li, Jianxin Wang. Clinical Big Data and Deep Learning: Applications, Challenges, and Future Outlooks[J]. Big Data Mining and Analytics, 2019, 2(4): 288-305.
[3] Wenmao Wu, Zhizhou Yu, Jieyue He. A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure[J]. Big Data Mining and Analytics, 2019, 2(3): 205-216.
[4] Jiangcheng Zhu, Shuang Hu, Rossella Arcucci, Chao Xu, Jihong Zhu, Yi-ke Guo. Model Error Correction in Data Assimilation by Integrating Neural Networks[J]. Big Data Mining and Analytics, 2019, 2(2): 83-91.
[5] Jin Liu, Yi Pan, Min Li, Ziyue Chen, Lu Tang, Chengqian Lu, Jianxin Wang. Applications of Deep Learning to MRI Images: A Survey[J]. Big Data Mining and Analytics, 2018, 1(1): 1-18.
[6] Qianyu Meng, Kun Wang, Xiaoming He, Minyi Guo. QoE-Driven Big Data Management in Pervasive Edge Computing Environment[J]. Big Data Mining and Analytics, 2018, 01(03): 222-233.
[7] Ning Yu, Zhihua Li, Zeng Yu. Survey on Encoding Schemes for Genomic Data Representation and Feature Learning—From Signal Processing to Machine Learning[J]. Big Data Mining and Analytics, 2018, 01(03): 191-210.