748 Hits in 6.1 sec

DBPal: Weak Supervision for Learning a Natural Language Interface to Databases [article]

Nathaniel Weir, Andrew Crotty, Alex Galakatos, Amir Ilkhechi, Shekar Ramaswamy, Rohin Bhushan, Ugur Cetintemel, Prasetya Utama, Nadja Geisler, Benjamin Hättasch, Steffen Eger, Carsten Binnig
2019 arXiv   pre-print
In order to avoid this issue, DBPal implements a novel training pipeline based on weak supervision that synthesizes all training data from a given database schema.  ...  While other recent approaches use neural machine translation to implement a Natural Language Interface to Databases (NLIDB), existing techniques rely on supervised learning with manually curated training  ...  As a second baseline, we also used NaLIR [11, 10] , a state-of-the-art rule-based NLIDB that requires no training data to support a new schema.  ... 
arXiv:1909.06182v1 fatcat:gvoe4rtymfesdpeqlbmj7xlgii

Efficient Deployment of Conversational Natural Language Interfaces over Databases [article]

Anthony Colas, Trung Bui, Franck Dernoncourt, Moumita Sinha, Doo Soon Kim
2020 arXiv   pre-print
We train two current state-of-the-art NL-to-QL models, on both an SQL and SPARQL-based datasets in order to showcase the adaptability and efficacy of our created data.  ...  Our system allows one to generate conversational multi-term data, where multiple turns define a dialogue session, enabling one to better utilize chatbot interfaces.  ...  To generate such pairs, the NL-QL generator takes in each LF from the LF Dialog as input.  ... 
arXiv:2006.00591v2 fatcat:u3xdhyfhsrgrpebwudw2qnz7pu

An End-to-end Neural Natural Language Interface for Databases [article]

Prasetya Utama, Nathaniel Weir, Fuat Basik, Carsten Binnig, Ugur Cetintemel, Benjamin Hättasch, Amir Ilkhechi, Shekar Ramaswamy, Arif Usta
2018 arXiv   pre-print
In this paper, we present DBPal, a novel data exploration tool with a natural language interface.  ...  Natural language has recently gained traction as an alternative query interface to databases with the potential to enable non-expert users to formulate complex questions and information needs efficiently  ...  In the first data generation step (called Generator in Figure 3 ), we use the database schema along with a set of base templates that describe NL-SQL pairs and so called 'slot-filling' dictionaries to  ... 
arXiv:1804.00401v1 fatcat:hblzvhczajcmzi3suknmk6tuhy


Fuat Basik, Benjamin Hättasch, Amir Ilkhechi, Arif Usta, Shekar Ramaswamy, Prasetya Utama, Nathaniel Weir, Carsten Binnig, Ugur Cetintemel
2018 Proceedings of the 2018 International Conference on Management of Data - SIGMOD '18  
In this demo, we present DBPal, a novel data exploration tool with a natural language interface.  ...  to SQL, making the translation process more robust to paraphrasing and linguistic variations.  ...  ACKNOWLEDGEMENTS This research is funded in part by NSF Awards IIS-1526639 and IIS-1514491, as well as gifts from Google.  ... 
doi:10.1145/3183713.3193562 dblp:conf/sigmod/BasikHIURUWBC18 fatcat:dgjqy2ac4jguxnsfj5qziybzpy

Quda: Natural Language Queries for Visual Data Analytics [article]

Siwei Fu, Kai Xiong, Xiaodong Ge, Siliang Tang, Wei Chen, Yingcai Wu
2020 arXiv   pre-print
With the release of Quda, we hope it will boost the research and development of V-NLIs in data analysis and visualization.  ...  We achieve this goal by first gathering seed queries with data analysts and then employing extensive crowd force for paraphrase generation and validation.  ...  Sisl [12] is a multi-modal interface that accepts various input modes, including point-and-click interface, NL input in textual form, and NL using speech.  ... 
arXiv:2005.03257v5 fatcat:gzp57l5p75gbblpz3khwoilkkm

Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge [article]

Nicholas Locascio, Karthik Narasimhan, Eduardo DeLeon, Nate Kushman, Regina Barzilay
2016 arXiv   pre-print
In contrast to prior work, the proposed neural model does not utilize domain-specific crafting, learning to translate directly from a parallel corpus.  ...  To fully explore the potential of neural models, we propose a methodology for collecting a large corpus of regular expression, natural language pairs.  ...  Early research into this task used rule-based techniques to create a natural language interface to regular expression writing (Ranta, 1998) .  ... 
arXiv:1608.03000v1 fatcat:kg3i4y56nrboxcznzl635ywuky

Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge

Nicholas Locascio, Karthik Narasimhan, Eduardo De Leon, Nate Kushman, Regina Barzilay
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
In contrast to prior work, the proposed neural model does not utilize domain-specific crafting, learning to translate directly from a parallel corpus.  ...  To fully explore the potential of neural models, we propose a methodology for collecting a large corpus 1 of regular expression, natural language pairs.  ...  Acknowledgments We thank the anonymous reviewers for their helpful feedback and suggestions.  ... 
doi:10.18653/v1/d16-1197 dblp:conf/emnlp/LocascioNDKB16 fatcat:7l5g6u45evfknpoh22nofwso4a

Natural language interactions with artificial experts

T.W. Finin, A.K. Joshi, B.L. Webber
1986 Proceedings of the IEEE  
ACKNOWLEDGMENT The authors like to thank their referee for his or her excellent comments. They would also like to thank those people whose work they have reported on here: Kathy M c K e o w n , R.  ...  Both of these paraphrases are produced by the same NL generator.  ...  Our position is that support for these NL capabilities cannot come solely from the NL interface itself: that in many cases, the underlying reasoning system and knowledge base will have to be adapted or  ... 
doi:10.1109/proc.1986.13572 fatcat:f3kt3zlbabe25midjmae7nt7mm

Building Natural Language Interfaces to Web APIs

Yu Su, Ahmed Hassan Awadallah, Madian Khabsa, Patrick Pantel, Michael Gamon, Mark Encarnacion
2017 Proceedings of the 2017 ACM on Conference on Information and Knowledge Management - CIKM '17  
As the Web evolves towards a service-oriented architecture, application program interfaces (APIs) are becoming an increasingly important way to provide access to data, services, and devices.  ...  We propose a novel approach to collect training data for NL2API via crowdsourcing, where crowd workers are employed to generate diversiied NL commands.  ...  NLIs rely on supervised training data, consisting of NL command-API call pairs in the case of NL2API, to learn the semantic mapping from NL commands to the corresponding formal representations [32] .  ... 
doi:10.1145/3132847.3133009 dblp:conf/cikm/SuAKPGE17 fatcat:jxeytrhvyna6jhyzbmf4iikxoe

On The Ingredients of an Effective Zero-shot Semantic Parser [article]

Pengcheng Yin, John Wieting, Avirup Sil, Graham Neubig
2021 arXiv   pre-print
Such models are typically bottlenecked by the paucity of training data due to the required laborious annotation efforts.  ...  Recent studies have performed zero-shot learning by synthesizing training examples of canonical utterances and programs from a grammar, and further paraphrasing these utterances to improve linguistic diversity  ...  What, When, How many, based on the answer type) to half hypotheses in the beam to generate question paraphrases (e.g. paraphrases prefixed with “How many” for u3 in Fig. 1).  ... 
arXiv:2110.08381v1 fatcat:xw4l4jg6fbhxxbh5f2xdrtzuvq


Seungyeop Han, Matthai Philipose, Yun-Cheng Ju
2013 Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing - UbiComp '13  
We have realized our design fully as an extension to the Visual Studio IDE.  ...  This paper presents the design and implementation of a programming system that enables third-party developers to add spoken natural language (SNL) interfaces to standalone mobile applications.  ...  , Madhu Chintagunta for access to server-based recognizers and Jitu Padhye for discussions on metrics for evaluating NLify.  ... 
doi:10.1145/2493432.2493458 dblp:conf/huc/HanPJ13 fatcat:miul72dn6rg3lf3yznroy3z32m

Lexical paraphrasing for document retrieval and node identification

Ingrid Zukerman, Sarah George, Yingying Wen
2003 Proceedings of the second international workshop on Paraphrasing -  
Node identification -performed in the context of a Bayesian argumentation system -matches users' Natural Language sentences to nodes in a Bayesian network.  ...  Lexical paraphrases are generated using syntactic, semantic and corpus-based information. Our evaluation shows that lexical paraphrasing improves retrieval performance for both applications.  ...  Acknowledgments This research was supported in part by grants A49927212 and DP0209565 from the Australian Research Council.  ... 
doi:10.3115/1118984.1118997 dblp:conf/acl-iwp/ZukermanGW03 fatcat:ur5424nb2rcehjkoqyzvjeytoy

The SAL Representation Language [chapter]

Bernard Scott
2018 Translation, Brains and the Computer  
The adaptation of Open-Logos resources to a specific application concerning paraphrasing in Portuguese is also described here. References are provided for access to OpenLogos and to SAL.  ...  This paper describes OpenLogos, a rule-driven machine translation system, and the syntactic-semantic taxonomy SAL that underlies this system.  ...  In this, SAL elements of the input stream serve as search arguments, in a similar way as NL words do in conventional dictionary look-up.  ... 
doi:10.1007/978-3-319-76629-4_9 fatcat:ttty6dagwjhkbgbpigylststly

Rule based Domain Specific Semantic Analysis for Natural Language Interface for Database

Probin Anand, Zuber Farooqui
2017 International Journal of Computer Applications  
All our data is stored in a database and there are multiple ways to interact with the database to access our data. A user needs some technical knowledge to extract data from the database.  ...  In this paper, I will show you how to develop an effective and simple interface for a non-technical user to interact with their database in their natural language.  ...  The users request in English is generated to suitable requests in the underlying system by ASK transparently.  NALIX (2005) is XML based natural language interface.  PRECISE [2] has a compact and interesting  ... 
doi:10.5120/ijca2017913502 fatcat:ayhtcuhrsvaizj3i6jyuiwx3ii

NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation [article]

Kaustubh D. Dhole, Varun Gangal, Sebastian Gehrmann, Aadesh Gupta, Zhenhao Li, Saad Mahamood, Abinaya Mahendiran, Simon Mille, Ashish Srivastava, Samson Tan, Tongshuang Wu, Jascha Sohl-Dickstein (+113 others)
2021 arXiv   pre-print
In this paper, we present NL-Augmenter, a new participatory Python-based natural language augmentation framework which supports the creation of both transformations (modifications to the data) and filters  ...  Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.  ...  interfaces and the base repository NL- Jiaao Chen, Derek Tam, Colin Raffel, Mohit Bansal, Augmenter for participants to contribute.  ... 
arXiv:2112.02721v1 fatcat:uqizuxc4wzgxnnfsc6azh6ckpq
« Previous Showing results 1 — 15 out of 748 results