Stanford CoreNLP & Question Answering 2017


Notes:

Stanford CoreNLP toolkit is an extensible pipeline that provides core natural language analysis.

The framework integrates many Stanford NLP tools, including:

  • the part-of-speech (POS) tagger,
  • the named entity recognizer (NER),
  • the parser,
  • the coreference resolution system,
  • the sentiment analysis,
  • and the bootstrapped pattern learning tools.

Resources:

  • askplatyp.us .. query engine resulting from master’s degree project of seven students
  • huric .. human robot interaction corpus
  • projetpp.github.io .. modular and open source question answering framework
  • reassistant.googlecode.com .. support tool for analyzing software requirements specifications

See also:

100 Best Stanford NLP VideosStanford ClassifierStanford NLP & Dialog SystemsStanford Parser & Dialog SystemsStanford Tregex


Reading wikipedia to answer open-domain questions
D Chen, A Fisch, J Weston, A Bordes – arXiv preprint arXiv:1704.00051, 2017 – arxiv.org
… Document Reader 833,500 Document Retriever Figure 1: An overview of our question answering system DrQA … We ap- ply the Stanford CoreNLP toolkit (Manning et al., 2014) for tokenization and also generating lemma, part-of-speech, and named entity manual features …

Neural Question Generation from Text: A Preliminary Study
Q Zhou, N Yang, F Wei, C Tan, H Bao… – National CCF Conference …, 2017 – Springer
… We use Stanford CoreNLP v3.7.0 2 [13] to annotate POS and NER tags in sentences with its default configuration and pre-trained models … In future work, we would like to investigate whether the automatically generated questions can help to improve question answering systems …

Review on the advancements of disambiguation in semantic question answering system
S Hazrina, NM Sharef, H Ibrahim, MAA Murad… – Information Processing …, 2017 – Elsevier
… 2. Semantic question answering system … For example, Hakimov et al. (2013) utilizes Stanford CoreNLP (SCNLP) to determine the part-of-speech of each NL word, word dependencies, named entity recognition (NER) and the subject/object of each NL question …

Multimodal question answering over structured data with ambiguous entities
H Li, Y Wang, G de Melo, C Tu, B Chen – Proceedings of the 26th …, 2017 – dl.acm.org
… Early expert systems and question answering systems, such as BASEBALL [16], SHRDLU [30] and LUNAR [31], were limited to a very specific domain … To find possible ?n, a1, a2?, we choose edges in T1 with specific Stanford Dependency tags …

A passage retrieval method based on probabilistic information retrieval model and UMLS concepts in biomedical question answering
M Sarrouti, SO El Alaoui – Journal of biomedical informatics, 2017 – Elsevier
… Highlights. • A new passage retrieval method is proposed for biomedical question answering system. • It is based on PubMed and UMLS similarity to retrieve relevant documents. • Stanford CoreNLP sentence length is used as passage length in this work. • …

A machine learning-based method for question type classification in biomedical question answering
M Sarrouti, SO El Alaoui – Methods of information in medicine, 2017 – thieme-connect.com
… 2015; 20 Neves M. HPI question answering system in the BioASQ 2015 challenge … In: CLEF 2015. 2015; 35 Manning C, Surdeanu M, Bauer J, Finkel J, Bethard S, McClosky D. The Stanford CoreNLP Natural Language Processing Toolkit …

MIT at SemEval-2017 Task 10: Relation Extraction with Convolutional Neural Networks
JY Lee, F Dernoncourt, P Szolovits – arXiv preprint arXiv:1704.01523, 2017 – arxiv.org
… Extracted relations can be used for a variety of tasks such as question-answering systems (Ravichandran and Hovy, 2002), ontol- ogy extension … Sentence and token boundaries as well as POS tags are detected using the Stanford CoreNLP toolkit (Manning et al., 2014), and …

Split and rephrase
S Narayan, C Gardent, SB Cohen… – arXiv preprint arXiv …, 2017 – arxiv.org
… To achieve this, we proceed in three main steps as follows. Sentence segmentation We first preprocess all 13,308 distinct verbalisations contained in the WEBNLG corpus using the Stanford CoreNLP 4We use a version from February 2017 given to us by the authors …

Natural Language Processing Based Question Answering Using Vector Space Model
R Jayashree, N Niveditha – … of Sixth International Conference on Soft …, 2017 – Springer
… In most of the basic question answering system there are three basic set of modules for the functionality and they are described as: 1. Question Analysis module … Open NLP, Stanford Core NLP Parser are some of the tools used for this Processing …

NLCI: a natural language command interpreter
M Landhäußer, S Weigelt, WF Tichy – Automated Software Engineering, 2017 – Springer
… It uses Stanford CoreNLP (Manning et al … The authors also use Stanford parse trees to extract words from the user input to create SPARQL queries … Unger and Cimiano demand that question answering systems need “to bridge the gap between the user and the data […] Unger …

What Do You Mean Exactly?: Analyzing Clarification Questions in CQA
P Braslavski, D Savenkov, E Agichtein… – Proceedings of the 2017 …, 2017 – dl.acm.org
… [7] CD Manning et al. The Stanford CoreNLP natural language processing toolkit. In ACL System Demonstrations’2014. [8] S. Quarteroni and S. Manandhar. Designing an interactive open-domain question answering system. Natural Language Engineering, 15(01):73–95, 2009 …

An effective corpus-based question answering pipeline for Italian
E Damiano, R Spinelli, M Esposito… – … Conference on Intelligent …, 2017 – Springer
… However, building Question Answering systems for Italian and able to extract answers from a corpus pertaining a closed domain is … exploiting UIMA (Unstructured Information Management Architecture) 1 and it relies on different NLP tools, like Stanford CoreNLP, OpenNLP, and …

Grounding proposition stores for question answering over linked data
B Cabaleiro, A Peñas, S Manandhar – Knowledge-Based Systems, 2017 – Elsevier
… 2. Architecture of the question answering system. 3.1. Text processing … Proposition store building. Sentences from the ClueWeb09 Corpus are processed with Stanford CoreNLP [22] to obtain dependency trees which are also annotated with part-of-speech and coreferences [23] …

Natural Language Understanding (NLU, not NLP) in Cognitive Systems.
M McShane – AI Magazine, 2017 – search.ebscohost.com
… and system setups that circumvent the need for language understanding. For example, consider a question-answering system that has access to a large and highly redundant corpus. When asked to indi- cate when the city of …

Towards a unifying framework for conceptual represention and reasoning in cognitive systems
A Lieto, D Radicioni, V Rho, E Mensa – Intelligenza Artificiale, 2017 – content.iospress.com
… extraction of the linguistic input is not implemented in the two cognitive architectures, but it relies on the CoreNLP Stanford Parser [43], which … by the search engines, and not only the first one, since we are aware that these systems are not standard Question-Answering Systems …

A Biomedical Question Answering System in BioASQ 2017
M Sarrouti, SO El Alaoui – BioNLP 2017, 2017 – aclweb.org
… answering system of kangwon national university and sogang university in the 2016 BioASQ chal- lenge. ACL 2016 page 45. Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David Mc- Closky. 2014. The stanford CoreNLP natural …

Forst: Question Answering System for Term and Essay Questions at NTCIR-13 QA Lab-3 Task
K Sakamoto, M Ishioroshi, Y Fukuhara, A Iizuka… – research.nii.ac.jp
… Retrieving passages using the passage retrieval module of the term question answering system … The system is the same as the Japanese first sys- tem. However, the knowledge source is translated by Google translation, and Stanford CoreNLP [4] is used for parsing …

Self-learning improvement by means of cloud computing
GCÄ Deac, CN Deac, CE Cotet, M Ghinea – International Conference on …, 2017 – icesba.eu
… Question Answering System … The Document Reader component is implemented using a 3-layer bidirectional LSTMs (Long Short-Term Memory) with h=128 hidden units for both paragraph and question encoding applying the tokenizers (Stanford CoreNLP and Spacy), and …

DGLab Question Answering System and Automatic Evaluation Method at NTCIR-13 QA Lab-3 for University Entrance Exam on World History Essay
MTJ Jiang – pdfs.semanticscholar.org
… definition of passage, although paragraphs or ranged/overlapped sentences are often applied in factoid question-answering systems, this study … or stop-word filtering, while sentence segmentation by spaCy6, Penn Treebank style tokenization by Stanford CoreNLP, and Krovetz …

A Syntactic Approach to Domain-Specific Automatic Question Generation
G Danon, M Last – arXiv preprint arXiv:1712.09827, 2017 – arxiv.org
… trigger to ask the ques- tion (relevant mostly to dialogs and question- answering systems), 2) text … Heilman employs some core NLP tools in his system in order to analyze the linguis … We retrieve the head nouns of the answer phrases using Stanford CoreNLP library (Manning et al …

A Yes/No Answer Generator Based on Sentiment-Word Scores in Biomedical Question Answering
M Sarrouti, SO El Alaoui – International Journal of Healthcare …, 2017 – igi-global.com
… basedonsentiment- wordscoresinbiomedicalQA.Methods:Intheproposedmethod,wefirstuse theStanfordCoreNLP fortokenizationand … andbrowsing timewhilemaximizingtheusefulnessof thatknowledgeisagrowinginterestforbiomedicalquestion answering systems (Bauer & …

ScoQAS: A Semantic-based Closed and Open Domain Question Answering System
M Latifi, H Rodríguez Hontoria, M Sànchez-Marrè – 2017 – rua.ua.es
… Figure 1: Architecture of Semantic-based closed and open domain Question Answering System (ScoQAS) … Those of the components which are outside of the cube are external tools reused by ScoQAS such as Stanford CoreNLP parser, Word- Net, and SPARQL query endpoint8 …

Efficiency-aware Answering of Compositional Questions using Answer Type Prediction
D Ziegler, A Abujabal, RS Roy, G Weikum – Proceedings of the Eighth …, 2017 – aclweb.org
… Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David Mc- Closky. 2014. The Stanford CoreNLP natural lan- guage processing toolkit. In ACL … 2002. Learn- ing surface text patterns for a question answering system. In ACL …

End-to-End Representation Learning for Question Answering with Weak Supervision
D Sorokin, I Gurevych – Semantic Web Evaluation Challenge, 2017 – Springer
… Multiple successful question answering systems were presented in the previous QALD competitions [17], as well as in conjunction with other QA datasets [3, 13, 16] … We tokenize it and add part-of-speech tags with the Stanford CoreNLP toolkit [14] …

Evaluating Semantic Parsing against a Simple Web-based Question Answering Model
A Talmor, M Geva, J Berant – arXiv preprint arXiv:1707.04412, 2017 – arxiv.org
… We performed 5 random 70/30 splits of the training set for de- velopment. We computed POS tags and named entities with Stanford CoreNLP (Manning et al., 2014) … An analy- sis of the AskMSR question-answering system. In Association for Computational Linguistics (ACL) …

Question Answering system for the travel domain
H Kahaduwa, D Pathirana, PL Arachchi… – Engineering …, 2017 – ieeexplore.ieee.org
Page 1. 978-1-5090-6491-5/17/$31.00 ©2017 IEEE Question Answering System for the Travel Domain Hasangi Kahaduwa, Dilshan … a statement. The QuestiontoStatementTranslator in the Stanford CoreNLP was used for this. The …

Action Languages and Question Answering
Y Lierler, D Inclezan, M Gelfond – IWCS 2017—12th International …, 2017 – aclweb.org
… Abstract This paper describes a methodology for designing Question Answering systems that utilize an action language ALM to allow inferences based on complex interactions of events described in texts … Stanford CoreNLP a suite of core NLP tools …

Recovering Question Answering Errors via Query Revision
S Yavuz, I Gur, Y Su, X Yan – Proceedings of the 2017 Conference on …, 2017 – aclweb.org
… We eval- uate our method using STAGG (Yih et al., 2015) as the base question answering system … 2014. The stanford corenlp natural lan- guage processing toolkit. In Annual Meeting of the Association for Computational Linguistics: System Demonstrations …

Utilizing typed dependency subtree patterns for answer sentence generation in question answering systems
R Perera, P Nand, A Naeem – Progress in Artificial Intelligence, 2017 – Springer
… Question Answering over Linked Data (QALD) refer to the use of Linked Data by question answering systems, and in recent times this has … In this research, we utilized the Stanford Parser [17], a CFG grammar-based parser which utilizes universal typed dependencies which will …

A semantic approach for question answering using DBpedia and WordNet
K Sengloiluean, N Arch-int, S Arch-int… – … Science and Software …, 2017 – ieeexplore.ieee.org
… question processing since it was considered the very important and prerequisite processing for research on the question answering system which still … of extracting named entities from the questions was solved by using DBpedia spotlight API [10] and Stanford CoreNLP API [11 …

Information Retrieval from a Structured Knowledgebase
P Yadav – euroasiapub.org
… It is a java implemented method and to parse the question, Core NLP toolkit is … Cooper, R., and Ruger, S, (2000): “A simple question answering system”, In Voorhees and Harman … Bauer,J., Finkel,J., Bethard,SJ, and McClosky,D.(2014): “The Stanford CoreNLP Natural Language …

” Let me convince you to buy my product…”: A Case Study of an Automated Persuasive System for Fashion Products
V Munigala, S Tamilselvam, A Sankaran – arXiv preprint arXiv:1709.08366, 2017 – arxiv.org
… Existing question-answering systems and conversation systems are well trained for resolving the facts from the input query and finding … 7]. Next, suitable word replacements are identified by extracting all the nouns, verbs, adjectives, adverbs using Stanford CoreNLP parser from …

A Composite Natural Language Processing and Information Retrieval Approach to Question Answering Using a Structured Knowledge Base
A Chandurkar, A Bansal – International Journal of Semantic …, 2017 – World Scientific
… Hence processing, tagging and parsing the question to make sense out of it is the ?rst step towards development of a good question answering system … Stanford CoreNLP toolkit [16] is used for parsing the question … The stemming is done using Stanford Core NLP package …

Information Retrieval from a Structured KnowledgeBase
A Chandurkar, A Bansal – Semantic Computing (ICSC), 2017 …, 2017 – ieeexplore.ieee.org
… [12] Mcgowan, K. (nd). “Emma : A Natural Language Question Answering System” from www.umich. edu. [13] Barskar, R., et al … [16] Manning, CD, et al. “The Stanford CoreNLP Natural Language Processing Toolkit”. [17] Bizer, C. , et al …

Alquist: An Open-Domain Dialogue System
J Pichl – radio.feld.cvut.cz
… The stanford corenlp natural language processing toolkit … May 2012. Available from: https://www.microsoft.com/en-us/research/publication/probase- a-probabilistic-taxonomy-for-text- understanding/ [18] Baudiš, P. YodaQA: a modular question answering system pipeline …

Using Multi-Label Classification for Improved Question Answering
R Usbeck, M Hoffmann, M Röder, J Lehmann… – arXiv preprint arXiv …, 2017 – arxiv.org
… While these features are clearly handcrafted, we show their ability to effectively determine the question answering systems according to their capabilities as well as to accurately choose the correct … We rely on the Stanford CoreNLP library [13] in our current implementation …

INSTANT ANSWERS, 5W’S & H TOOL
M Faisal, U Waheed, MN Arif – sci-int.com
… REFERENCES [1] http://start.csail.mit.edu/index.php, “START, the world’s first Web-based question answering system” 1993-2013 [2] Borchardt, Gary C. “Understanding causal descriptions of physical systems.” AAAI. 1992 … “The Stanford CoreNLP Natural Language Processing …

ICE: Idiom and Collocation Extractor for Research and Education
S Baki, A Nguyen, R Verma – … of the Software Demonstrations of the …, 2017 – aclweb.org
… Araly Barrera, Rakesh Verma, and Ryan Vincent. 2011. Semquest: University of houston’s semantics- based question answering system. In Proceedings … 2014. The stanford corenlp natural lan- guage processing toolkit. In ACL (System Demon- strations), pages 55–60 …

An Effective Corpus-Based Question Answering Pipeline for Italian
G De Pietro – … Interactive Multimedia Systems and Services 2017, 2017 – books.google.com
… However, building Question Answering systems for Italian and able to extract answers from a corpus pertaining a closed domain is still an … UIMA (Unstructured Information Manage- ment Architecture) 1 and it relies on different NLP tools, like Stanford CoreNLP, OpenNLP, and …

IJCNLP-2017 Task 5: Multi-choice Question Answering in Examinations
S Guo, K Liu, S He, C Liu, J Zhao, Z Wei – Proceedings of the IJCNLP …, 2017 – aclweb.org
… 1 Sim(q, d) where n ? 3 and ifn = 0, score(q, a)=0; All questions and options are preprocessed by Stanford CoreNLP7 … 7https://stanfordnlp.github.io/CoreNLP/ 36 Page 4 … 2017. Ju nitm: A classification approach for answer selec- tion in multi-choice question answering system …

Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation
B Pan, H Li, Z Zhao, D Cai, X He – arXiv preprint arXiv:1711.00179, 2017 – arxiv.org
… A er the Demand Optimization Model is trained, we train the full question answer system end-to-end using the ground-truth answer as label … 5 EXPERIMENT 5.1 Implementation Settings e tokenizers we use in the step of preprocessing data are from Stanford CoreNLP [21] …

Two-step cascaded textual entailment for legal bar exam question answering
MY Kim, R Goebel – Proceedings of the 16th edition of the International …, 2017 – dl.acm.org
… ABSTRACT Our legal question answering system combines legal information retrieval and textual entailment, and exploits semantic information using a logic-based representation … [2] provided the basis for a Yes/No Arabic Question Answering System …

READING COMPREHENSION SYSTEM–A REVIEW
KM ARIVUCHELVAN, K LAKAHMI – Indian J. Sci. Res, 2017 – ijsr.in
… (2013) focused on Multiple Choice Question answering system for entrance … Preprocessing are done through all standard NLP tools such as sentence splitting (OpenNLP), tokenization (Stanford CoreNLP), PoS Tagging and stemming (TreeTagger) synonym extraction (WordNet …

Male or female: What traits characterize questions prompted by each gender in community question answering?
A Figueroa – Expert Systems with Applications, 2017 – Elsevier
… Broadly speaking, community Question Answering (cQA) sites distinguish from other sorts of question-answering systems not only by allowing their members to post a … To be more exact, we capitalized on CoreNLP 6 for the following linguistic processing (Manning et al., 2014): • …

Ontology-based information extraction from learning management systems
RB Deyab – 2017 – dspace.uevora.pt
… nltk.org/ 14http://nlp.stanford.edu/ 15http://nlp.stanford.edu:8080/corenlp … Stanford Dependency Parser: presented in [CM14], uses Neural Network approach … Question answering systems: these systems works on extracting understandable machine commands from a natural …

Graph Enhanced Memory Networks for Sentiment Analysis
Z Xu, R Vial, K Kersting – Joint European Conference on Machine Learning …, 2017 – Springer
… In general, the input and the generalization modules map the facts and the question q (eg a question sentence for a question-answering system) into a feature … The graph structure of a sentence, used in the proposed approach, is extracted with Stanford’s CoreNLP Toolkit [27] …

Modelling semantic relations with distributitional semantics and deep learning: question answering, entailment recognition and paraphrase detection
V Maraev – 2017 – repositorio.ul.pt
… in a natural language, and not just as a sequence of keywords. Over the years, a great variety of question answering systems have been created … 1 Page 14. Introduction There are dozens of textual question answering systems described in the literature …

Relation Extraction and Its Application to Question Answering
Y Xu – 2017 – era.library.ualberta.ca
… It is also an example of compound artificial nodes. . . . 79 6.2 Our open question answering system structure. . . . . 83 x … relations between named entities, where the entities are detected by a more sophisticated NLP tool, the Stanford NER [Finkel et al., 2005]. According to …

Learning to Solve Geometry Problems from Natural Language Demonstrations in Textbooks
M Sachan, E Xing – Proceedings of the 6th Joint Conference on Lexical …, 2017 – aclweb.org
… In this paper, we raise the question – “Can we leverage demonstrative solu- tions for questions as provided by a teacher to im- prove our question answering systems?” … We used Stanford CoreNLP (Manning et al., 2014) for linguistic pre-processing …

Building Structured Databases of Factual Knowledge from Massive Text Corpora
X Ren, M Jiang, J Shang, J Han – Proceedings of the 2017 ACM …, 2017 – dl.acm.org
… Downstream applications A. Knowledge base completion B. Question answering systems (b) Traditional supervised RE systems i. Supervised RE methods A. Supervised models B. Features for relation extraction C … The stanford corenlp natural language processing toolkit …

If No Media Were Allowed inside the Venue, Was Anybody Allowed?
Z Sarabi, E Blanco – Proceedings of the 15th Conference of the …, 2017 – aclweb.org
… For example, a question answering system would benefit from interpretation (1b) when answering question Did John ever earn a steady paycheck … We trans- formed the parse trees into syntactic dependencies using Stanford CoreNLP (Manning et al., 2014) …

Using Rich Inference to Find Novel Answers to Questions
K Nuamah, A Bundy, C Lucas – pdfs.semanticscholar.org
… 8, no. 12, pp. 792–798, 1965. [19] RF Simmons, “Natural language question-answering systems: 1969,” Communications of the ACM, vol. 13, no. 1, pp … [28] CD Manning, M. Surdeanu, J. Bauer, J. Finkel, SJ Bethard, and D. McClosky, “The Stanford CoreNLP Natural Language …

A Hybrid Approach for Biomedical Relation Extraction Using Finite State Automata and Random Forest-Weighted Fusion
T Mavropoulos, D Liparas, S Symeonidis, S Vrochidis… – researchgate.net
… is considered to be a very important task, due to the multitude of applications that it can support, from question answering systems to the … The morphosyntactic features include the POS (extracted by the Stanford CoreNLP suite [22]) of the lexical units in question, the number of …

Semantic query graph based SPARQL generation from natural language questions
S Song, W Huang, Y Sun – Cluster Computing, 2017 – Springer
… scale knowledge base like Freebase and DBpedia has been come to an important semantic database for supporting open domain question answering systems (QASs) … For example “What is the name of football clubs in EEFA?”, we use Stanford CoreNLP to syntactic analysis …

Community graph and linguistic analysis to validate relationships for knowledge base population
R Rahman, B Grau, S Rosset – 4th International Symposium on …, 2017 – ceur-ws.org
… Some question-answering systems mea- sured point-wise mutual information (Magnini et al., 2002), (Cui et al., 2005) to exploit redun- dancy … Recognition of named entities is done us- ing Stanford system (Manning et al., 2014) and Luxid2 …

A natural language interface to a graph-based bibliographic information retrieval system
Y Zhu, E Yan, IY Song – Data & Knowledge Engineering, 2017 – Elsevier
… Some NER systems use more than one type of NER: for example, Stanford NER [20] provides both dictionary- and statistical-based NER through a gazette feature … We use Stanford PTBTokenizer [30] in this work. Table 1. Tokenization without NER and with NER …

Tuning SyntaxNet for POS Tagging Italian Sentences
F Marulli, M Pota, M Esposito, A Maisto… – … Conference on P2P …, 2017 – Springer
… Part-of-speech (POS) tagging is a Natural Language Processing (NLP) technique extremely relevant in Question Answering systems and becomes … doi:10.1002/9781119992691.ch6. 7. Aprosio, AP, Moretti, G.: Italy goes to Stanford: a collection of CoreNLP modules for …

Semantic/Content Analysis/Natural Language Processing
P Nulty – Encyclopedia of Big Data, 2017 – Springer
… On the other hand, some applications, such as the IBM Watson question answering system (Ferruci et al … The python libraries spaCy and gensim and the Java-based Stanford Core NLP software are widely used in industry and academia …

Natural language understanding and communication for human-robot collaboration
MI Bloch – ipvs.informatik.uni-stuttgart.de
… There are natural language systems, like IBM’s question answering system Wat- son [Fer+10], which seem to achieve this … [RLS14] introduces a data driven approach for a question answering system for querying Freebase in natural language …

Reinforcement Learning Based Conversational Search Assistant
M Aggarwal, A Arora, S Sodhani… – arXiv preprint arXiv …, 2017 – arxiv.org
… a minimal set of questions but these have not been designed and evaluated on tasks involving human interaction in a search task [1]. Question answering systems are closely … 3User the message is parsed using Stanford CoreNLP v3.6.0 toolkit available at http://stanfordnlp …

Chinese temporal relation resolution based on Chinese-English parallel corpus
L Li, J Zhang, Y He, H Wang – International Journal of …, 2017 – inderscienceonline.com
… TimeML has been widely applied to the TRR research in question answering system, machine translation and other fields in AI. Page 3 … Currently, SUTime is available as part of the Stanford CoreNLP pipeline and it can be used to annotate documents with temporal information …

Computational Natural Language Inference: Robust and Interpretable Question Answering
RR Sharp – 2017 – search.proquest.com
Computational Natural Language Inference: Robust and Interpretable Question Answering. Abstract. We address the challenging task of computational natural language inference, by which we mean bridging two or more natural …

Programming bots by synthesizing natural language expressions into API invocations
S Zamanirad, B Benatallah, M Chai Barukh… – Proceedings of the …, 2017 – dl.acm.org
… from Augur [23] which is a knowledge graph of human actions, activities and their relation with objects; KnowBot [24] a question-answer system that builds … 14] CD Manning, M. Surdeanu, J. Bauer, J. Finkel, SJ Bethard, and D. McClosky, “The Stanford CoreNLP natural language …

Using Extended Tree Kernel to Recognize Metalanguage in Text
BA Galitsky – Uncertainty Modeling, 2017 – Springer
… expense which is the base for our classification. We used Stanford Core NLP, coreferences resolution [19] and its visualization to form Figs. 1 and 2. Figure 8 shows the resultant extended tree with the root ‘I’ from the first sentence …

Summa at tac knowledge base population task 2017
A Mendes, D Nogueira, S Broscheit, F Aleixo… – Proc …, 2017 – tecnico.ulisboa.pt
… model from 10 runs with randomly initialized weights; for Spanish, we train a multilin- gual model using both Spanish and English train data; and for the Chinese submission, we used the Stanford CoreNLP (Manning et al … Priberam’s question answering system in qa@ clef 2008 …

Identifying the Provision of Choices in Privacy Policy Text
KM Sathyendra, S Wilson, F Schaub… – Proceedings of the …, 2017 – aclweb.org
… Furthermore, extracted choice options can be presented to users in more concise and usable notice formats (Schaub et al., 2015), such as a browser plug-in or a privacy based question answering system … 2014. The Stanford CoreNLP natural lan- guage processing toolkit …

CoType: Joint extraction of typed entities and relations with knowledge bases
X Ren, Z Wu, W He, M Qu, CR Voss, H Ji… – Proceedings of the 26th …, 2017 – dl.acm.org
… Once ex- tracted, such structured information is used in many ways, eg, as primitives in information extraction, knowledge base popula- tion [10, 52], and question-answering systems [48, 3]. Traditional systems for relation extraction [2, 9, 17] partition the process into several …

A framework for an adaptable and personalised e-learning system based on free web resources
E Aeiad – 2017 – usir.salford.ac.uk
… 16 2.1.2.4 Stanford CoreNLP ….. 17 … 77 Figure 4-13 Stanford CoreNLP ….. 78 Figure 4-14 XML format generated by Stanford CoreNLP….. 79 …

Event Extraction for Document-Level Structured Summarization
A Hsi – 2017 – cs.cmu.edu
Page 1. June 28, 2017 DRAFT Event Extraction for Document-Level Structured Summarization Andrew Hsi June 2017 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee: Yiming …

Disambiguating Spatial Prepositions Using Deep Convolutional Networks.
K Hassani, WS Lee – AAAI, 2017 – aaai.org
… actions, natural language interfaces, machine vision, text- to-scene conversion systems, geographical information systems, question answering systems, search engines … the preposition and the words: DE: [dep(wi-k, wi),…Null,…,dep(wi+k, wi)] Stanford CoreNLP toolkit (Manning …

Relation Enhanced Neural Model for Type Classification of Entity Mentions with a Fine-Grained Taxonomy
KY Cui, PJ Ren, ZM Chen, T Lian, J Ma – Journal of Computer Science …, 2017 – Springer
Page 1. Cui KY, Ren PJ, Chen ZM et al. Relation enhanced neural model for type classification of entity mentions with a fine- grained taxonomy. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 32(4): 814–827 July 2017. DOI 10.1007/s11390-017-1762-7 …

Domain adaptation for automatic detection of speculative sentences
S Štajner, G Glavaš, SP Ponzetto… – … (ICSC), 2017 IEEE …, 2017 – ieeexplore.ieee.org
… between factual and non-factual, uncertain or speculative sentences, eg summarisation and question answering systems [9], deception … all sentences (and lists of triggers, where used) were first lemmatised with the Stanford Core NLP lemmatiser: http … github.io/CoreNLP …

Machine-Translation History and Evolution: Survey for Arabic-English Translations
NT Alsohybe, NA Dahan, FM Ba-Alwi – arXiv preprint arXiv:1709.04685, 2017 – arxiv.org
Page 1. _____ *Corresponding author: E-mail: alsohybe@gmail.com; Coauthor Email: neama.abdulaziz@gmail.com, dr.fadlbaalwi@gmail.com; …

Framing qa as building and ranking intersentence answer justifications
P Jansen, R Sharp, M Surdeanu, P Clark – Computational Linguistics, 2017 – MIT Press
… Finally, we round out our discussion of question answering systems with a comparison to the famous Watson QA system, which achieved performance on par with the human champions in the Jeopardy! game (Ferrucci 2012) …

Dual PECCS: a cognitive system for conceptual representation and categorization
A Lieto, DP Radicioni, V Rho – Journal of Experimental & …, 2017 – Taylor & Francis
… 27, 137–152.[Taylor & Francis Online], [Web of Science ®] [Google Scholar]) show that the resulting system also provides advances in performing common-sense categorization of linguistic descriptions compared with state-of-the-art question–answering systems (including Bing …

Comparative opinion mining: a review
KD Varathan, A Giachanou… – Journal of the Association …, 2017 – Wiley Online Library
… There is also research on comparative sentiment identification through the use of logics (Ballard, 1988; Rayner & Banks, 1990; Von Stechow, 1984). Work reported in Friedman (1989) used comparatives in question answering systems …

Towards the Implementation of an Intelligent Software Agent for the Elderly
AHF Dinevari – 2017 – era.library.ualberta.ca
… 24 4.1 An example of a triple extracted by Stanford Open IE … Having the appropriate response is crucial. • Question Answering: System should be able to answer personal and general questions, which may need a reasoning on different knowledge bases …

Challenges as enablers for high quality Linked Data: insights from the Semantic Publishing Challenge
A Dimou, S Vahdati, A Di Iorio, C Lange… – PeerJ Computer …, 2017 – peerj.com
… Like us, Lopez et al. present the definition of the QALD challenge’s tasks and the datasets used, and draw conclusions for the subsequent evaluation of question answering systems from reviewing concrete results of the first two challenge editions …

Temporally Biased Search Result Snippets
J Tatineni Abhiram – corescholar.libraries.wright.edu
… 3.1 Temporal tagging TimeML was proposed during the 2002 TERQAS (Time and Event Recognition for Question Answering Systems) workshop which mainly focused on understanding and … values in text [5]. It is an integral part of Stanford CoreNLP. This rule based temporal …

Sentiment Analysis and Social Cognition Engine (SEANCE): An automatic tool for sentiment, social cognition, and social-order analysis
SA Crossley, K Kyle, DS McNamara – Behavior research methods, 2017 – Springer
… For instance, in question-answering systems, knowing the opinions of different sources can provide better answers to users (Stoyanov, Cardie … also includes the Stanford POS tagger (Toutanova, Klein, Manning, & Singer, 2003) as implemented in Stanford CoreNLP (Manning …

Constructing Sentences from Text Fragments: Aggregation in Text-to-text Generation
V Chenal – 2017 – digitool.library.mcgill.ca
… The constituent tree was converted into a dependency tree using the Stanford CoreNLP framework (Manning et al. 2014) … into dependency trees using the Stanford CoreNLP framework (Manning et al. 2014) (see Chapter 4). 3.2 SENTENCE COMPRESSION …

Propositional Knowledge: Acquisition and Application to Syntactic and Semantic Parsing
B Cabaleiro Barciela – 2017 – e-spacio.uned.es
… apposition. Regarding semantic parsing, we build a lexicon that permits to map natural language utterances in the form of propositions with linked data relations, and show how to use this resource in a question answering system …

Commonsense Knowledge for 3D Modeling: A Machine Learning Approach
K Hassani – 2017 – ruor.uottawa.ca
Page 1. Commonsense Knowledge for 3D Modeling: A Machine Learning Approach Kaveh Hassani Thesis submitted to the Faculty of Graduate and Postdoctoral Studies In partial fulfillment of the requirements for the degree Doctor of Electrical and Computer Engineering …

AUTOMATED SEMANTIC QUERY FORMULATION USING MACHINE LEARNING APPROACH.
RA Kadir, A RUFAI YAURI – Journal of Theoretical & Applied …, 2017 – search.ebscohost.com
… This research used Stanford’s CoreNLP Java library for lemmatization. After lemmatization, the imput query is then parse to part of speech tagger and assigns parts of speech to each word token, such as adjectives, nouns, prepositions, or verbs …

Sequential short-text classification with neural networks
F Dernoncourt – 2017 – dspace.mit.edu
Page 1. Sequential Short-Text Classification MAOT ITUTEl OF TECHNQLOGY with Neural Networks JUN 23 201 by Franck Dernoncourt ARCHiVES Submitted to the Department of Electrical Engineering and Computer Science …

Sqlizer: Query synthesis from natural language
N Yaghmazadeh, Y Wang, I Dillig, T Dillig – Proceedings of the ACM on …, 2017 – dl.acm.org
… 2013], which is a toolkit for building semantic parsers. For the linguistic processor, we leverage the pre-trained models of the Stanford CoreNLP [Manning et al. 2014] library for part-of-speech tagging and named entity recognition …

Weighted Networks: Applications from Power grid construction to crowd control
TC McAndrew – 2017 – search.proquest.com
… Named Entity Recognition (NER) was performed using the 4-class, distributional similarity tagger provided as part of the Stanford CoreNLP v3.6.0 toolkit [110] … We used the sentiment classier [156] included in the Stanford CoreNLP v3.6.0 toolkit to documents in each corpus …

CQAVis: Visual Text Analytics for Community Question Answering
E Hoque, S Joty, L Marquez, G Carenini – Proceedings of the 22nd …, 2017 – dl.acm.org
… Similar results were found for a social-question-answering system, with 64.7% of the queries were found to … is likely to be a relevant answer to the new question.4 The core NLP component of … shallow syntactic trees for the question and for the comment using the Stanford parser …

Logic-based Approach to Machine Comprehension of Text
P Chabierski, A Russo, M Law – 2017 – imperial.ac.uk
Page 1. Imperial College London Department of Computing MEng Individual Project Logic-based Approach to Machine Comprehension of Text Author: Piotr Chabierski Project Supervisors: Prof. Alessandra Russo Mark Law June 19, 2017 Page 2. Page 3. Abstract …

Information extraction with neural networks
JY Lee – 2017 – dspace.mit.edu
Page 1. Information Extraction with Neural Networks by Ji Young Lee Submitted to the Department of Electrical Engineering and Computer Science in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science at the …

Supervised algorithms for complex relation extraction
G Khirbat – 2017 – minerva-access.unimelb.edu.au
Page 1. THE UNIVERSITY OF MELBOURNE Supervised Algorithms for Complex Relation Extraction Gitansh Khirbat A thesis submitted in total fulfillment for the degree of Master of Philosophy in the School of Computing and …

Hybrid Deep Open-Domain Question Answering
A Aghaebrahimian – ufal.mff.cuni.cz
… Stan- ford Core NLP toolkit is used in this mod- ule … 3.1.3 SQuAD Stanford Question Answering Dataset (SQuAD) (Rajpurkaretal.,2016) is a dataset for QA in the context of MC. It includes 107,785 question-answer pairs posed by crowd workers on 536 Wikipedia articles …

Glossa—A Formal Language as a Mapping Mechanism of NL Sentences into SPN State Machine for Actions/Events Association
A Psarologou, N Bourbakis – International Journal on Artificial …, 2017 – World Scientific
… In our case we use the Stanford CoreNLP toolkid for the production of parse trees. For the extraction of kernels we used our proposed algorithm presented in Figure 1. Then, for each sentence we represent its kernel (one or many) using Glossa language …

Entity-Centric Discourse Analysis and Its Applications
X Wang – 2017 – repository.kulib.kyoto-u.ac.jp
Page 1. Title Entity-Centric Discourse Analysis and Its Applications( Dissertation_ ?? ) Author(s) Wang, Xun Citation Kyoto University (????) Issue Date 2017-11-24 URL https://dx.doi.org/10.14989/doctor.k20777 Right The …

A proposal for an integrated framewoek capable of aggregating IoT data with diverse data types.
MLL Faria – teses.usp.br
… 54 Figure 23 – Question answering system design … API Application Programming Interface AR Augmented Reality BER Bit Error Rate CoreNLP A set of natural language analysis tools DBMS Database Management System DBN Deep Belief Networks …

FrameBase: Enabling integration of heterogeneous knowledge
J Rouces, G de Melo, K Hose – Semantic Web, 2017 – content.iospress.com
… For instance, commercial search engines exploit these KBs to provide direct answers to user queries, while IBM’s Watson question answering system [21,34 … The Stanford CoreNLP library [67] is used to clean XML tags, tokenize, POS-label, and lemmatize the text, and all words …

Advances in Statistical Script Learning
K Erk – cs.utexas.edu
… script models). Robust question-answering systems must be able to infer highly- probable … Bartók never felt fully at home in the USA.5 Suppose we want to build a question-answering system that can answer questions about …

Advances in statistical script learning
K Pichotta – 2017 – repositories.lib.utexas.edu
… script models). Robust question-answering systems must be able to infer highly- probable … Bartók never felt fully at home in the USA.5 Suppose we want to build a question-answering system that can answer questions about …

Detection of Claims and Supporting Evidence in Wikipedia Articles on Controversial Topics
W Mebane – 2017 – libtreasures.utdallas.edu
… In the style of their artificial question answering system, Watson, that defeated top players in the question answering … Defeasible reasoning and nonmonotonic logic The Stanford Encyclopedia of Philosophy gives the following explanation of the meaning of defeasible reasoning …

From Event to Story Understanding
N Mostafazadeh – 2017 – search.proquest.com
… 36. 3.1 Example question and its corresponding relevant information posed to. a question answering system … 39. Figure 3.1: Example question and its corresponding relevant information posed to a. question answering system. system [Mehdi H. Manshadi, 2008] …

Methods and Techniques for Clinical Text Modeling and Analytics
Y Ling – 2017 – search.proquest.com
… First, we process clinical notes to identify words and sentences from clinical notes using Stanford CoreNLP Tool2. During the pre-processing, we use section annotator to identify di erent sections for each clinical note. The section …

Improving Lexical Inference using Context-sensitive Distributional Models with Rich Context Representations
O Melamud – u.cs.biu.ac.il
… It includes phrase pairs from PPDB 2.0 (Ganitkevitch et al., 2013) that were put in sentential contexts and re-annotated taking this context into account. One other related benchmark is Stanford’s Contextual Word Similarity (SCWS) dataset, introduced by Huang et al. (2012) …

Machine Learning Methods for Strategy Research
MH Teodorescu – 2017 – papers.ssrn.com
… developed linguistic corpora for statistical analysis and grammar models for parsers in the 1960s and for question-answering systems in the 1970s and 1980s … natural language processing is Stanford’s CoreNLP. Machine learning package examples for Java …

Exploratory visual text analytics in the scientific literature domain
F Heimerl – 2017 – elib.uni-stuttgart.de
Page 1. Page 2. Page 3. Exploratory Visual Text Analytics in the Scientific Literature Domain Von der Fakultät Informatik, Elektrotechnik und Informationstechnik der Universität Stuttgart zur Erlangung der Würde eines Doktors der Naturwissenschaften (Dr. rer. nat.) …

From Natural
I Pogrebezky – 2017 – idc.ac.il
… Semantic level algorithms focus on the meaning of the given utterance. For example, in question-answering systems, in order to capture the knowledge and make reasoning possible, the knowledge is usually captured by some formal logic that supports the reasoning process …

Pronominal anaphora and verbal tenses in machine translation
S Loaiciga Sanchez – 2017 – archive-ouverte.unige.ch
… account for all the non-pronominal translations. Working with the Stanford Maximum … pour tenir compte de toutes les traductions non-pronominales. À l’aide de la boîte à out- ils Stanford Maximum Entropy (Manning and Klein 2003), cette approche nous a permis …

Feature management framework for Open Source Software development projects
KG Damarasingu – 2017 – search.proquest.com
Feature management framework for Open Source Software development projects. Abstract. Dynamic changes in the world of business have been driving the demand for advanced Open Source Software (OSS) development techniques for many years …

Methods for Efficient Ontology Lexicalization for Non-Indo-European Languages: The Case of Japanese
B Lanser – 2017 – pub.uni-bielefeld.de
… intuitive way. One way to accomplish this is by means of language technology, eg in the form of question answering systems, that allows users to query repositories of conceptual knowledge through natural language. One of …

A Frame-Based Approach for Integrating Heterogeneous Knowledge Sources
JR Gonzalez – vbn.aau.dk
Page 1. Aalborg Universitet A Frame-Based Approach for Integrating Heterogeneous Knowledge Sources Gonzalez, Jacobo Rouces DOI (link to publication from Publisher): 10.5278/vbn.phd.engsci.00102 Publication date: 2016 …

(Visited 469 times, 1 visits today)