Stanford CoreNLP & Question Answering 2014


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:

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


Watsonsim: Overview of a Question Answering Engine S Gallagher, W Zadrozny, W Shalaby… – arXiv preprint arXiv: …, 2014 – arxiv.org … 2. DATA SOURCES 2.1 Offline sources Data collection is a major part of the question answering process, and occupied a large fraction of effort expended … in place of n-grams, they search for the num- ber of common phrase subtrees taken from the Open- and CoreNLP parsers. … Related articles All 3 versions

Dr. Tux: A Question Answering System for Ubuntu users BA Philip, M Jog, AM Upasani – www-scf.usc.edu … The prototype was implemented in Python and uses NLTK and CoreNLP tools for Natural … a documents that might contain the answer to the user’s query, a question answering system has … input directly into the NLP layer which then returns the best matching question-answer set. … Related articles

LIMSI-CNRS @CLEF 2014: Invalidating Answers for Multiple Choice Question Answering M Gleize, AL Ligozat, B Grau – CLEF 2014 Working Notes, 2014 – ceur-ws.org … The architecture of our multiple-choice question- answering system is described in Figure 1. Its pipeline is composed of mainly four modules: preprocessing, passage retrieval, predicate-argument extractor and val- idation/invalidation. … Stanford CoreNLP TruthTeller … Cited by 1 Related articles

A framework for restricted domain Question Answering System P Biswas, A Sharan, N Malik – Issues and Challenges in …, 2014 – ieeexplore.ieee.org … Algorithm: 3 Answer Extraction Algorithm for Factoid Type of Question: 1) Find out “KEYWORD” from Question. … (2000). ‘The structure and perfonnance of an open-domain question answering system.” In 38th Annual … [29] http://nlp.stanford.edulsoftware/corenlp.shtml [30] http … Cited by 1 Related articles

OntoBAeval: Ontology Based Automatic Evaluation of Free-Text Response P Thanawala, J Pareek, M Shah – Technology for Education ( …, 2014 – ieeexplore.ieee.org … only endorse the semantic capability of Information Retrieval as Question Answering, but is … Systems -LMS based discussion forums or Community-based Question Answer (Q & … III. PROPOSED ARCHITECTURE OntoBAeval architecture relies on Stanford CoreNLP [7]: A suite … Related articles

Distributed Representations for Semantic Matching in non-factoid Question Answering P Molino, LM Aiello – ceur-ws.org … 3http://snowball.tartarus.org 4http://clearnlp.com 5http://sourceforge.net/projects/supersensetag/ 6http://nlp.stanford.edu/software/corenlp.shtml … A noisy-channel approach to question answering. … Discovering authorities in question answer communities by using link analysis. … Related articles All 2 versions

English Slot Filling with the Knowledge Resolver System H Chalupsky – nist.gov … stanford-corenlp-full- 2013-06-20.zip the TAC-KBP 2010 evaluations (Chen et al., 2010). We only used its slot filling tools which are com- prised of a pattern-based QA pipeline (labeled “PA Slot Filling” in Figure 1) derived from the OpenE- phyra question answering system, and … Related articles

Making Test Corpora for Question Answering More Representative A Walker, A Starkey, JZ Pan, A Siddharthan – … Multimodality, and Interaction, 2014 – Springer … t, normalised by tf-idf5. We then 3 http://answers.yahoo.com/ 4 Stanford CoreNLP version 1.3 … Making Test Corpora for Question Answering More Representative … 30(1), 107–117 (1998) 7. Buscaldi, D., Rosso, P.: Mining knowledge from wikipedia for the question answer- ing task. … Cited by 1 Related articles All 3 versions

Stanford’s 2013 KBP system G Angeli, A Chaganty, A Chang, K Reschke… – 2014 – stanford.edu … Web snippets, as used in previous versions of the Stanford KBP system. The CoreNLP pipeline included the default an- notators, augmented with the RNN parser of ?). … This is similar to approaches taken by ?) and other question answering systems. … Cited by 1 Related articles All 3 versions

An annotation similarity model in passage ranking for historical fact validation J Araki, J Callan – Proceedings of the 37th international ACM SIGIR …, 2014 – dl.acm.org … 1. INTRODUCTION Passage retrieval is a core component for question answer- ing (QA) systems … dependency relations into a multi-layer index in passage retrieval for Dutch question answering. … Algorithm 1 shows our algorithm to 6http://nlp.stanford.edu/software/corenlp.shtml … Cited by 1 Related articles All 4 versions

Hpi in-memory-based database system in task 2b of bioasq M Neves – Proceedings of Question Answering Lab at CLEF, 2014 – ceur-ws.org … Question answering systems usually include three main components [1]: ques- tion processing, passage retrieval and answer processing. … component includes sentence splitting, tokenization, part-of-speech tagging and chunking using the Stanford CoreNLP package5. … Cited by 2 Related articles

Course Project in Tokenization, Normalization, and Lemmatization G Iacoboni, A Di Cagno – giorgioiacoboni.eu … will be combined into a large Question Answering system: Palmisano Question Answering System, a live, real-world Question Answering (QA) system … Stanford CoreNLP provides a set of natural lan- guage analysis tools which can take raw English language text input and give … Related articles

A Hybrid Approach to Textual Entailment Recognition R Mei, H Fu, X Li – … , Industrial and Control Engineering (MEIC-14), 2014 – atlantis-press.com … The textual entailment recognition methods can be used in many information processing applications such as question answering, information retrieval … In the preprocessing module, texts and hypothesis terms are processed using Stanford CoreNLP [9] and ClearNLP [10] tools. … Related articles All 2 versions

Modeling biological processes for reading comprehension J Berant, V Srikumar, PC Chen, B Huang, CD Manning… – Proc. EMNLP, 2014 – aclweb.org … comprehension rather than lexical variability.1 A biologist created the question-answer part of … 80%/20%), and tuned hyper- parameters by maximizing average accuracy on question answering. We preprocessed the para- graphs with the Stanford CoreNLP pipeline ver- sion 3.4 … Cited by 4 Related articles All 12 versions

CSGS: Adapting a short answer scoring system for multiple-choice reading comprehension exercises S Ostermann, N Koleva, A Palmer… – CLEF 2014 Working …, 2014 – ceur-ws.org … assumption that this sentence has a reasonable likelihood of containing the question’s answer. … given task is to provide a computational solution towards auto- matic question answering. … NLP tools: for sentence splitting (OpenNLP) and tokenization (Stanford CoreNLP),23 POS … Cited by 1 Related articles All 2 versions

Application-Driven Relation Extraction with Limited Distant Supervision A Vlachos, S Clark – COLING 2014, 2014 – user.tu-berlin.de … Dunstane House William Playfair Dunstane House was… – Craigiehall Second Division Craigiehall isa… – Craigiehall British Army Craigiehall is a… entity filter relation extractor question answer score Dunstane … We then processed the texts using the Stanford CoreNLP toolkit. … Cited by 2 Related articles All 6 versions

Context Aware Text Representation SA Khazaeli, GM Knapp – xcdsystem.com … Figure 5: Graphical representation of dependency tree by online Stanford CoreNLP 3.2. … 13. Pustejovsky, James, et al. “TimeML: Robust Specification of Event and Temporal Expressions in Text.” New directions in question answering 3 (2003): 28-34. 14. Lee, Heeyoung, et al. … Related articles All 2 versions

Overview of knowledge extraction techniques in five question-answering systems F Jebbor, L Benhlima – … and Applications (SITA-14), 2014 9th …, 2014 – ieeexplore.ieee.org … E. Translinguistic architecture Translinguistic architecture attempts to resolve the problem of the dependence of the majority of question answering systems with … To extract these triples from the question, the system uses the Stanford CoreNLP library (SCNLP)[15] which provides … Related articles

Answering natural language questions with Intui3 C Dima – 2014 – sfs.uni-tuebingen.de … the output produced by SENNA and lemma information from the output of Stanford CoreNLP. … Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer pairs. … 2493–2537 (2011) 4. Dima, C.: Intui2: A prototype system for question answering over linked … Cited by 1 Related articles All 2 versions

Results of the BioASQ Track of the Question Answering Lab at CLEF 2014 G Balikas, I Partalas, ACN Ngomo, A Krithara… – 2014 – ceur-ws.org … The goal of task 2b was to provide a large-scale ques- tion answering challenge where the systems should be able to cope with all the stages of a question answering task, including the retrieval of relevant con … It uses the Stanford CoreNLP package for tokenizing the questions. … Cited by 1 Related articles All 2 versions

A hierarchical taxonomy for classifying hardness of inference tasks M Gleize, B Grau – Proceedings of the Ninth International Conference on … – lrec-conf.org … The overall difficulty of the question answering task (QA) can be approximated by taking the maximum of the difficulties of the two subtasks, passage retrieval and answer … The tokenizer and lemmatizer used are part of the Stanford CoreNLP tagging tool (Toutanova et al., 2003). … Cited by 1 Related articles All 3 versions

Information extraction over structured data: Question answering with freebase X Yao, B Van Durme – Proceedings of ACL, 2014 – cs.jhu.edu … Question answering (QA) from a knowledge base (KB) has a long history within natural language processing, going back to the 1960s and 1970s, with systems such as Baseball (Green Jr et … Every question was pro- cessed by the Stanford CoreNLP suite with the caseless model … Cited by 12 Related articles All 8 versions

A Language Visualization System E Unal – 2014 – denizyuret.com … generality and ambiguity of the language in order to visualize the natural language text. A question answering module is built as well to answer certain types of spa- tial inference questions after the scene generation process is completed. The system … 23 3.3 CoreNLP . . . . . … Related articles All 2 versions

Semantic parsing via paraphrasing J Berant, P Liang – Proceedings of ACL, 2014 – nlp.stanford.edu … Our work relates to recent lines of research in semantic parsing and question answering. … Since we train from question-answer pairs, we collect answers by executing the gold logical … We run all questions through the Stanford CoreNLP pipeline (Toutanova and Manning, 2003 … Cited by 19 Related articles All 14 versions

A bottom-up kernel of pattern learning for relation extraction C Zhang, W Xu, S Gao, J Guo – Chinese Spoken Language …, 2014 – ieeexplore.ieee.org … important task, which can po- tentially benefit a wide range of Natural Language Processing (NLP) tasks such as question answering, ontology learning … All relevant docs are analyzed by Stanford CoreNLP [25] to create dependencies in the “collapsedDependency” format [26]. … Related articles

Efficient calculation of sentence semantic similarity: a proposed scheme based on machine learning approaches and NLP techniques M Roostaee, SM Fakhrahmad… – Scientific Journal of …, 2014 – sjournals.com … On the other hand, question answering applications need to specify the similarity of question-answer or question-question pairs (Sangeetha and Arok, 2012). … Stanford CoreNLP performs Tokenization, POS Tagging, Named Entity Recognition and Syntactic parsing. … Related articles All 3 versions

SemantiKLUE: Robust Semantic Similarity at Multiple Levels Using Maximum Weight Matching T Proisl, S Evert, P Greiner, B Kabashi – SemEval 2014, 2014 – anthology.aclweb.org … License details: http: //creativecommons. org/licenses/by/4.0/ broad range of NLP applications, eg paraphrasing, MT evaluation, information extraction, question answering and summarization. … stanford. edu/software/corenlp. shtml 2 http://networkx. github. … Cited by 1 Related articles All 9 versions

AI-KU: Using Co-Occurrence Modeling for Semantic Similarity O Baskaya – SemEval 2014, 2014 – aclweb.org … ous Natural Language Processing (NLP) tasks such as textual entailment (Berant et al., 2012), summa- rization (Lin and Hovy, 2003), question answering (Surdeanu et al … 3Lemmatization is carried out with Stanford CoreNLP and transforms a word into its canonical or base form. … Related articles All 6 versions

An Analysis of Causality between Events and its Relation to Temporal Information P Mirza, S Tonelli – anthology.aclweb.org … However, information on causality could be beneficial to a number of natural language processing tasks such as question answering, text summarization … 2. Run Stanford CoreNLP tool4 to get information on lemma, part-of-speech (PoS) tags and dependency relations between … Related articles All 3 versions

Chinese Temporal Relation Resolution based on Chinese-English Parallel Corpus L Li, J Zhang, Y He, Y Zhang, H Wang – researchgate.net … of the current field in NLP, which shows a good prospect in question answering system, machine … supported, TimeML has been widely applied to the TRR research in question answer system, machine … Now SUTime is available as a part of the Stanford CoreNLP pipeline and can …

Extracting Latent Attributes from Video Scenes Using Text as Background Knowledge A Tran, M Surdeanu, P Cohen – Lexical and Computational Semantics (* …, 2014 – aclweb.org … (2011) tried to infer yes/no answers from indirect yes/no question-answer pairs (IQAPs … a noun.(Mental state adjec- tives are allowed to appear as verbs because some are often mis-tagged as verbs; eg, agitated, deter- mined, welcoming.) We used Stanford’s CoreNLP toolkit for … Related articles All 6 versions

Spotting Knowledge Base Facts in Web Texts T Tylenda, SK Kondreddi… – 4th Workshop on …, 2014 – people.mpi-inf.mpg.de … [2] J. Berant, A. Chou, R. Frostig, and P. Liang. Semantic parsing on freebase from question-answer pairs. … [5] A. Fader, LS Zettlemoyer, and O. Etzioni. Paraphrase-driven learning for open question answering. … The Stanford CoreNLP natural language processing toolkit. … Related articles All 3 versions

Textual Inference and Meaning Representation in Human Robot Interaction E Bastianelli, G Castellucci, D Croce, R Basili – anthology.aclweb.org … In many NLP tasks where robustness is crucial, eg Question Answering as discussed in (Ferrucci et al., 2010), methods based on … Automatic Speech Recognizer (ASR) (eg the CMU Sphinx (Walker et al., 2004)); morpho- syntactic modules (eg Stanford CoreNLP (Klein and … Related articles All 3 versions

A text mining based approach for web service classification R Nisa, U Qamar – Information Systems and e-Business Management – Springer … In general, automatic text classification plays a vital role in text summarization, question answering and information extraction. … Lemmatization is performed using Stanford CoreNLP (nlp.stanford.edu/software/corenlp.shtm). 3.3 Web service classifier. … Related articles

Effective and Robust Natural Language Understanding for Human-Robot Interaction E Bastianelli, G Castellucci, D Croce… – Proceedings of the …, 2014 – researchgate.net … In many Natural Language Processing tasks, where robustness and domain adaptation are cru- cial, eg Question Answering as discussed in [13], methods based on Statistical … It includes tokenization, POS tagging, Named 2 http://nlp.stanford.edu/software/corenlp.shtml Page 4. … Cited by 1 Related articles All 3 versions

Logical inference on dependency-based compositional semantics R Tian, Y Miyao, T Matsuzaki – Proceedings of ACL, 2014 – acl2014.org … on a relational database, yet simple enough to be latently learned from question-answer pairs … It should be noted that, however, a framework primarily designed for question answering is not readily … 5http://nlp.stanford.edu/software/ corenlp.shtml 6In (Liang et al., 2011) DCS trees … Cited by 4 Related articles All 6 versions

Exploiting Timegraphs in Temporal Relation Classification N Laokulrat, M Miwa, Y Tsuruoka – TextGraphs-9, 2014 – aclweb.org … Deepak Ravichandran and Eduard Hovy. 2002. Learn- ing surface text patterns for a question answering system. In ACL 2002, pages 41–47. Stanford Natural Language Processing Group. 2012. Stanford CoreNLP. Marta Tatu and Munirathnam Srikanth. 2008. … Related articles All 2 versions

Statistical script learning with multi-argument events K Pichotta, RJ Mooney – EACL 2014, 2014 – aclweb.org … example, if during training we observe the two co-occurring events (2) ask (mary, bob, question) answer (bob,•,•) we … 4 of the Stanford CoreNLP system … Neural Network system which stores sequences of events from text in episodic memory, capable of simple question answering. … Cited by 2 Related articles All 6 versions

Assuming Facts Are Expressed More Than Once J Betteridge, A Ritter, T Mitchell – The Twenty-Seventh International …, 2014 – rtw.ml.cmu.edu … in order to enable widespread adoption for truly intelligent, text-based appli- cations, such as semantic search, question answering (QA), and deep … ing annotations provided in the Hazy collection include POS tags and NER labels generated using the Stanford CoreNLP tools 6 … Cited by 1 Related articles All 3 versions

Dependency Parsing Features for Semantic Parsing W Monroe, Y Wang – stanford.edu … representations is useful for a variety of applica- tions, such as question answering (Clarke et … learns to parse utterances into MRs from a training set of question-answer pairs, without … each utterance with a Stanford Dependencies tree, using the Stanford CoreNLP parser (Socher … Related articles

Causal discourse analyzer: improving automated feedback on academic ESL writing E Chukharev-Hudilainen… – Computer Assisted …, 2014 – Taylor & Francis … Girju, R. (2003). Automatic detection of causal relations for question answering. In Proceedings of the ACL 2003 Workshop on Multilingual Summarization and Question Answering (Vol. 12, pp. 76–83). Morristown, NJ: ACL. [CrossRef] View all references). … Related articles

The DBOX Corpus Collection of Spoken Human-Human and Human-Machine Dialogues V Petukhova, M Gropp, D Klakow… – Proceedings of the …, 2014 – infoscience.epfl.ch … more important for our purposes is to build an interac- tive Question-Answering Dialogue System (QADS) where the answers are extracted not as information chunks or slot fillers, but rather form full-fledged dialogue utterances. … 11http://nlp.stanford.edu/software/corenlp.shtml … Cited by 1 Related articles All 3 versions

Towards Compositional Tree Kernels P Annesi, D Croce, R Basili – … on Computational Linguistics CLiC-it 2014, 2014 – torrossa.it … from parse trees and used to solve complex tasks such as Question Answering (Mos- chitti … Texts are processed with Stanford CoreNLP and compositional trees are generated as discussed in … Exploiting syntactic and shallow semantic kernels for question answer classification. … Related articles All 8 versions

Projet Pensées Profondes M CHEVALIER, R CHARRONDIÈRE, Q CORMIER… – projetpp.github.io … tasks include data querying (using the young and open knowledge base Wikidata), ques- tion parsing (using machine learning and the CoreNLP software written … Our project is about Question Answering, a field of research included in Natural Language Processing (NLP) theory … Related articles All 2 versions

Extraction of salient spatial descriptions from geo-tagged documents A Vlachos, S Clark – 2014 – spacebook-project.eu … relation extractor question answer score Dunstane House William Playfair 2 Ross 1 Craigiehall WEB … We then process the texts to extract sentences containing the question entities and candidate answers using components of the Stanford CoreNLP toolkit3. … Related articles

SSMT: A Machine Translation Evaluation View to Paragraph-to-Sentence Semantic Similarity P Huang, B Chang – SemEval 2014, 2014 – aclweb.org … cs. cmu. edu/alavie/METEOR/ 3cqa: Community Question Answering site text coreNLP4. For METEOR-derived features, we use the tool’s option for text normalization before matching. … In heavy 4http://nlp. stanford. edu/software/corenlp. shtml 587 Page 608. … All 6 versions

Discovering Relations By Entity Search In Lightweight Semantic Text Graphs M Laclav?k, Š Dlugolinský, M Ciglan – Computing and Informatics, 2014 – laclavik.sk … New types of question answering systems such as IBM Watson, based on structured and unstructured data [14], are being developed, but the task of entity … 4 http://gate.ac.uk/ 5 http://nlp.stanford.edu/software/corenlp.shtml#About 6 http://www.nzdl.org/wikification/ 7 http:// … Related articles All 2 versions

Unsupervised Verb Inference from Nouns Crossing Root Boundary SG Hong, SH Cho, MY Yi – anthology.aclweb.org … For example, in question answering, paraphrases from bilingual parallel corpus were used to expand the original questions (Lin and Pantel, 2001 … 2http://wiki.dbpedia.org/Downloads38?v= 6c5 3http://nlp.stanford.edu/software/corenlp.shtml 4https://opennlp.apache.org 5http://nlp … Related articles All 4 versions

Toward Automated International Law Compliance Monitoring (TAILCM) L Morgenstern – 2014 – DTIC Document … Tasks typically associated with the newswire domain are question answering and summarization. … Our initial analysis of a sample of sentences from our corpus on three freely available, widely-used parsers, including Stanford CoreNLP, Enju, and C&C, (http://nlp.stanford.edu … Related articles

LaSEWeb: Automating search strategies over semi-structured web data O Polozov, S Gulwani – Proceedings of the 20th ACM SIGKDD …, 2014 – dl.acm.org … Keywords Semi-structured data; domain-specific languages; structure extraction; Web programming; question answering. 1. INTRODUCTION The creation of search engines changed the way people locate information on the Web. … Cited by 1 Related articles All 12 versions

Assisting requirements analysts to find latent concerns with REAssistant A Rago, C Marcos, JA Diaz-Pace – Automated Software Engineering, 2014 – Springer … Typical NLP applications using SRL include: question answering, machine translation, or information extraction. … implementations for the same NLP task, they can easily be exchanged (eg, substitution of the OpenNLP POS tagger for its counterpart in Stanford CoreNLP). … Cited by 3 Related articles

Contextual keyword extraction by building sentences with crowdsourcing SG Hong, S Shin, MY Yi – Multimedia Tools and Applications, 2014 – Springer … For our research, we selected a document entitled “Knowledge Sharing and Yahoo Answers: Everyone Knows Something,” which describes Yahoo Answer, one of the largest question-answer forums. … We preprocessed the chosen document by using the Stanford CoreNLP suite … Related articles All 4 versions

Determining the Temporal Order of Events in Natural Language Using Learned Commonsense Knowledge D Ziegler – 2014 – david-ziegler.info … Understanding temporal order can be beneficial for a number of Natural Language Processing (NLP) applications, such as, for example, question answering and doc- ument summarization. … first split using the sentence classifier from Stanford CoreNLP. This is more … Related articles

Learning to Rank Answer Candidates for Automatic Resolution of Crossword Puzzles G Barlacchi, M Nicosia, A Moschitti – CoNLL-2014, 2014 – aclweb.org … This basically suggests that, similarly to the Jeopardy! challenge case (Ferrucci et al., 2010b), the solution relies on Question Answering (QA) research. … 3http://nlp. stanford. edu/software/ corenlp. shtml 4http://cogcomp. cs. illinois. … Cited by 2 Related articles All 6 versions

Solving Open-Domain Multiple Choice Questions with Textual Entailment and Text Similarity Measures N Dhruva, O Ferschke, I Gurevych – CLEF 2014 Working Notes, 2014 – ceur-ws.org … 4 System Architecture We now present the architecture of our question answering system which is based on text similarity measures, textual entailment and coreference resolution. … 4 http://nlp.stanford.edu/software/corenlp.shtml 1378 Page 5. 4.3 Sentence Retrieval … Cited by 1 Related articles

Named Entity Tagging a Very Large Unbalanced Corpus: Training and Evaluating NE Classifiers J Bingel, T Haider – 2014 – ids-pub.bsz-bw.de … plays a central role in many different linguistic and text-processing applications such as question answer- ing (Mollá … Systems and training data We train different models for the Stanford NERC (coreNLP) system v3.2.0 (Finkel et … Named entity recognition for question answering. … Related articles All 4 versions

Discovering Implicit Discourse Relations Through Brown Cluster Pair Representation and Coreference Patterns AT Rutherford, N Xue – EACL 2014, 2014 – aclweb.org … It is also central to many applications such as automatic summarization and question-answering systems. … We use the Stanford CoreNLP suite to lemmatize and part- of-speech tag each word (Toutanova et al., 2003; 646 Page 673. … Related articles All 5 versions

Semantic Compositionality in Tree Kernels P Annesi, D Croce, R Basili – Proceedings of the 23rd ACM International …, 2014 – dl.acm.org … CSPTK for Question Classification Question Classification has been largely used for limiting the re- trieval complexity in many Question Answering processes … For learning our models, we used two extensions of the 4 http://nlp.stanford.edu/software/corenlp.shtml 5Left contexts of … Related articles

Discovering Relations By Entity Search In Semantic Text Graphs M Laclav?k, Š Dlugolinský, M Ciglan – cai.sk … New types of question answering systems such as IBM Watson, based on structured and unstructured data [16], are being developed, but the task of entity … 8 http://gate.ac.uk/ 9 http://nlp.stanford.edu/software/corenlp.shtml#About 10 http://www.nzdl.org/wikification/ 11 http:// …

Generating Comprehension Questions Using Paraphrase YM Tseng, YT Huang, MC Chen, YS Sun – Technologies and Applications …, 2014 – Springer … They showed that the source of 71% of the questions in an independent why question answering data set could be found in the … The CoreNLP pipeline [11] splits the article into sentences and provides information on coreference chains, part-of-speech tags and syntactic trees. … Related articles All 3 versions

Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence MA Sultan, S Bethard, T Sumner – Transactions of the …, 2014 – tacl2013.cs.columbia.edu … Consequently, alignment is a central component of a number of important tasks involving text comparison: textual entailment recognition, textual similarity identifica- tion, paraphrase detection, question answering and text summarization, to name a few. … Related articles All 8 versions

Mining semantic structures from syntactic structures in free text documents H Mousavi, D Kerr, M Iseli… – … Computing (ICSC), 2014 …, 2014 – ieeexplore.ieee.org … Markus Iseli CRESST, UCLA iseli@cse.ucla.edu Carlo Zaniolo CSD, UCLA zaniolo@cs.ucla. edu Abstract—The Web has made possible many advanced text- mining applications, such as news summarization, essay grading, question answering, and semantic search. … Cited by 3 Related articles All 6 versions

Information evolution in wikipedia A Ceroni, M Georgescu, U Gadiraju, KD Naini… – Proceedings of The …, 2014 – dl.acm.org … temporal information, even if its involvement has been studied in several areas like informa- tion extraction, topic-detection, question-answering, query log … version w(t) was also annotated with the named entities mentioned in it, extracted through the Stanford CoreNLP parser5. … Cited by 2 Related articles All 4 versions

Distantly Supervised Web Relation Extraction for Knowledge Base Population I Augenstein, D Maynard, F Ciravegna – semantic-web-journal.net … Ontology-based question answering systems often use patterns learned by semi-supervised information ex- traction approaches as part of their approach … Each paragraph is then processed with Stan- ford CoreNLP 3 to split the text into sentences, tokenise it, annotate it with part … Related articles

Relation extraction from the web using distant supervision I Augenstein, D Maynard, F Ciravegna – Knowledge Engineering and …, 2014 – Springer … Ontology-based question answering systems often use patterns learned by semi- supervised information extraction approaches as part of their approach, Unger et … Each paragraph is then processed with Stanford CoreNLP 2 to split the text into sentences, tokenise it, annotate it … Cited by 1 Related articles All 6 versions

UoW: NLP techniques developed at the University of Wolverhampton for Semantic Similarity and Textual Entailment R Gupta, H Béchara, I El Maarouf, C Orasan – SemEval 2014, 2014 – aclweb.org … com/rohitguptacs/wlvsimilarity 3http://nlp. stanford. edu/software/corenlp. shtml calculated using clusters of coreferential entities. … 2003. COGEX: A Logic Prover for Question Answering. In Proceedings of HLT- NAACL, number June, pages 87–93. … Cited by 1 Related articles All 6 versions

Generating Object-Oriented Semantic Graph for Text Summarisation M Joshi, H Wang, S McClean – Mining Intelligence and Knowledge …, 2014 – Springer … We use Stanford CoreNLP library[20] for preprocessing. … It can be pruned to generate abstractions of the original information present in the document. This semantic graph can also be used as a basic structure in other natural language applications ie Question/answering. … Related articles All 3 versions

Acquiring a Dictionary of Emotion-Provoking Events HT Vu, G Neubig, S Sakti, T Toda, S Nakamura – EACL 2014, 2014 – aclweb.org … twitter. com 4http://nlp. stanford. edu/software/ corenlp. shtml 130 Page 151. … 2002. Learn- ing surface text patterns for a question answering system. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, pages 41–47. … Related articles All 6 versions

Searching Locally-Defined Entities Z Wu, Y Lv, A Fuxman – Proceedings of the 23rd ACM International …, 2014 – dl.acm.org … of improv- ing relevance estimation of documents, eg, [4, 16, 14, 21], while the research on passage retrieval for question answer- ing aims … The use of paragraph-based pas- sages is partially inspired by an interesting observation in question answering [19] that users generally … Related articles All 2 versions

Using part-of-speech tags as deep-syntax indicators in determining short-text semantic similarity V Batanovi?, D Boji? – Computer Science and Information Systems, 2014 – doiserbia.nb.rs … in multi-document summarization, it is essential to avoid choosing a sentence that carries the same information as the already selected ones [1]. In information retrieval or question answering systems, the … For text preprocessing we used the Stanford CoreNLP package [30]. … Related articles All 4 versions

Enhanced Factored Sequence Kernel for Sentiment Classification L Trindade, H Wang, W Blackburn… – Web Intelligence (WI) …, 2014 – ieeexplore.ieee.org … This enabled kernel functions to consider extra linguistic knowledge making them very effective for text classification and NLP tasks [15] – example include Summarization, Question Answering and Recognizing Textual … 3 Available at nlp.stanford.edu/software/corenlp.shtml … Related articles All 2 versions

HuRIC: a Human Robot Interaction Corpus E Bastianelli, G Castellucci, D Croce, L Iocchi… – of the LREC, Reykjavik …, 2014 – lrec-conf.org … In many Natural Language Processing tasks, where robustness and domain adaptation are crucial, eg Open Domain Question Answering as dis- cussed in (Ferrucci et al., 2010), methods based on Statisti- cal Learning (SL) theory have … 4 nlp.stanford.edu/software/corenlp.shtml … Cited by 1 Related articles All 2 versions

Extending Linked Open Data resources exploiting Wikipedia as source of information AP Aprosio, E Damiani, A Lavelli, C Giuliano – air.unimi.it … 8 1.6.1 DBpedia expansion . . . . . 8 1.6.2 Question Answering . . . . . 8 1.7 Structure of the thesis . . . . . … 32 3.5 Question answering . . . . . 33 … Related articles All 2 versions

Ensemble-Based Medical Relation Classification J D’Souza, V Ng – hlt.utdallas.edu … 3To compute the features, we use (1) the Stanford CoreNLP tool (Manning et al., 2014) to obtain POS tags, word lemmas, and dependency structures; (2) GENIA (http://www.nactem.ac.uk/tsujii/ GENIA/tagger) to obtain phrase chunks; and (3) SENNA (Collobert et al., 2011) to … Related articles All 5 versions

A New Corpus and Imitation Learning Framework for Context-Dependent Semantic Parsing A Vlachos, S Clark – Transactions of the Association for …, 2014 – tacl2013.cs.columbia.edu Page 1. A New Corpus and Imitation Learning Framework for Context-Dependent Semantic Parsing Andreas Vlachos Computer Science Department University College London a.vlachos@cs.ucl.ac.uk Stephen Clark Computer … Related articles All 5 versions

Construction and evaluation of event graphs G Glavaš, J Šnajder – Natural Language Engineering, 2014 – Cambridge Univ Press … For example, in question answering a question about a factual event (eg, ‘Who killed Osama bin Laden?’) is much more likely to appear than a question about a non-factual event (eg, ‘Who did not win a medal in 2012 Olympics … 2 http://nlp.stanford.edu/downloads/corenlp.shtml … Cited by 1 Related articles All 3 versions

ANA: Automated Nursing Agent K Quinn – 2014 – era.library.ualberta.ca … for our other classifiers. 2.3 Stanford CoreNLP The tools that Stanford’s NLP group provides are used in this thesis. Almost every … with beginning and ending n-grams. Cong et al. detect question/answer pairs, but they focus on forum posts [10]. … Related articles All 2 versions

Relation Extraction using Distant Supervision, SVMs, and Probabilistic First Order Logic MW Greaves – 2014 – reports-archive.adm.cs.cmu.edu … to build context specific definitions of unknown words. Lehnert’s 1977 dissertation in- vestigated question answering as a problem in natural language understanding. Lehnert (1977) proposed a theory of question answering that combined ideas from conceptual 4 … Related articles All 4 versions

Transforming graph-based sentence representations to alleviate overfitting in relation extraction RJ Lima, J Batista, R Ferreira, F Freitas… – Proceedings of the …, 2014 – dl.acm.org … text document. Ontology Population, Automatic Summariza- tion, and Question Answering are fields in which relation extrac- tion offers valuable solutions. A relation … in Fig. 4. 1 http://nlp.stanford.edu/software/corenlp.shtml This graph … Related articles

Human computing and crowdsourcing methods for knowledge acquisition SK Kondreddi – 2014 – scidok.sulb.uni-saarland.de … Also, I would like to acknowledge the authors of the Stanford CoreNLP software and the OpenIE tools, … ingly being built and used in areas that include Web search, machine translation, summarization, question answering, information integration and expert systems. … Related articles All 8 versions

Good debt or bad debt: Detecting semantic orientations in economic texts P Malo, A Sinha, P Korhonen… – Journal of the …, 2014 – Wiley Online Library … In addition to the use of negative word lists, there are also many other word categories that can be helpful in detecting semantic orientations in financial and economic texts. Using the more general multiperspective question answering (MPQA) lexicon by Wiebe et al. … Cited by 2 Related articles All 10 versions

Weakly Supervised Learning for Compositional Sentiment Recognition M Haas – 2014 – computerlinguist.org … updated during training for incorrect predictions. Choi and Cardie [2008] evaluate their approaches on the Multi-Perspective Question Answering corpus (MPQA) [Wiebe et al., 2005], [Wilson et al., 2005]. This newswire cor- pus is … Related articles All 2 versions

Realistic Dialogue Engine for Video Games CM Rose – 2014 – ir.lib.uwo.ca … 23 3.2.1 Potential Use in Video Games ….. 23 3.3 Question Answering….. 24 … 41 5.4 Question Answering System ….. 42 …

From hyperlinks to Semantic Web properties using Open Knowledge Extraction V Presutti, AG Nuzzolese, S Consoli… – … to Semantic Web …, 2014 – semantic-web-journal.net Page 1. Undefined 1 (2009) 1–5 1 IOS Press From hyperlinks to Semantic Web properties using Open Knowledge Extraction Editor(s): Name Surname, University, Country Solicited review(s): Name Surname, University, Country … Related articles All 2 versions

Identifying Latent Attributes from Video Scenes Using Knowledge Acquired From Large Collections of Text Documents AX Tran – 2014 – arizona.openrepository.com … Mohtarami et al. (2011) tried to infer yes/no answers from indirect yes/no question-answer pairs (IQAPs) by predicting the uncertainty of sentiment adjectives in indirect answers. Their method employs antonyms, synonyms, word sense disambiguation as well as … Related articles All 2 versions

Reasoning with Qualitative Spatial and Temporal Textual Cases V Dufour-Lussier – 2014 – hal.inria.fr Page 1. Reasoning with Qualitative Spatial and Temporal Textual Cases Valmi Dufour-Lussier To cite this version: Valmi Dufour-Lussier. Reasoning with Qualitative Spatial and Temporal Textual Cases. Arti- ficial Intelligence. Université de Lorraine, 2014. English. … Related articles All 8 versions

Exploiting extra-textual and linguistic information in keyphrase extraction G BEREND – Natural Language Engineering – Cambridge Univ Press … the normalized form of innov diffus. For the linguistic analysis of the articles (ie tokenization, lemmatization, POS tagging) we used the Stanford CoreNLP API (Toutanova and Manning 2000). As stated above, all the sequences … Related articles All 2 versions

Entity-based Enrichment for Information Extraction and Retrieval J Dalton – 2014 – scholarworks.umass.edu … base entries. 1.1 Entities in Retrieval The recent popularity of question answering services such as IBM Watson and personal … 1. For what task? (Document retrieval, question answering, in-document coreference, entity linking) 2. Entities from what source? … Related articles

Prior Art Search and Its Evaluation J Luo – 2014 – repository.library.georgetown.edu Page 1. Prior Art Search and Its Evaluation A Thesis submitted to the Faculty of the Graduate School of Arts and Sciences of Georgetown University in partial fulfillment of the requirements for the degree of Master of Science in Computer Science By Jiyun Luo, BE … Related articles All 2 versions

Computer Assisted Design Reflection: A Web Application to Improve Early Stage Product Design in Startup Companies CC Gimenez – 2014 – claygimenez.github.io … ligence, and linguistics that seeks to enable computers to process and understand human languages. It is a large and diverse field of study, with work on tasks ranging from machine translation to recommender systems and automated question answering [6]. 18 Page 19. … Related articles

Statistical Dialog Management for Health Interventions U Yasavur – 2014 – digitalcommons.fiu.edu … such as customer service automation, reservation/booking and question answering systems. … in the 90s and early 2000s. Commercial systems have been deployed for reserva- tion/booking, customer center automation, and question answering in the last decade … Related articles All 3 versions

Inducing Implicit Arguments via Cross-document Alignment: A Framework and its Applications M Roth – 2014 – archiv.ub.uni-heidelberg.de … texts computationally. Successful approaches to this task could hence be useful to improve the performance of natural language processing systems in applications such as question answering and information extraction. We … Cited by 1 Related articles All 4 versions