Stanford CoreNLP & Coreference Resolution 2014


See also:

Apache OpenNLP & Coreference Resolution 2014 | Stanford CoreNLP & Coreference Resolution 2015Stanford CoreNLP & Question Answering 2014


The Stanford CoreNLP natural language processing toolkit CD Manning, M Surdeanu, J Bauer, J Finkel… – Proceedings of 52nd …, 2014 – acl2014.org … This paper describe the design and development of Stanford CoreNLP, a Java (or at least JVM-based) annotation pipeline framework, which provides most of the common core natural language pro- cessing (NLP) steps, from tokenization through to coreference resolution. … Cited by 68 Related articles All 14 versions

Ixa pipeline: Efficient and ready to use multilingual nlp tools R Agerri, J Bermudez, G Rigau – … of the 9th Language Resources and …, 2014 – lrec-conf.org … The data-centric architecture of IXA pipeline means that our coreference resolution module, unlike most of the other coreference systems available, is highly independent and … We have produced KAF/NAF wrappers for other modules, such as some of the Stanford CoreNLP tools. … Cited by 13 Related articles All 4 versions

Evaluation of coreference resolution for biomedical text M Choi, K Verspoor, J Zobel – Proceedings of the SIGIR workshop on …, 2014 – ceur-ws.org … how domain-specific information impacts on performance for coreference resolution involving protein and gene entities. The TEES system, which includes a biomedical domain-specific NER component for protein and gene mentions [4], and the Stanford CoreNLP system, which … Cited by 2 Related articles All 3 versions

Limited memory incremental coreference resolution K Webster, JR Curran – … of the Conference on Computational Linguistics, 2014 – aclweb.org … By drawing an analogy between tokens and phrases in syntactic parsing with mentions and clusters in coreference resolution, we derive an algorithm … 3since distinct feature strings correspond to completely distinct features 4http://nlp.stanford.edu/software/corenlp.shtml 5http … Cited by 2 Related articles All 3 versions

An Exercise in Reuse of Resources: Adapting General Discourse Coreference Resolution for Detecting Lexical Chains in Patent Documentation N Bouayad-Agha, A Burga, G Casamayor… – Proceedings of LREC- …, 2014 – lrec-conf.org … One of these resources is the Stanford Determinis- tic Coreference Resolution System1 (henceforth, StCR). It is the last stage of a pipeline of linguistic processing modules in the Stanford CoreNLP platform, and uses the results of the preceding modules (eg, tokenization … Cited by 1 Related articles

Linking people in videos with “their” names using coreference resolution V Ramanathan, A Joulin, P Liang, L Fei-Fei – Computer Vision–ECCV …, 2014 – Springer … The Stanford CoreNLP coreference system uses a fixed set of rules to itera- tively group mentions with similar properties. … Also, our model performs explicit entity linking by asso- ciating every mention to a name from the cast list, unlike standard coreference resolution methods. … Cited by 2 Related articles All 6 versions

Recall error analysis for coreference resolution S Martschat, M Strube – 2014 – anthology.aclweb.org … 4.1 Data We analyze the errors of the systems on the En- glish development data of the CoNLL’12 shared task on multilingual coreference resolution (Prad- han et al., 2012). … 4Part of Stanford CoreNLP, available at http://nlp. stanford.edu/software/corenlp.shtml. We … Cited by 1 Related articles All 5 versions

KOSHIK: A large-scale distributed computing framework for NLP P Exner, P Nugues – … on Pattern Recognition Applications and Methods, 2014 – lup.lub.lu.se … KOSHIK uses the Stanford CoreNLP multi-pass sieve corefer- ence resolver to resolve anaphoric expressions (Lee et al., 2011). … Stanford’s multi-pass sieve coreference resolution system at the conll-2011 shared task. … Cited by 3 Related articles All 4 versions

kLogNLP: Graph kernel–based relational learning of natural language M Verbeke, P Frasconi, K De Grave… – Proceedings of the …, 2014 – lirias.kuleuven.be … tagging and parsing, and offers an interface to WordNet. Stanford CoreNLP Stanford CoreNLP2 pro- vides POS tagging, NER, parsing and coreference resolution functionality. The preprocessing toolkit to be used can be set … Cited by 1 Related articles All 9 versions

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 … We use Stanford CoreNLP as our main Natural Language annotation tool. Each sentence from the document, questions or answer choices is tagged with Part- Of-Speech [9] and syntactically parsed [4]. In addition, we apply coreference resolution [7] on the whole document. … Cited by 1 Related articles

Determiner-Established Deixis to Communicative Artifacts in Pedagogical Text S Wilson, J Oberlander – Proc. ACL 2014 – ling.uni-potsdam.de … This limits the effectiveness of traditional approaches to coreference resolution toward the present problem. … In preparation for analysis, the documents were POS tagged and parsed by the Stanford CoreNLP suite (Socher et al., 2013; Toutanova et al., 2003). … Cited by 1 Related articles All 7 versions

Multilingual, Efficient and Easy NLP Processing with IXA Pipeline R Agerri, D San-Sebastián, J Bermudez, G Rigau… – EACL 2014, 2014 – aclweb.org … 316404, and by the SKATER Span- ish MICINN project No TIN2012-38584-C06-01. The work of Josu Bermudez on coreference resolution is supported by a PhD Grant of the University of Deusto (http://www. deusto. es). … stanford. edu/software/corenlp. shtml 18http://www. … Cited by 1 Related articles All 6 versions

KUL-Eval: A Combinatory Categorial Grammar Approach for Improving Semantic Parsing of Robot Commands using Spatial Context W Mattelaer, M Verbeke, D Nitti – SemEval 2014, 2014 – anthology.aclweb.org … is transformed to the sentence Pick the blue block [1] and place it (1) above the gray one {1}. The anaphoric references are found using the coreference resolution system of Stanford CoreNLP (Recasens et al., 2013; Lee et al., 2013; Lee et al., 2011; Raghunathan et al., 2010). … Cited by 1 Related articles All 7 versions

A Bayesian mixed effects model of literary character D Bamman, T Underwood, NA Smith – … of the 52nd Annual Meeting of …, 2014 – acl2014.org … While previous work uses the Stanford CoreNLP toolkit to identify characters and extract typed dependencies for them, we found this … tokens); in particular, syntactic parsing, with cubic complexity in sentence length, and out-of-the-box coreference resolution (with thousands of … Cited by 3 Related articles All 5 versions

Corpus for Coreference Resolution on Scientific Papers P Chaimongkol, A Aizawa, Y Tateisi – lrec-conf.org … 4. Performance on Existing Coreference Resolver System To compare the coreference resolution result of our corpus with those of other corpora, we have tested our corpus on an existing coreference system: Stanford CoreNLP Coref- erence Resolver (Lee et al., 2013). … Related articles

SinoCoreferencer: An End-to-End Chinese Event Coreference Resolver C Chen, V Ng – lrec-conf.org … by the Stanford CoreNLP tool) and the named entities (provided by Component 3). The corefer- ence resolution algorithm used by this component adopts a sieve-based approach, as described in detail below. The sieve-based approach to coreference resolution was originally … Related articles All 2 versions

Analysis of Coreference Relations in the Biomedical Literature M Choi, K Verspoor, J Zobel – Australasian Language Technology Association … – aclweb.org … tics of both anaphor and antecedent. 3 Experiment We compare an existing coreference resolution system, TEES, that uses a domain-specific named entity recognition (NER) module with an existing general system, Stanford CoreNLP, that does not use a domain-specific NER. … Related articles All 4 versions

Text Mining with the Stanford CoreNLP M Song, T Chambers – Measuring Scholarly Impact, 2014 – Springer … dcoref DeterministicCorefAnnotator CorefChainAnnotation Implements both pronominal and nominal coreference resolution. Adapted from the Stanford CoreNLP website, http://nlp.stanford. edu/software/corenlp.shtml 222 M. Song and T. Chambers Page 9. … Related articles All 3 versions

Discovering Implicit Discourse Relations Through Brown Cluster Pair Representation and Coreference Patterns AT Rutherford, N Xue – EACL 2014, 2014 – aclweb.org … Through word-level semantic commonalities revealed by Brown clusters and entity-level rela- tions revealed by coreference resolution, we might be able to paint a … We use the Stanford CoreNLP suite to lemmatize and part- of-speech tag each word (Toutanova et al., 2003; 646 … Cited by 1 Related articles All 5 versions

DIT: Summarisation and Semantic Expansion in Evaluating Semantic Similarity M Kacmajor, JD Kelleher – SemEval 2014, 2014 – aclweb.org … 2.2 Pre-processing Paragraphs and sentences are tokenized and anno- tated using Stanford CoreNLP1. The annotations include part-of-speech (POS), lemmatisation, de- pendency parse and coreference resolution. Then 1http://nlp. stanford. edu/software/corenlp. shtml 230 … Related articles All 6 versions

Concretely Annotated Corpora F Ferraro, M Thomas, MR Gormley, T Wolfe… – mahe.ece.jhu.edu … Second, coreference resolution only included non- singleton entities (those that have at least two mentions). … Tokens Syntax Entities Situations POS Lemma NER CP DP Mention Id. Coref JHU BBN SERIF CMU SEMAFOR STANFORD CORENLP … Related articles All 6 versions

Visual Entity Linking: A Preliminary Study R Weegar, L Hammarlund, A Tegen… – AAAI 2014 Workshop …, 2014 – lup.lub.lu.se … It consists of a sequence of processing steps: part- of-speech tagging, dependency parsing, and coreference resolution that enables us to identify the entities as … We restricted these mentions to nouns that we identi- fied using the Stanford CoreNLP program (Raghunathan et al. … Related articles All 8 versions

OutbreakSum: Automatic Summarization of Texts Relating to Disease Outbreaks R Gruss, D Morgado, N Craun, C Shea-Blymyer – 2014 – vtechworks.lib.vt.edu … API directly. 4. Utilities to leverage the full extent of the Stanford CoreNLP library, which include tools for parsing and coreference resolution. 5. Utilities to simplify using the OpenNLP Java library for text processing. By configuring …

A Content-Based Recommendation System for Online Communities at High Scale R Elwell, K Cooney, T Chong, C Fife – robertelwell.info … We use a modification of the Stanford CoreNLP pipeline that supports the polling of a directory of flat files of raw text, attaching an available thread in a set pool to each file. … Deterministic coreference resolution based on entity-centric, precision-ranked rules. Comput. … Related articles All 2 versions

Language Resources and Annotation Tools for Cross-Sentence Relation Extraction S Krause, H Li, F Xu, H Uszkoreit, R Hummel… – Proceedings of the …, 2014 – lrec-conf.org … A second purpose is the learning of additional patterns needed for cross- sentence RE and for the training of improved specialized coreference resolution. … Sentence segmentation: We employed the sentence splitter for English from Stanford CoreNLP. … Related articles

Exploring the utility of coreference chains for improved identification of personal names A Glaser, J Kuhn – lrec-conf.org … Preprocessing The Stanford CoreNLP system provides all necessary tools to annotate the extracted raw data, including part-of-speech tagging (Toutanova et al., 2003), named entity recognition (Finkel et al., 2005), and coreference resolution (Raghu- nathan et al., 2010; Lee … Related articles

Big data for Natural Language Processing: A streaming approach R Agerri, X Artola, Z Beloki, G Rigau, A Soroa – Knowledge-Based Systems, 2014 – Elsevier … ixa-pipe-coref performs coreference resolution. The algorithm is loosely based on the Stanford Multi Sieve Pass system [19]. … The Stanford CoreNLP 16 is also a monolithic suite, which makes it difficult to integrate other tools in its chain. … Related articles All 2 versions

A Conceptual Framework of Online Natural Language Processing Pipeline Application C Shi, M Verhagen, J Pustejovsky – COLING 2014, 2014 – aclweb.org … appli- cation perspective, where tools are available for concrete text mining for communities such as OpenNLP, Stanford CoreNLP and NLTK … process POS T agging Noun -phrase chunking Lem m atization NER Sentence Splitter T okenization Coreference Resolution Figure 2 … Related articles All 3 versions

MUCK: A toolkit for extracting and visualizing semantic dimensions of large text collections R Weiss – Sponsor: Idibon, 2014 – anthology.aclweb.org … NLP task Currently, this system only incor- porates the full Stanford CoreNLP pipeline4, which processes … Stanford’s multi-pass sieve coref- erence resolution system at the conll-2011 shared task … Deterministic coreference resolution based on entity-centric, precision-ranked rules … Related articles All 7 versions

An Example-Based Approach to Difficult Pronoun Resolution C Kruengkrai, N Inoue, J Sugiura, K Inui – 2014 – aclweb.org … We classify the problem of pronoun resolution into two main categories: traditional anaphora and Wino- grad schemas. Anaphora (or coreference) resolution has a long history in NLP. … After retrieving snippets, we analyze them using the Stanford CoreNLP (Manning et al., 2014). …

Company Mention Detection for Large Scale Text Mining RJ Passonneau, T Ramelson, B Xie – parasol.tamu.edu … The corefer- ence resolution model that our method builds on is the Stanford CoreNLP parser (Manning et al., 2014). Named entity recognition and coreference resolution are the two key components in our company mention detection task. … Related articles

BIT’s Slot-Filling Method for TAC-KBP 2013 S Xu, C Zhang, Z Niu, R Mei, J Chen, J Zhang, H Fu – nist.gov … For each slot, a binary probabilistic Support Vector Machine classifier (LIBSVM) is trained on the collected dataset. Stanford CoreNLP is used to preprocess the test sentences. … Second, we don’t use coreference resolution technique to extract more candidate slot values. … 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 … Stanford CoreNLP is used for tokenization, stem, part of speech tagging, while ClearNLP is applied to identify semantic roles of sentences within texts and hypothesis. … Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task. … Related articles All 2 versions

Context Aware Text Representation SA Khazaeli, GM Knapp – xcdsystem.com … Figure 5: Graphical representation of dependency tree by online Stanford CoreNLP 3.2. … 14. Lee, Heeyoung, et al. “Deterministic coreference resolution based on entity-centric, precision-ranked rules.”, Computational Linguistic Vol. 39, No. 4 (2013): 885-916. 15. … Related articles All 2 versions

Towards content-oriented patent document processing: Intelligent patent analysis and summarization S Brügmann, N Bouayad-Agha, A Burga… – World Patent …, 2014 – Elsevier … (ii) Coreference resolution: Application of a succession of independent coreference models (called “sieves”), from highest to lowest precision to all … To adapt StCR to patent material, we substituted the Stanford CoreNLP pipeline by our own processing pipeline that consists of a … Related articles

Annotating cohesion for multilingual analysis E Lapshinova-Koltunski, KA Kunz – Proceedings 10th Joint ISO-ACL …, 2014 – sigsem.uvt.nl … 50% for spoken texts, see, for instance,(Amoia et al., 2012) for the analyses with Stanford CoreNLP (Lee et al., 2011). … 2011. Stanford’s multi-pass sieve coreference resolution system. In CoNLL-2011 Shared Task. MM Louwerse and AC Graesser. 2005. … Cited by 1 Related articles All 3 versions

Mining semantic structures from syntactic structures in free text documents H Mousavi, D Kerr, M Iseli… – … Computing (ICSC), 2014 …, 2014 – ieeexplore.ieee.org … We propose a new Coreference Resolution technique through a … such as dates, floating point numbers, etc, and partitioning the text into its paragraphs and sentences, SemScape parses each sentence using a proba- bilistic parser (eg Charniak [8] and Stanford [22] parsers). … Cited by 3 Related articles All 6 versions

News Visualization Based on Semantic Knowledge S Arnold, D Burke, T Dörsch, B Loeber, A Lommatzsch – ceur-ws.org … 1. It consists of a periodic RSS feed crawler as source for news documents2 and the language components for sentence splitting, part- of-speech (POS) tagging, named entity recognition (NER) and coreference resolution. We utilize a Stanford CoreNLP named entity recognition … Related articles

Lightly Supervised Named Entity Recognition for Hotel Names NPTWE Putri – zhekova.net … 1.6+. Stanford CoreNLP intregrates all Stanford NLP Tools in its argument -annotators (includes Stanford POS tagger, named entity recognizer, parser, coreference resolution system and sentiment analyses tools). Of course … Related articles All 2 versions

Logical inference on dependency-based compositional semantics R Tian, Y Miyao, T Matsuzaki – Proceedings of ACL, 2014 – acl2014.org … Coreference We use Stanford CoreNLP to re- solve coreferences (Raghunathan et al., 2010), whereas coreference is implemented as a special type of selection. … 1. For a TH pair, apply dependency parsing and coreference resolution. … Cited by 4 Related articles All 6 versions

Textual emigration analysis A Blessing, J Kuhn – … of the Ninth International Conference on …, 2014 – lrec-conf.org … German NER (Faruqui and Padó, 2010) German Named Entity Recognizer based on Stanford CoreNLP http://hdl.handle.net/11858/00-247C-0000-0022-DDA1-3 … Structured data can be used instead of more expensive coreference resolution methods. … Cited by 2 Related articles

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

User-Level Opinion Propagation Analysis in Discussion Forum Threads DC Cercel, ? Tr?u?an-Matu – Artificial Intelligence: Methodology, Systems, …, 2014 – Springer … 1. First, using the Stanford CoreNLP tool (http://nlp.stanford. edu/software/corenlp.shtml), specific natural language processing techniques are applied to each post in the discussion thread [14]: tokenization, part of speech tagging, syntactic parsing, and coreference resolution. … Related articles All 4 versions

Automatic classification of communicative functions of definiteness A Bhatia, CC Lin, N Schneider, Y Tsvetkov… – Proc. of …, 2014 – anthology.aclweb.org … Preprocessing. Automatic dependency parses and coreference information were obtained with the parser and coreference resolution system in Stanford CoreNLP v. 3.3.0 (Socher et al., 2013; Recasens et al., 2013) for use in features (§4.2). … Cited by 1 Related articles All 5 versions

Type-Aware Distantly Supervised Relation Extraction with Linked Arguments MKJGS Soderland, DS Weld – anthology.aclweb.org … Coreference resolution is the task of clustering mentions of entities together, typically within a single document. … As required for features, we use Stanford CoreNLP’s tokenizer, part of speech tagger (Toutanova et al., 2003), and dependency parser (de Marneffe and Manning … Related articles All 7 versions

A Latent Variable Model for Discourse-aware Concept and Entity Disambiguation A Fahrni, M Strube – EACL 2014, 2014 – aclweb.org … 5http://nlp. stanford. edu/software/ corenlp. shtml 6We use the English Wikipedia dump from Jan. 4, 2012. … Poon and Domingos (2008) also use latent variables with Markov Logic, al- though with a completely different aim, ie for un- supervised coreference resolution. … Cited by 1 Related articles All 4 versions

A broad-coverage collection of portable NLP components for building shareable analysis pipelines RE de Castilho, I Gurevych – Proceedings of the Workshop on Open …, 2014 – aclweb.org … Several NLP tools (eg ClearNLP (2014), Stanford CoreNLP (Manning et al., 2014), MaltParser (Nivre et al., 2007), ClearTK (Ogren et al., 2009 … NLP tools Most NLP tools are not comprehensive suites that cover all tasks from tok- enization to eg coreference resolution, but are … Cited by 2 Related articles All 5 versions

Extracting Latent Attributes from Video Scenes Using Text as Background Knowledge A Tran, M Surdeanu, P Cohen – Lexical and Computational Semantics (* …, 2014 – aclweb.org … being chased. We implemented additional patterns to model passive voice and other exceptions. We used Stanford’s CoreNLP toolkit for syntactic dependency parsing and the downstream coreference resolution. 2: Once the … Related articles All 6 versions

Statistical script learning with multi-argument events K Pichotta, RJ Mooney – EACL 2014, 2014 – aclweb.org … 4.2 Experimental Evaluation For each document, we use the Stanford depen- dency parser (De Marneffe et al., 2006) to get syn- tactic information about the document; we then use the Stanford coreference resolution engine (Raghunathan et al … 4 of the Stanford CoreNLP system … Cited by 3 Related articles All 6 versions

Using Mined Coreference Chains as a Resource for a Semantic Task H Adel, H Schütze – aclweb.org … We use CoreNLP (Lee et al., 2011) to extract coref- erence chains from the … Except for the publicly available coreference resolution system, our approach does not need ex- ternal … 2011. Stanford’s multi-pass sieve corefer- ence resolution system at the CoNLL-2011 shared task. … Cited by 1 Related articles All 4 versions

A multi-document summarization system based on statistics and linguistic treatment R Ferreira, L de Souza Cabral, F Freitas… – Expert Systems with …, 2014 – Elsevier … Co-reference resolution: Co-reference resolution is the process by which different nouns that refer to a same entity are identified. The Stanford CoreNLP 1 tool was used here for indicating co-reference. When a co-reference is found, an edge in the graph with the relation is built. … Cited by 4 Related articles All 3 versions

A hierarchical taxonomy for classifying hardness of inference tasks M Gleize, B Grau – Proceedings of the Ninth International Conference on … – lrec-conf.org … We will use exam- ples of Winograd Schemas to demonstrate that coreference resolution can reach a very high difficulty level. … 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

A Tale of Two Entity Linking and Discovery Systems K Mazaitis, RC Wang, F Lin, B Dalvi… – Prof. Text Analysis …, 2014 – www-cgi.cs.cmu.edu … We used the Stanford CoreNLP NER tag- ger to do most of the extraction, augmented by a wrapper to exclude quoted text … Facts Extractor Stanford NLP DB … This was used for a simplified coreference resolution to han- dle cases where, eg, “Casey Jones” is used as the first entity … Cited by 2 Related articles All 3 versions

Unsupervised Sentence Enhancement for Automatic Summarization JCK Cheung, G Penn – aclweb.org … are competitive with a sen- tence fusion baseline in terms of con- tent quality, but better in terms of gram- maticality, and that the benefit of sen- tence enhancement relies crucially on an event coreference resolution algorithm us … stanford.edu/software/corenlp.shtml 2As … Cited by 2 Related articles All 4 versions

Story-based video retrieval in TV series using plot synopses M Tapaswi, M Bäuml, R Stiefelhagen – Proceedings of International …, 2014 – dl.acm.org … IMDb and Wikipedia. This aids in improving the person identification results and is necessary for the alignment. We perform part-of-speech tagging on the plot synopses using Stanford CoreNLP [1] toolbox. The tags are used … Cited by 3 Related articles All 3 versions

Sentiment Variations in Text for Persuasion Technology L Gatti, M Guerini, O Stock, C Strapparava – Persuasive Technology, 2014 – Springer … Then its dependencies and coreference relations are reconstructed using the Stanford CoreNLP suite [8,25]. … Stanford University (1994) 12. … Lee, H., Chang, A., Peirsman, Y., Chambers, N., Surdeanu, M., Jurafsky, D.: De- terministic coreference resolution based on entity-centric … Cited by 1 Related articles All 2 versions

Annotating relation mentions in tabloid press H Li, S Krause, F Xu, H Uszkoreit, R Hummel… – Proceedings of the …, 2014 – lrec-conf.org … 2. For sentences from 1): Verification of automatic concept-mention annotation of the NLP tools, includ- ing information about coreference resolution for per- sonal pronouns … 3 http://www. opencalais.com/ 4 http://sprout.dfki.de/ 5 http://nlp.stanford.edu/software/corenlp.shtml 3254 … Cited by 2 Related articles

Identifying interactions between chemical entities in biomedical text A Lamurias, JD Ferreira, FM Couto – Journal of integrative …, 2014 – journal.imbio.de … 2.5.1 Pre-processing As a pre-processing step on our RE module, we run the input text through Stanford CoreNLP to extract additional information provided by this tool: • Part-of-speech (POS) tagging [25]. • Parse tree [26]. … Coreference resolution Tokenization PRP$ its its its NN … Cited by 1 Related articles All 5 versions

An NLP Assistant for Clide T Kortkamp – arXiv preprint arXiv:1409.2073, 2014 – arxiv.org … clide-nlp uses the CoreNLP framework by the Stanford University’s NLP group that provides access to several NLP tools, including a coreference resolution system, which groups related entities in a text together, and a dependency parser, that describes the relations between … Related articles All 2 versions

“One Entity per Discourse” and “One Entity per Collocation” Improve Named-Entity Disambiguation A Barrena, E Agirre, B Cabaleiro, A Penas, A Soroa – aclweb.org … We have parsed them with the Stanford CoreNLP software (Klein and Manning, 2003), obtaining around 650 million dependen- cies (De Marneffe and Manning, 2008). … URL http://nlp. stanford. … Deterministic coreference resolution based on entity-centric, precision-ranked rules. … Related articles All 3 versions

Recognition of Sarcasm in Tweets Based on Concept Level Sentiment Analysis and Supervised Learning Approaches P Tungthamthiti, K Shirai, M Mohd – 2014 – anthology.aclweb.org … In this study, a simple coreference resolution method is applied to identify coherence of multiple sentences. … ConceptNet is a semantic network 2http://nlp.stanford.edu/software/corenlp. shtml 3http://conceptnet5.media.mit.edu Page 5. PACLIC 28 !408 …

Searching Locally-Defined Entities Z Wu, Y Lv, A Fuxman – Proceedings of the 23rd ACM International …, 2014 – dl.acm.org … Coref(ei,e) is a score obtained by performing coreference resolution. Since off-the-shelf tool- s for coreference resolution are computationally expensive and have low accuracy (about 70%) [18], we propose the heuristics that we describe next. … Related articles All 2 versions

Construction and evaluation of event graphs G Glavaš, J Šnajder – Natural Language Engineering, 2014 – Cambridge Univ Press … For coreference resolution, we do not consider mentions other than event anchors (eg, we do not consider pronominal anaphoric mentions). 3.2 Anchor extraction … 2 http://nlp.stanford. edu/downloads/corenlp.shtml Page 14. 14 G. Glavaš and J. Šnajder … Cited by 1 Related articles All 3 versions

Relation extraction for inferring access control rules from natural language artifacts J Slankas, X Xiao, L Williams, T Xie – Proceedings of Annual …, 2014 – engr.illinois.edu … The state of the art parsers have an F1 score of 90.4% [31]. Coreference resolution identifies whether or not two expressions in a document refer to the same identity. … 3 http://www-nlp. stanford.edu/software/corenlp.shtml shallow parsing) systems [33]. … Cited by 1 Related articles All 3 versions

Opinion Influence Analysis in Online Forum Threads DC Cercel, S Trausan-Matu – Symbolic and Numeric Algorithms …, 2014 – ieeexplore.ieee.org … of several steps grouped as shown in Figure 2. First of all, using the Stanford CoreNLP tool [11], specific natural language processing techniques are applied to each post in the forum thread: tokenization, part-of-speech tagging, syntactic parsing, and coreference resolution [12]. …

Mocking ads through mobile web services L Gatti, M Guerini, O Stock… – Computational …, 2014 – Wiley Online Library … It is then PoS tagged and morphologically analyzed with Stanford CoreNLP, which also gives us a typed dependency tree and coreference information (De Marneffe, MacCartney, and Manning 2006; Lee et al. 2013) to be added to the sentence constituents. … Cited by 1 Related articles

A Language Visualization System E Unal – 2014 – denizyuret.com … 24 3.3 CoreNLP CoreNLP [28] suite from Stanford provides many useful natural language analysis tools like parser, named entity recognizer, part of speech tagger and a coreference resolution system for English. These tools make a solid foundation for our language … Related articles All 2 versions

Advanced natural language processing for improved prosody in text-to-speech synthesis GI Schlünz – 2014 – dspace.nwu.ac.za … from POS tagging through constituent and dependency parsing to coreference resolution. The machine learning algorithms that are generally employed in NLP are discussed in detail in Schlünz (2010). The software to be used in this research is Stanford CoreNLP (http://nlp … Related articles

Semantic, Pragmatic and Discourse Analysis X Lu – Computational Methods for Corpus Annotation and …, 2014 – Springer … examples of tagged text. As is the case with the output from the Stanford Part-of-Speech (POS) Tagger (Toutanova et al. 2003 ), an underscore is used in the output to concatenate a word and its semantic tag. The sentences in … Related articles

Socially-Informed Timeline Generation for Complex Events L Wang, C Cardie, G Marchetti – constitution, 2014 – cs.cornell.edu … We extract parse trees, dependency trees, and coreference resolution results of articles and com- ments with Stanford CoreNLP (Manning et al., 2014). Sentences in articles are labeled with times- tamps using SUTime (Chang and Manning, 2012). …

Discriminative lexical semantic segmentation with gaps: running the MWE gamut N Schneider, E Danchik, C Dyer… – Transactions of the …, 2014 – tacl2013.cs.columbia.edu … 3.2 Evaluation Matching criteria. Given that most tokens do not belong to an MWE, to evaluate MWE identification we adopt a precision/recall-based measure from the coreference resolution literature. The MUC criterion (Vilain et al., 1995) measures precision and recall … Cited by 6 Related articles All 5 versions

Relation Extraction using Distant Supervision, SVMs, and Probabilistic First Order Logic MW Greaves – 2014 – reports-archive.adm.cs.cmu.edu Page 1. Relation Extraction using Distant Supervision, SVMs, and Probabilistic First Order Logic Malcolm W. Greaves CMU-CS-14-128 May 2014 School of Computer Science Computer Science Department Carnegie Mellon University Pittsburgh, PA Thesis Committee … Related articles All 4 versions

Identifying Latent Attributes from Video Scenes Using Knowledge Acquired From Large Collections of Text Documents AX Tran – 2014 – arizona.openrepository.com … 95 7.2.4 Coreference Resolution . . . . . … ated with participants in the relevant event (identified using syntactic patterns and coreference resolution). We design our models to output a normalized distribution over mental state labels for each video. … Related articles All 2 versions

Discriminative Lexical Semantic Segmentation with Gaps: Running the MWE Gamut NSEDC Dyer, NA Smith – acl2014.org … 3.2 Evaluation Matching criteria. Given that most tokens do not belong to an MWE, to evaluate MWE identification we adopt a precision/recall-based measure from the coreference resolution literature. The MUC criterion (Vilain et al., 1995) measures precision and recall … Related articles All 8 versions

INDREX: In-database relation extraction T Kilias, A Löser, P Andritsos – Information Systems, 2014 – Elsevier The management of text data has a long-standing history in the human mankind. A particular common task is extracting relations from text. Typically, the user pe. Related articles

Identifying interactions between chemical entities in text AFM Lamúrias – 2014 – repositorio.ul.pt Page 1. UNIVERSIDADE DE LISBOA FACULDADE DE CIÊNCIAS DEPARTAMENTO DE INFORMÁTICA Identifying Interactions Between Chemical Entities in Text André Francisco Martins Lamúrias DISSERTAÇÃO MESTRADO … Related articles All 5 versions

Aligning plot synopses to videos for story-based retrieval M Tapaswi, M Bäuml, R Stiefelhagen – International Journal of Multimedia …, 2014 – Springer … chain, we perform part-of-speech tag- ging on the sentences of the plot synopsis using the Stan- ford CoreNLP [2] software … Identity extraction from text To resolve pronouns and other character references (eg, sister, father, etc.), we perform coreference resolution [24] and cluster … Related articles All 2 versions

Realistic Dialogue Engine for Video Games CM Rose – 2014 – ir.lib.uwo.ca … 16 3.1.1 Named Entity Recognition and Classification ….. 17 3.1.2 Coreference Resolution ….. 19 … 59 6.4.2 Coreference Resolution ….. 59 …

ANA: Automated Nursing Agent K Quinn – 2014 – era.library.ualberta.ca … In this section we will discuss the contributions that ANA makes. Our system is built upon a basic information extraction framework using Stanford’s CoreNLP tools. … for our other classifiers. 2.3 Stanford CoreNLP The tools that Stanford’s NLP group provides are used in this thesis. … Related articles All 2 versions

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, ReVerb, PATTY and OLLIE, for making their data and source code available. I am extremely thankful to my colleagues at the Max Planck Institute for Informat- … Related articles All 8 versions

Dense Event Ordering with a Multi-Pass Architecture N Chambers, T Cassidy… – Transactions of the …, 2014 – tacl2013.cs.columbia.edu … Full time expression phrase Figure 3: Features for event-time edges. inform each other through the architecture’s transi- tive constraints. All models use the MaxEnt classifier from the Stanford CoreNLP with its default settings. Below we describe the features for each sieve. … Related articles All 7 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 … For text preprocessing we used the Stanford CoreNLP package [30]. This suite encompasses many NLP tools, including a tokenizer, a sentence splitter, a lemmatizer, a POS tagger, a named entity recognizer, a dependency parser, and a coreference resolution tool. … Related articles All 4 versions

Inducing Implicit Arguments via Cross-document Alignment: A Framework and its Applications M Roth – 2014 – archiv.ub.uni-heidelberg.de … implicit argument). Given such cases, we apply a cross-document coreference resolution tech- nique to also find co-referring entity mentions in the document in which the entity is implicit in the aligned structure. We describe … Cited by 1 Related articles All 4 versions

Entity-based Enrichment for Information Extraction and Retrieval J Dalton – 2014 – scholarworks.umass.edu … The last word indicates the query generation method from Section 5.4.3. . . . . 66 5.6 Phrase level F1 scores for base NER models described in Section 5.3 compared with the Stanford NER tagger on the CoNLL 2003 Named Entity Recognition test (b) set. . . . . … Related articles