Rozmiar: 11246
Komentarz:
|
Rozmiar: 23797
Komentarz:
|
Usunięcia zostały oznaczone w ten sposób. | Dodatki zostały oznaczone w ten sposób. |
Linia 1: | Linia 1: |
#acl +All:read Default | |
Linia 3: | Linia 4: |
The work reported here was carried out within the ''Computer-based methods for coreference resolution in Polish texts'' (PL: ''Komputerowe metody identyfikacji nawiązań w tekstach polskich'') project financed by the Polish National Science Centre (contract number 6505/B/T02/2011/40) and carried out between April 2011 and July 2014 at the Institute of Computer Science, Polish Academy of Sciences. It was targeted at the creation of innovative methods and tools for automated coreference resolution in Polish, with planned quality compared to state-of-the-art tools available for other languages. | The work reported here was carried out within the ''Computer-based methods for coreference resolution in Polish texts'' (PL: ''Komputerowe metody identyfikacji nawiązań w tekstach polskich'') project financed by the Polish [[http://www.ncn.gov.pl/?language=en|National Science Centre]] (contract number 6505/B/T02/2011/40) and carried out between April 2011 and July 2014 at the [[http://www2.ipipan.waw.pl/index.php/en/|Institute of Computer Science, Polish Academy of Sciences]]. It was targeted at the creation of innovative methods and tools for automated coreference resolution in Polish, with planned quality compared to state-of-the-art tools available for other languages. |
Linia 12: | Linia 13: |
== Publications and project presentations == | == Selected publications and project presentations == |
Linia 14: | Linia 15: |
1. [[http://www.degruyter.com/view/product/428667|Ogrodniczuk (ed.) – Coreference: Annotation, Resolution and Evaluation in Polish]]<<BR>> A monograph published by Walther De Gruyter. |
1. [[http://www.degruyter.com/view/product/428667|Ogrodniczuk, Głowińska, Kopeć, Savary, Zawisławska – Coreference: Annotation, Resolution and Evaluation in Polish]]<<BR>> <<BR>> A monograph published by Walther De Gruyter. The book presents work on coreference understanding, annotation and resolution of a Slavic language which can be applied to natural language processing in computers and software using English and other languages. The book presents specificities of reference, anaphora and coreference in Polish, establish identity-of-reference annotation model and present methodology used to create the corpus of Polish general nominal coreference. Various resolution approaches are presented, followed by their evaluation. By presenting the subsequent steps of building a coreference-related component of the natural language processing toolset, the volume also serves as a reference book on state-of-the art methods in carrying out coreference projects for new languages and a tutorial for NLP practitioners.<<BR>> <<BR>> |
Linia 17: | Linia 18: |
* BibTeX citation . . . |
|
Linia 21: | Linia 19: |
1. [[attachment:poltal.pdf|Ogrodniczuk, Wójcicka, Głowińska, Kopeć – Nested Mention Detection for Polish Coreference Resolution]] (PolTAL 2014 conference paper) | 1. [[attachment:poltal.pdf|Ogrodniczuk, Wójcicka, Głowińska, Kopeć – Nested Mention Detection for Polish Coreference Resolution]]<<BR>> <<BR>> |
Linia 23: | Linia 21: |
* BibTeX citation * Springer LNCS link 1. [[attachment:cognitive-linguistics.pdf|Zawisławska, Ogrodniczuk – The same or just much the same? Problems with coreference from the reader’s perspective]] (book chapter) * BibTeX citation * book page * * konferencja 'Cognitive Linguistics in the Year 2012', Wrocław, 17-18 września 2012: [[attachment:wroclaw-2012.pdf|Zawisławska, Ogrodniczuk – Ten sam czy taki sam? O problemach z identycznością z perspektywy odbiorcy]] (zob. też [[attachment:wroclaw-2012-opis.pdf|krótki opis]]) |
[[http://poltal.ipipan.waw.pl/|PolTAL 2014]] (September 17-19, 2014, Warsaw) conference paper describing the results of creating a shallow grammar of Polish capable of detecting multi-level nested nominal phrases, intended to be used as mentions in coreference resolution tasks. The work is based on existing grammar developed for the National Corpus of Polish and evaluated on manually annotated Polish Coreference Corpus.<<BR>> <<BR>> |
Linia 34: | Linia 24: |
1. [[attachment:lrec-2014.pdf|Ogrodniczuk, Kopeć, Savary – Polish Coreference Corpus in Numbers]] (LREC 2014 conference paper) | 1. [[http://nlp.ipipan.waw.pl/Bib/zaw:ogro:14:cl.pdf|Zawisławska, Ogrodniczuk – The same or just much the same? Problems with coreference from the reader’s perspective]]<<BR>> <<BR>> |
Linia 36: | Linia 26: |
* BibTeX citation * Springer LNCS link * [[attachment:lrec-2014-plakat.pdf|LREC 2014 poster]] |
A Peter Lang book chapter and [[https://sites.google.com/site/coglin2012/|Cognitive Linguistics in the Year 2012]] (September 17-18, 2012) conference paper presenting problems related to coreference annotation in the Polish Coreference corpus. There are three main causes of annotator errors: grammatical (e.g. the lack of an article system in Polish), semantic (the so-called co-extension, involving lexical relations between words) and cognitive (the annotators’ insufficient real-world knowledge about certain relationships). Apart from provided examples of different kinds of annotation problems, the paper analyzes how coreference relates to identity in extralinguistic reality and in discourse. It also discusses the distinction between coreference and anaphora, as well as dependence of coreference on specific properties of Polish grammar. It questions M. Recasens’ theory of near-identity and the need for its detailed classification.<<BR>> <<BR>> See [[http://zil.ipipan.waw.pl/publications/bibtex/zaw%3Aogro%3A14%3Acl|BibTeX citation]], [[attachment:wroclaw-2012.pdf|conference presentation]] and [[http://www.peterlang.com/index.cfm?event=cmp.ccc.seitenstruktur.detailseiten&seitentyp=produkt&pk=74449&cid=462|the book link]].<<BR>> <<BR>> 1. [[http://www.lrec-conf.org/proceedings/lrec2014/pdf/1088_Paper.pdf|Ogrodniczuk, Kopeć, Savary – Polish Coreference Corpus in Numbers]] [[http://lrec2014.lrec-conf.org/en/|LREC 2014]] (May 26-31, 2014, Reykjavik) conference paper on a preliminary interpretation of the occurrence of different types of linguistic constructs in the manually-annotated Polish Coreference Corpus by providing analyses of various statistical properties related to mentions, clusters and near-identity links. Among others, frequency of mentions, zero subjects and singleton clusters is presented, as well as the average mention and cluster size. We also show that some coreference clustering constraints, such as gender or number agreement, are frequently not valid in case of Polish. The need for lemmatization for automatic coreference resolution is supported by an empirical study. Correlation between cluster and mention count within a text is investigated, with short characteristics of outlier cases. We also examine this correlation in each of the 14 text domains present in the corpus and show that none of them has abnormal frequency of outlier texts regarding the cluster/mention ratio. Finally, we report on our negative experiences concerning the annotation of the near-identity relation. In the conclusion we put forward some guidelines for the future research in the area.<<BR>> <<BR>> See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro%3Aetal%3A14%3Alrec|BibTeX citation]] and [[attachment:lrec-2014-plakat.pdf|conference poster]].<<BR>> <<BR>> |
Linia 41: | Linia 37: |
1. EACL 2014: [[attachment:eacl-demo.pdf|Kopeć – MMAX2 for coreference annotation]] | 1. [[http://www.aclweb.org/anthology/E14-4043|Kopeć – Zero subject detection for Polish]]<<BR>> <<BR>> |
Linia 43: | Linia 39: |
* BibTeX citation * Springer LNCS link |
[[http://eacl2014.org/|EACL 2014]] (April 26-30, 2014, Gothenburg) paper on the first machine learning experiments on detection of null subjects in Polish. It emphasizes the role of zero subject detection as the part of mention detection – the initial step of end-to-end coreference resolution. Anaphora resolution is not studied in this article.<<BR>> <<BR>> See [[http://zil.ipipan.waw.pl/publications/bibtex/kop%3A14%3Aeacl%3Ashort|BibTeX citation]] and [[attachment:eacl-2014-prezentacja.pdf|EACL presentation]].<<BR>> <<BR>> |
Linia 47: | Linia 44: |
1. EACL 2014: [[attachment:EACL-2014-short.pdf|Kopeć – Zero subject detection for Polish]] (zob. też [[attachment:eacl-2014-prezentacja.pdf|prezentację]] i [[attachment:EACL-2013-1.pdf|wersję długą]]) | 1. [[http://www.aclweb.org/anthology/E14-2024|Kopeć – MMAX2 for coreference annotation]]<<BR>> <<BR>> |
Linia 49: | Linia 46: |
konferencja EACL 2014, Göteborg, 29 kwietnia 2014: | EACL 2014 demo session paper presenting major modifications in the MMAX2 manual annotation tool, which were implemented for the coreference annotation of Polish texts. Among other things, a new feature of adjudication is described, as well as some general insight into the manual annotation tool selection process for the natural language processing tasks.<<BR>> <<BR>> |
Linia 51: | Linia 48: |
* BibTeX citation * Springer LNCS link * [[attachment:eacl-2014-prezentacja.pdf|EACL 2014 presentation]] |
See [[http://zil.ipipan.waw.pl/publications/bibtex/kop%3A14%3Aeacl%3Ademo|BibTeX citation]].<<BR>> <<BR>> |
Linia 56: | Linia 51: |
1. ACIIDS 2014: [[attachment:ACIIDS-2014.pdf|Kopeć, Ogrodniczuk – Inter-Annotator Agreement in Coreference Annotation of Polish]] (zob. też [[attachment:aciids-2014-plakat.pdf|plakat]]) | 1. [[attachment:ACIIDS-2014.pdf|Kopeć, Ogrodniczuk – Inter-Annotator Agreement in Coreference Annotation of Polish]]<<BR>> <<BR>> |
Linia 58: | Linia 53: |
* BibTeX citation * Springer LNCS link * [[attachment:aciids-2014-plakat.pdf|ACIIDS 2014 poster]] |
[[http://www.ic.kmitl.ac.th/aciids2014/|ACIIDS 2014]] (April 7-9, 2014, Bangkok) conference paper discussing different methods of estimating the inter-annotator agreement in manual annotation of Polish coreference and proposing a new BLANC-based annotation agreement metric. The commonly used agreement indicators are calculated for mention detection, semantic head annotation, near-identity markup and coreference resolution.<<BR>> <<BR>> |
Linia 62: | Linia 55: |
1. seminarium IPI, Warszawa, 27 stycznia 2014: [[attachment:seminarium-2014-01.pdf|Kopeć – Automatyczne wykrywanie podmiotu zerowego]] * [[http://nlp.ipipan.waw.pl/NLP-SEMINAR/140127.html|short description]] |
See [[http://zil.ipipan.waw.pl/publications/bibtex/kop:ogro:14:aciids|BibTeX citation]], [[attachment:aciids-2014-plakat.pdf|ACIIDS 2014 poster]] and [[http://link.springer.com/chapter/10.1007/978-3-319-05503-9_15|Springer link]].<<BR>> <<BR>> |
Linia 67: | Linia 58: |
1. LTC 2013: [[attachment:ltc-2013.pdf|Ogrodniczuk, Głowińska, Kopeć, Savary, Zawisławska – Polish Coreference Corpus]] (zob. też [[attachment:ltc-pcc-prezentacja.pdf|prezentację]]) | 1. [[http://nlp.ipipan.waw.pl/NLP-SEMINAR/140127.pdf|Kopeć – Automatyczne wykrywanie podmiotu zerowego]]<<BR>> <<BR>> |
Linia 69: | Linia 60: |
konferencja LTC 2013, Poznań, 9 grudnia 2013: * BibTeX citation * Springer LNCS link * [[attachment:ltc-pcc-prezentacja.pdf|LTC 2013 presentation]] |
Presentation at the Natural Language Processing Seminar (January 27, 2014, Warsaw) discussing automated null subject detection (in Polish).<<BR>> <<BR>> |
Linia 76: | Linia 63: |
1. LTC 2013: [[attachment:ltc-2013-2.pdf|Nitoń – Evaluation of Uryupina’s coreference resolution features for Polish]] (zob. też [[attachment:ltc-niton-prezentacja.pdf|prezentację]]) | 1. [[http://nlp.ipipan.waw.pl/Bib/ogro:etal:13:ltc.pdf|Ogrodniczuk, Głowińska, Kopeć, Savary, Zawisławska – Polish Coreference Corpus]]<<BR>> <<BR>> |
Linia 78: | Linia 65: |
konferencja LTC 2013, Poznań, 7 grudnia 2013: | [[http://www.ltc.amu.edu.pl/|LTC 2013]] (December 7-9, 2013, Poznań) conference paper describing the composition, annotation process and availability of the newly constructed Polish Coreference Corpus – a large Polish corpus of general nominal coreference. The tools used in the process and final linguistic representation formats are also presented.<<BR>> <<BR>> |
Linia 80: | Linia 67: |
* BibTeX citation * Springer LNCS link * [[attachment:ltc-niton-prezentacja.pdf|LTC 2013 presentation]] |
See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro:etal:13:ltc|BibTeX citation]] and [[attachment:ltc-pcc-prezentacja.pdf|LTC 2013 presentation]].<<BR>> <<BR>> |
Linia 85: | Linia 70: |
1. MIKE 2013: [[attachment:mike.pdf|Ogrodniczuk – Discovery of Common Nominal Facts for Coreference Resolution: Proof of concept]] (zob. też [[attachment:mike-prezentacja.pdf|prezentację]]) | 1. [[http://nlp.ipipan.waw.pl/Bib/nito:13:ltc.pdf|Nitoń – Evaluation of Uryupina’s coreference resolution features for Polish]]<<BR>> <<BR>> |
Linia 87: | Linia 72: |
konferencja MIKE 2013, Virudhunagar, 18 grudnia 2013: | LTC 2013 conference paper describing evaluation of a set of surface, syntactic and anaphoric features proposed in Uryupina 2007 and their usefulness for coreference resolution in Polish texts.<<BR>> <<BR>> |
Linia 89: | Linia 74: |
* BibTeX citation * Springer LNCS link * [[attachment:mike-prezentacja.pdf|MIKE 2013 presentation]] |
See [[http://zil.ipipan.waw.pl/publications/bibtex/nito:13:ltc|BibTeX citation]] and [[attachment:ltc-niton-prezentacja.pdf|LTC 2013 presentation]].<<BR>> <<BR>> |
Linia 94: | Linia 77: |
1. CNCCL 2013: [[attachment:cnccl-2013.pdf|Ogrodniczuk, Głowińska, Kopeć, Savary, Zawisławska – Interesting Linguistic Features in Coreference Annotation of a Highly Inflectional Language]] (zob. też [[attachment:cnccl.pdf|plakat]]) | 1. [[http://nlp.ipipan.waw.pl/Bib/ogro:13:mike.pdf|Ogrodniczuk – Discovery of Common Nominal Facts for Coreference Resolution: Proof of concept]]<<BR>> <<BR>> |
Linia 96: | Linia 79: |
* BibTeX citation * Springer LNCS link * [[attachment:cnccl.pdf|CNCCL 2013 poster]] |
[[http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=30962©ownerid=51382|MIKE 2013]] (December 18-20, 2013, Virudhunagar) conference paper reporting on the preliminary experiment aimed at verification whether extraction of nominal facts corresponding to world knowledge from both structured and unstructured data could be effectively performed and its results used as a source of pragmatic knowledge for coreference resolution in Polish. Being the proof-of-concept only, this approach is work in progress and is intended to be further validated in a full-scale project.<<BR>> <<BR>> See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro:13:mike|BibTeX citation]], [[http://link.springer.com/chapter/10.1007/978-3-319-03844-5_69|Springer LNCS link]] and [[attachment:mike-prezentacja.pdf|MIKE 2013 presentation]].<<BR>> <<BR>> |
Linia 101: | Linia 84: |
1. NLDB 2013: [[attachment:nldb-2013.pdf|Ogrodniczuk, Lenart – A Multi-Purpose Online Toolset for NLP Applications]] | 1. [[http://nlp.ipipan.waw.pl/Bib/ogro:etal:13:cnccl.pdf|Ogrodniczuk, Głowińska, Kopeć, Savary, Zawisławska – Interesting Linguistic Features in Coreference Annotation of a Highly Inflectional Language]]<<BR>> <<BR>> |
Linia 103: | Linia 86: |
* BibTeX citation * Springer LNCS link |
[[http://210.29.169.226/CNCCL2013/en/home.html|CCL 2013/NLP-NABD 2013]] (October 10-12, 2013, Suzhou) conference paper reporting on linguistic features and decisions that we find vital in the process of annotation and resolution of coreference for highly inflectional languages. The presented results have been collected during preparation of a corpus of general direct nominal coreference of Polish. Starting from the notion of a mention, its borders and potential vs. actual referentiality, we discuss the problem of complete and near-identity, zero subjects and dominant expressions. We also present interesting linguistic cases influencing the coreference resolution such as the difference between semantic and syntactic heads or the phenomenon of coreference chains made of indefinite pronouns.<<BR>> <<BR>> See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro:etal:13:cnccl|BibTeX citation]], [[http://link.springer.com/chapter/10.1007/978-3-642-41491-6_10|Springer LNCS link]] and [[attachment:cnccl.pdf|CNCCL 2013 poster]].<<BR>> <<BR>> |
Linia 107: | Linia 91: |
1. LP&IIS 2013: [[attachment:iis-2013.pdf|Ogrodniczuk – Translation- and projection-based unsupervised coreference resolution for Polish]] (zob. też [[attachment:iis-prezentacja.pdf|prezentację]]) | 1. [[http://nlp.ipipan.waw.pl/Bib/ogro:len:13:nldb.pdf|Ogrodniczuk, Lenart – A Multi-Purpose Online Toolset for NLP Applications]]<<BR>> <<BR>> |
Linia 109: | Linia 93: |
konferencja LP&IIS 2013, Warszawa, 18 czerwca 2013: | [[http://nldb.csesalford.com/index.htm|NLDB 2013]] (June 19-21, 2013, Manchester) conference paper presenting a new implementation of the multipurpose set of NLP tools for Polish, made available online in a common web service framework. The tool set comprises a morphological analyzer, a tagger, a named entity recognizer, a dependency parser, a constituency parser and a coreference resolver. Additionally, a web application offering chaining capabilities and a common BRAT-based presentation framework is presented.<<BR>> <<BR>> |
Linia 111: | Linia 95: |
* BibTeX citation * Springer LNCS link * [[attachment:iis-prezentacja.pdf|LP&IIS 2013 presentation]] |
See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro:len:13:nldb|BibTeX citation]] and [[http://link.springer.com/chapter/10.1007/978-3-642-38824-8_46|Springer LNCS link]].<<BR>> <<BR>> |
Linia 116: | Linia 98: |
1. CICLING 2013: [[attachment:cicling-2013.pdf|Ogrodniczuk, Zawisławska, Głowińska, Savary – Coreference annotation schema for an inflectional language]] | 1. [[http://nlp.ipipan.waw.pl/Bib/ogro:13:iis.pdf|Ogrodniczuk – Translation- and projection-based unsupervised coreference resolution for Polish]]<<BR>> <<BR>> |
Linia 118: | Linia 100: |
* BibTeX citation * Springer LNCS link |
[[http://iis.ipipan.waw.pl/lpiis/|LP&IIS 2013]] (June 17-18, 2013, Warsaw) conference paper describing the test of the translation- and projection-based method of implementation of a coreference resolver for an inflectional language. The paper also presents evaluation of the result on a corpus of general coreference and compare the results with state-of-the-art solutions of this type for other languages.<<BR>> <<BR>> See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro:13:iis|BibTeX citation]], [[http://link.springer.com/chapter/10.1007/978-3-642-38634-3_14|Springer LNCS link]] and [[attachment:iis-prezentacja.pdf|LP&IIS 2013 presentation]].<<BR>> <<BR>> |
Linia 122: | Linia 105: |
1. seminarium IPI, Warszawa, 3 grudnia 2012: [[attachment:seminarium-2012-12.pdf|Ogrodniczuk, Głowińska, Zawisławska, Kopeć, Savary – Polski korpus koreferencyjny: wersja wstępna]] * [[http://nlp.ipipan.waw.pl/NLP-SEMINAR/121203.html|short description]] |
1. [[http://nlp.ipipan.waw.pl/Bib/ogro:etal:13:cicling.pdf|Ogrodniczuk, Zawisławska, Głowińska, Savary – Coreference annotation schema for an inflectional language]]<<BR>> <<BR>> |
Linia 125: | Linia 107: |
1. KI 2012: [[attachment:ki-2012.pdf|Ogrodniczuk, Zawisławska – Semantic Approach to Identity in Coreference Resolution Task]] | [[http://www.cicling.org/2013/|CICLING 2013]] (March 24–30, 2013, Samos) conference paper commenting on the experience gained in preparation of a coreference corpus for an inflectional and free-word-order language carried out in an ongoing project, aiming at creating tools for coreference resolution. Starting with a clarification of the relation between noun groups and mentions, through definition of the annotation scope and strategies, up to actual decisions for borderline cases, we present the process of building the first, to our best knowledge, corpus of general coreference of Polish.<<BR>> <<BR>> |
Linia 127: | Linia 109: |
* BibTeX citation * Springer LNCS link 1. HLT 2012: [[attachment:hlt-2012.pdf|Kopeć, Ogrodniczuk – LRT for Polish coreference annotation and resolution]] Poster presented at |
See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro:etal:13:cicling|BibTeX citation]] and [[http://link.springer.com/chapter/10.1007%2F978-3-642-37247-6_32|Springer LNCS link]].<<BR>> <<BR>> |
Linia 135: | Linia 112: |
1. LREC 2012: [[attachment:lrec-2012.pdf|Kopeć, Ogrodniczuk – Creating a Coreference Resolution System for Polish]] (zob. też [[attachment:lrec-2012-plakat.pdf|plakat]]) | 1. [[http://nlp.ipipan.waw.pl/NLP-SEMINAR/121203.pdf|Ogrodniczuk, Głowińska, Zawisławska, Kopeć, Savary – Polski korpus koreferencyjny: wersja wstępna]]<<BR>> <<BR>> |
Linia 137: | Linia 114: |
* BibTeX citation * Springer LNCS link * [[attachment:lrec-2012-plakat.pdf|LREC 2012 poster]] 1. seminarium IPI, Warszawa, 5 marca 2012: [[attachment:seminarium-2012-03.pdf|Ogrodniczuk, Głowińska, Zawisławska, Kopeć, Savary – Wstępna weryfikacja typologii i strategii anotacji koreferencji w tekstach polskich]] * [[http://nlp.ipipan.waw.pl/NLP-SEMINAR/120305.html|short description]] |
Presentation at the Natural Language Processing Seminar (December 3, 2012, Warsaw) discussing methodology of the construction of the Polish Coreference Corpus (in Polish).<<BR>> <<BR>> |
Linia 146: | Linia 117: |
1. LTC 2011: [[attachment:ltc-2011.pdf|Ogrodniczuk, Kopeć – End-to-end coreference resolution baseline system for Polish]] (zob. też [[attachment:ltc-2011-wystapienie.pdf|prezentację]]) | 1. [[http://hltdays.ipipan.waw.pl/pdf/lrt-for-polish-coreference-annotation-and-resolution.pdf|Kopeć, Ogrodniczuk – LRT for Polish coreference annotation and resolution]]<<BR>> <<BR>> |
Linia 148: | Linia 119: |
konferencja LTC 2011, Poznań, 26 listopada 2011: * BibTeX citation * Springer LNCS link * [[attachment:ltc-2011-wystapienie.pdf|LTC 2011 presentation]] |
[[http://hltdays.ipipan.waw.pl/|HLT Days 2012]] (September 27-28, 2012, Warsaw) poster presented in Language Resources and Tools Hackathon session.<<BR>> <<BR>> |
Linia 155: | Linia 122: |
1. DAARC 2011: [[attachment:daarc-2011.pdf|Ogrodniczuk, Kopeć – Rule-based coreference resolution module for Polish]] (DAARC 2011 conference paper) | 1. [[http://glass.ipipan.waw.pl/publications/download/ogro%3Azaw%3A12%3Aki|Ogrodniczuk, Zawisławska – Semantic Approach to Identity in Coreference Resolution Task]]<<BR>> <<BR>> |
Linia 157: | Linia 124: |
* BibTeX citation * Springer LNCS link * [[attachment:daarc-2011-plakat.pdf|DAARC 2011 poster]] |
[[http://www.dfki.de/KI2012/|KI 2012]] (September 24-27, 2012, Saarbrücken) coreference paper confronting the idea of continuous nature of identity with experimental data for Polish, resulting in a new approach to this notion. It extends the definition of coreference with speaker/recipient relation, believed to be valid for all languages, and explains the near-identity with lexical and conceptual means. The theory is supported with Polish-English examples presenting difficulties in coreference interpretation.<<BR>> <<BR>> |
Linia 161: | Linia 126: |
See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro%3Azaw%3A12%3Aki|BibTeX citation]] and [[http://link.springer.com/chapter/10.1007/978-3-642-33347-7_23|Springer LNCS link]].<<BR>> <<BR>> 1. [[http://www.lrec-conf.org/proceedings/lrec2012/pdf/1064_Paper.pdf|Kopeć, Ogrodniczuk – Creating a Coreference Resolution System for Polish]]<<BR>> <<BR>> [[http://www.lrec-conf.org/lrec2012/|LREC 2012]] (May 21-27, 2012, Istanbul) conference paper presenting the results of the first attempt of the coreference resolution for Polish using statistical methods. It presents the conclusions from the process of adapting the Beautiful Anaphora Resolution Toolkit (BART; a system primarily designed for the English language) for Polish and collates its evaluation results with those of the previously implemented rule-based system. Finally, we describe our plans for the future usage of the tool and highlight the upcoming research to be conducted, such as the experiments of a larger scale and the comparison with other machine learning tools.<<BR>> <<BR>> See [[http://zil.ipipan.waw.pl/publications/bibtex/kop%3Aogro%3A12%3Alrec|BibTeX citation]] and [[attachment:lrec-2012-plakat.pdf|LREC 2012 poster]].<<BR>> <<BR>> 1. [[http://nlp.ipipan.waw.pl/NLP-SEMINAR/120305.pdf|Ogrodniczuk, Głowińska, Zawisławska, Kopeć, Savary – Wstępna weryfikacja typologii i strategii anotacji koreferencji w tekstach polskich]]<<BR>> <<BR>> Presentation at the Natural Language Processing Seminar (March 5, 2012, Warsaw) discussing typology of coreference and strategies of its annotation (in Polish).<<BR>> <<BR>> 1. [[attachment:ltc-2011.pdf|Ogrodniczuk, Kopeć – End-to-end coreference resolution baseline system for Polish]]<<BR>> <<BR>> [[http://www.ltc.amu.edu.pl/a2011/|LTC 2011]] (November 25-27, 2011, Poznań) conference paper presenting the results of the first attempt of coreference resolution for Polish, intended to create a useful baseline for future experiments with this topic. The resulting implementation is designed to run either on true mention boundaries (discovering coreference chains between them) or in an end-to-end manner, performing their automatic detection as the first step. The system uses a few rich rules, corresponding to syntactic constraints (elimination of nested nominal groups), syntactic filters (elimination of syntactic incompatible heads), semantic filters (wordnet-derived compatibility) and selection (weighted scoring). Results are evaluated against human annotation for two commonly used baseline variants of the resolver (all-singletons/head-match) and two target rule-based settings. The best working method is analysed, showing simple statistics about the two classes of errors made by the system.<<BR>> <<BR>> See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro%3Akop%3A11%3Altc|BibTeX citation]] and [[attachment:ltc-2011-wystapienie.pdf|LTC 2011 presentation]].<<BR>> <<BR>> 1. [[attachment:daarc-2011.pdf|Ogrodniczuk, Kopeć – Rule-based coreference resolution module for Polish]]<<BR>> <<BR>> [[http://daarc2011.clul.ul.pt/|DAARC 2011]] (October 6-7, 2011, Faro) conference paper presenting the results of the first attempt of coreference resolution for Polish running on true mention boundaries and using a few rich rules, corresponding to syntactic constraints (elimination of nested nominal groups), syntactic filters (elimination of syntactic incompatible heads), semantic filters (wordnet-derived compatibility) and selection (weighted scoring). The results are compared to human annotation and presented in four sets: with two common baselines: all singletons/head-match, and two slightly more complex settings with four and five rules.<<BR>> <<BR>> See [[http://zil.ipipan.waw.pl/publications/bibtex/ogro%3Akop%3A11%3Adaarc|BibTeX citation]] and [[attachment:daarc-2011-plakat.pdf|DAARC 2011 poster]]. |
|
Linia 171: | Linia 163: |
* works related to coreference-based approach to summarization were carried out within [[[[http://phd.ipipan.waw.pl/|PhD studies]] of Mateusz Kopeć at the Institute of Computer Science, Polish Academy of Sciences | * works related to coreference-based approach to summarization were carried out within [[http://phd.ipipan.waw.pl/|PhD studies]] of Mateusz Kopeć at the Institute of Computer Science, Polish Academy of Sciences |
Linia 177: | Linia 169: |
* contacts established with the parallel French coreference annotation project [[[[http://tln.li.univ-tours.fr/Tln_Ancor.html|ANCOR]] were also beneficial for some of our scientific results and helped relate the CORE project more deeply to the international coreference community. | * contacts established with the parallel French coreference annotation project [[http://tln.li.univ-tours.fr/Tln_Ancor.html|ANCOR]] were also beneficial for some of our scientific results and helped relate the CORE project more deeply to the international coreference community. |
Linia 183: | Linia 175: |
* Maciej Ogrodniczuk — principal investigator | * [[http://zil.ipipan.waw.pl/MaciejOgrodniczuk|Maciej Ogrodniczuk]] — principal investigator |
Linia 196: | Linia 188: |
but there were numerous other people, mainly colleagues from the Linguistic Engineering Group at the Institute of Computer Science, Polish Academy of Sciences, who contributed to various stages of the project with their selfless help: |
but there were numerous other people, mainly colleagues from the [[http://zil.ipipan.waw.pl/|Linguistic Engineering Group at the Institute of Computer Science, Polish Academy of Sciences]], who contributed to various stages of the project with their selfless help: |
The CORE project
The work reported here was carried out within the Computer-based methods for coreference resolution in Polish texts (PL: Komputerowe metody identyfikacji nawiązań w tekstach polskich) project financed by the Polish National Science Centre (contract number 6505/B/T02/2011/40) and carried out between April 2011 and July 2014 at the Institute of Computer Science, Polish Academy of Sciences. It was targeted at the creation of innovative methods and tools for automated coreference resolution in Polish, with planned quality compared to state-of-the-art tools available for other languages.
Project results
Selected publications and project presentations
Ogrodniczuk, Głowińska, Kopeć, Savary, Zawisławska – Coreference: Annotation, Resolution and Evaluation in Polish
A monograph published by Walther De Gruyter. The book presents work on coreference understanding, annotation and resolution of a Slavic language which can be applied to natural language processing in computers and software using English and other languages. The book presents specificities of reference, anaphora and coreference in Polish, establish identity-of-reference annotation model and present methodology used to create the corpus of Polish general nominal coreference. Various resolution approaches are presented, followed by their evaluation. By presenting the subsequent steps of building a coreference-related component of the natural language processing toolset, the volume also serves as a reference book on state-of-the art methods in carrying out coreference projects for new languages and a tutorial for NLP practitioners.
Ogrodniczuk, Wójcicka, Głowińska, Kopeć – Nested Mention Detection for Polish Coreference Resolution
PolTAL 2014 (September 17-19, 2014, Warsaw) conference paper describing the results of creating a shallow grammar of Polish capable of detecting multi-level nested nominal phrases, intended to be used as mentions in coreference resolution tasks. The work is based on existing grammar developed for the National Corpus of Polish and evaluated on manually annotated Polish Coreference Corpus.
A Peter Lang book chapter and Cognitive Linguistics in the Year 2012 (September 17-18, 2012) conference paper presenting problems related to coreference annotation in the Polish Coreference corpus. There are three main causes of annotator errors: grammatical (e.g. the lack of an article system in Polish), semantic (the so-called co-extension, involving lexical relations between words) and cognitive (the annotators’ insufficient real-world knowledge about certain relationships). Apart from provided examples of different kinds of annotation problems, the paper analyzes how coreference relates to identity in extralinguistic reality and in discourse. It also discusses the distinction between coreference and anaphora, as well as dependence of coreference on specific properties of Polish grammar. It questions M. Recasens’ theory of near-identity and the need for its detailed classification.
See BibTeX citation, conference presentation and the book link.
Ogrodniczuk, Kopeć, Savary – Polish Coreference Corpus in Numbers
LREC 2014 (May 26-31, 2014, Reykjavik) conference paper on a preliminary interpretation of the occurrence of different types of linguistic constructs in the manually-annotated Polish Coreference Corpus by providing analyses of various statistical properties related to mentions, clusters and near-identity links. Among others, frequency of mentions, zero subjects and singleton clusters is presented, as well as the average mention and cluster size. We also show that some coreference clustering constraints, such as gender or number agreement, are frequently not valid in case of Polish. The need for lemmatization for automatic coreference resolution is supported by an empirical study. Correlation between cluster and mention count within a text is investigated, with short characteristics of outlier cases. We also examine this correlation in each of the 14 text domains present in the corpus and show that none of them has abnormal frequency of outlier texts regarding the cluster/mention ratio. Finally, we report on our negative experiences concerning the annotation of the near-identity relation. In the conclusion we put forward some guidelines for the future research in the area.
See BibTeX citation and conference poster.
Kopeć – Zero subject detection for Polish
EACL 2014 (April 26-30, 2014, Gothenburg) paper on the first machine learning experiments on detection of null subjects in Polish. It emphasizes the role of zero subject detection as the part of mention detection – the initial step of end-to-end coreference resolution. Anaphora resolution is not studied in this article.
See BibTeX citation and EACL presentation.
Kopeć – MMAX2 for coreference annotation
EACL 2014 demo session paper presenting major modifications in the MMAX2 manual annotation tool, which were implemented for the coreference annotation of Polish texts. Among other things, a new feature of adjudication is described, as well as some general insight into the manual annotation tool selection process for the natural language processing tasks.
See BibTeX citation.
Kopeć, Ogrodniczuk – Inter-Annotator Agreement in Coreference Annotation of Polish
ACIIDS 2014 (April 7-9, 2014, Bangkok) conference paper discussing different methods of estimating the inter-annotator agreement in manual annotation of Polish coreference and proposing a new BLANC-based annotation agreement metric. The commonly used agreement indicators are calculated for mention detection, semantic head annotation, near-identity markup and coreference resolution.
See BibTeX citation, ACIIDS 2014 poster and Springer link.
Kopeć – Automatyczne wykrywanie podmiotu zerowego
Presentation at the Natural Language Processing Seminar (January 27, 2014, Warsaw) discussing automated null subject detection (in Polish).
Ogrodniczuk, Głowińska, Kopeć, Savary, Zawisławska – Polish Coreference Corpus
LTC 2013 (December 7-9, 2013, Poznań) conference paper describing the composition, annotation process and availability of the newly constructed Polish Coreference Corpus – a large Polish corpus of general nominal coreference. The tools used in the process and final linguistic representation formats are also presented.
See BibTeX citation and LTC 2013 presentation.
Nitoń – Evaluation of Uryupina’s coreference resolution features for Polish
LTC 2013 conference paper describing evaluation of a set of surface, syntactic and anaphoric features proposed in Uryupina 2007 and their usefulness for coreference resolution in Polish texts.
See BibTeX citation and LTC 2013 presentation.
Ogrodniczuk – Discovery of Common Nominal Facts for Coreference Resolution: Proof of concept
MIKE 2013 (December 18-20, 2013, Virudhunagar) conference paper reporting on the preliminary experiment aimed at verification whether extraction of nominal facts corresponding to world knowledge from both structured and unstructured data could be effectively performed and its results used as a source of pragmatic knowledge for coreference resolution in Polish. Being the proof-of-concept only, this approach is work in progress and is intended to be further validated in a full-scale project.
See BibTeX citation, Springer LNCS link and MIKE 2013 presentation.
CCL 2013/NLP-NABD 2013 (October 10-12, 2013, Suzhou) conference paper reporting on linguistic features and decisions that we find vital in the process of annotation and resolution of coreference for highly inflectional languages. The presented results have been collected during preparation of a corpus of general direct nominal coreference of Polish. Starting from the notion of a mention, its borders and potential vs. actual referentiality, we discuss the problem of complete and near-identity, zero subjects and dominant expressions. We also present interesting linguistic cases influencing the coreference resolution such as the difference between semantic and syntactic heads or the phenomenon of coreference chains made of indefinite pronouns.
See BibTeX citation, Springer LNCS link and CNCCL 2013 poster.
Ogrodniczuk, Lenart – A Multi-Purpose Online Toolset for NLP Applications
NLDB 2013 (June 19-21, 2013, Manchester) conference paper presenting a new implementation of the multipurpose set of NLP tools for Polish, made available online in a common web service framework. The tool set comprises a morphological analyzer, a tagger, a named entity recognizer, a dependency parser, a constituency parser and a coreference resolver. Additionally, a web application offering chaining capabilities and a common BRAT-based presentation framework is presented.
See BibTeX citation and Springer LNCS link.
Ogrodniczuk – Translation- and projection-based unsupervised coreference resolution for Polish
LP&IIS 2013 (June 17-18, 2013, Warsaw) conference paper describing the test of the translation- and projection-based method of implementation of a coreference resolver for an inflectional language. The paper also presents evaluation of the result on a corpus of general coreference and compare the results with state-of-the-art solutions of this type for other languages.
See BibTeX citation, Springer LNCS link and LP&IIS 2013 presentation.
CICLING 2013 (March 24–30, 2013, Samos) conference paper commenting on the experience gained in preparation of a coreference corpus for an inflectional and free-word-order language carried out in an ongoing project, aiming at creating tools for coreference resolution. Starting with a clarification of the relation between noun groups and mentions, through definition of the annotation scope and strategies, up to actual decisions for borderline cases, we present the process of building the first, to our best knowledge, corpus of general coreference of Polish.
See BibTeX citation and Springer LNCS link.
Ogrodniczuk, Głowińska, Zawisławska, Kopeć, Savary – Polski korpus koreferencyjny: wersja wstępna
Presentation at the Natural Language Processing Seminar (December 3, 2012, Warsaw) discussing methodology of the construction of the Polish Coreference Corpus (in Polish).
Kopeć, Ogrodniczuk – LRT for Polish coreference annotation and resolution
HLT Days 2012 (September 27-28, 2012, Warsaw) poster presented in Language Resources and Tools Hackathon session.
Ogrodniczuk, Zawisławska – Semantic Approach to Identity in Coreference Resolution Task
KI 2012 (September 24-27, 2012, Saarbrücken) coreference paper confronting the idea of continuous nature of identity with experimental data for Polish, resulting in a new approach to this notion. It extends the definition of coreference with speaker/recipient relation, believed to be valid for all languages, and explains the near-identity with lexical and conceptual means. The theory is supported with Polish-English examples presenting difficulties in coreference interpretation.
See BibTeX citation and Springer LNCS link.
Kopeć, Ogrodniczuk – Creating a Coreference Resolution System for Polish
LREC 2012 (May 21-27, 2012, Istanbul) conference paper presenting the results of the first attempt of the coreference resolution for Polish using statistical methods. It presents the conclusions from the process of adapting the Beautiful Anaphora Resolution Toolkit (BART; a system primarily designed for the English language) for Polish and collates its evaluation results with those of the previously implemented rule-based system. Finally, we describe our plans for the future usage of the tool and highlight the upcoming research to be conducted, such as the experiments of a larger scale and the comparison with other machine learning tools.
See BibTeX citation and LREC 2012 poster.
Presentation at the Natural Language Processing Seminar (March 5, 2012, Warsaw) discussing typology of coreference and strategies of its annotation (in Polish).
Ogrodniczuk, Kopeć – End-to-end coreference resolution baseline system for Polish
LTC 2011 (November 25-27, 2011, Poznań) conference paper presenting the results of the first attempt of coreference resolution for Polish, intended to create a useful baseline for future experiments with this topic. The resulting implementation is designed to run either on true mention boundaries (discovering coreference chains between them) or in an end-to-end manner, performing their automatic detection as the first step. The system uses a few rich rules, corresponding to syntactic constraints (elimination of nested nominal groups), syntactic filters (elimination of syntactic incompatible heads), semantic filters (wordnet-derived compatibility) and selection (weighted scoring). Results are evaluated against human annotation for two commonly used baseline variants of the resolver (all-singletons/head-match) and two target rule-based settings. The best working method is analysed, showing simple statistics about the two classes of errors made by the system.
See BibTeX citation and LTC 2011 presentation.
Ogrodniczuk, Kopeć – Rule-based coreference resolution module for Polish
DAARC 2011 (October 6-7, 2011, Faro) conference paper presenting the results of the first attempt of coreference resolution for Polish running on true mention boundaries and using a few rich rules, corresponding to syntactic constraints (elimination of nested nominal groups), syntactic filters (elimination of syntactic incompatible heads), semantic filters (wordnet-derived compatibility) and selection (weighted scoring). The results are compared to human annotation and presented in four sets: with two common baselines: all singletons/head-match, and two slightly more complex settings with four and five rules.
See BibTeX citation and DAARC 2011 poster.
External contributions
Parts of the work described here were also contributed by other externally funded projects, carried out simultaneously with CORE:
- works on the new version of the Polish grammar for Spejd by Alicja Wójcicka and Katarzyna Głowińska were co-funded by the Polish Ministry of Science and Higher Education as an Investment in CLARINPL Research Infrastructure and by the European Union from resources of the European Social Fund
works related to linguistic evaluation of usefulness of Uryupina’s coreference features for Polish by Piotr Batko and development of adaptation of BART (Beautiful Anaphora Resolution Toolkit) for Polish by Bartłomiej Nitoń were co-funded by the European Union from financial resources of the European Social Fund, project PO KL Information technologies: Research and their interdisciplinary applications
works related to coreference-based approach to summarization were carried out within PhD studies of Mateusz Kopeć at the Institute of Computer Science, Polish Academy of Sciences
help with adaptation of coreference tools to Multiservice, a Web service framework for Polish NLP tools, was offered by Michał Lenart taking part in CESAR project (Central and South-east European Resources, part of META-NET) financed from a European Competitiveness and Innovation framework Programme, Information and Communication Technologies Policy Support Programme (CIP ICT-PSP, grant agreement 271022)
projection-based experiments were made possible by the University Research Program for Google Translate
contacts established with the parallel French coreference annotation project ANCOR were also beneficial for some of our scientific results and helped relate the CORE project more deeply to the international coreference community.
Project team
The core CORE project team constituted of (almost alphabetically):
Maciej Ogrodniczuk — principal investigator
- Barbara Dunin-Kęplicz — formalization of coreference rules
- Maria Głąbska — coreference annotation
- Katarzyna Głowińska — linguistic expertise related to anaphora, coreference and Polish syntax
- Anna Grzeszak — coreference annotation
- Mateusz Kopeć — technical leadership, implementation and IT design, development of the annotation environment and project tools
- Emilia Kubicka — coreference annotation
- Barbara Masny — coreference annotation
- Paulina Rosalska — coreference annotation
- Agata Savary — coreference annotation and annotation work expertise
- Magdalena Zawisławska — linguistic and semantic expertise, annotation management, adjudication of the annotation of Polish Coreference Corpus
- Sebastian Żurowski — coreference annotation
but there were numerous other people, mainly colleagues from the Linguistic Engineering Group at the Institute of Computer Science, Polish Academy of Sciences, who contributed to various stages of the project with their selfless help:
- Piotr Batko — coreference annotation, verification of coreference features for Polish (linguistic part)
- Łukasz Degórski — help related to processing NKJP data
- Łukasz Debowski — statistical expertise
- Michał Lenart — help related to processing NKJP data, hardware expertise, Multiservice integration assistance
- Małgorzata Marciniak — HPSG anaphora expertise
- Bartłomiej Nitoń — verification of coreference features for Polish (implementation part)
- Adam Przepiórkowski — linguistic and natural language processing expertise, management of co-operation with the National Corpus of Polish
- Filip Skwarski — translation and proofreading
- Jakub Waszczuk — expertise related to annotation and named entity-related tools, versioning system management
- Joanna Wierucka — translation and proofreading.