Building a Morphological Network for Persian on Top of a Morpheme-Segmented Lexicon

no code implementations • WS 2019 • Hamid Haghdoost, Ebrahim Ansari, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Mahshid Nikravesh

Universal Derivations Kickoff: A Collection of Harmonized Derivational Resources for Eleven Languages

no code implementations • WS 2019 • Luk{\'a}{\v{s}} Kyj{\'a}nek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Magda {\v{S}}ev{\v{c}}{\'\i}kov{\'a}, Jon{\'a}{\v{s}} Vidra

Attempting to separate inflection and derivation using vector space representations

no code implementations • WS 2019 • Rudolf Rosa, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Supervised Morphological Segmentation Using Rich Annotated Lexicon

no code implementations • RANLP 2019 • Ebrahim Ansari, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Mohammad Mahmoudi, Hamid Haghdoost, Jon{\'a}{\v{s}} Vidra

In the experimental phase, using the hand-annotated Persian lexicon and two smaller similar lexicons for Czech and Finnish languages, we evaluated the effect of the training data size, different hyper-parameters settings as well as different RNN-based models.

Segmentation

DeriNet 2.0: Towards an All-in-One Word-Formation Resource

no code implementations • WS 2019 • Jon{\'a}{\v{s}} Vidra, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Magda {\v{S}}ev{\v{c}}{\'\i}kov{\'a}, Luk{\'a}{\v{s}} Kyj{\'a}nek

Using Adversarial Examples in Natural Language Processing

no code implementations • LREC 2018 • Petr B{\v{e}}lohl{\'a}vek, Ond{\v{r}}ej Pl{\'a}tek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Milan Straka

Image Classification

SumeCzech: Large Czech News-Based Summarization Dataset

no code implementations • LREC 2018 • Milan Straka, Nikita Mediankin, Tom Kocmi, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Vojt{\v{e}}ch Hude{\v{c}}ek, Jan Haji{\v{c}}

Document Summarization Machine Translation +1

Semi-Automatic Construction of Word-Formation Networks (for Polish and Spanish)

no code implementations • LREC 2018 • Mateusz Lango, Magda {\v{S}}ev{\v{c}}{\'\i}kov{\'a}, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Learning-To-Rank Sequential Pattern Mining

Udapi: Universal API for Universal Dependencies

no code implementations • WS 2017 • Martin Popel, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Martin Vojtek

Dependency Parsing

Slavic Forest, Norwegian Wood

no code implementations • WS 2017 • Rudolf Rosa, Daniel Zeman, David Mare{\v{c}}ek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

We once had a corp, or should we say, it once had us They showed us its tags, isn{'}t it great, unified tags They asked us to parse and they told us to use everything So we looked around and we noticed there was near nothing We took other langs, bitext aligned: words one-to-one We played for two weeks, and then they said, here is the test The parser kept training till morning, just until deadline So we had to wait and hope what we get would be just fine And, when we awoke, the results were done, we saw we{'}d won So, we wrote this paper, isn{'}t it good, Norwegian wood.

Dependency Parsing Machine Translation +1

Projection-based Coreference Resolution Using Deep Syntax

no code implementations • WS 2017 • Michal Nov{\'a}k, Anna Nedoluzhko, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

The paper describes the system for coreference resolution in German and Russian, trained exclusively on coreference relations project ed through a parallel corpus from English.

coreference-resolution

Error Analysis of Cross-lingual Tagging and Parsing

1 code implementation • WS 2017 • Rudolf Rosa, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Machine Translation

Planting Trees in the Desert: Delexicalized Tagging and Parsing Combined

no code implementations • PACLIC 2016 • Daniel Zeman, David Mare{\v{c}}ek, Zhiwei Yu, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Dependency Parsing Machine Translation +2

If You Even Don't Have a Bit of Bible: Learning Delexicalized POS Taggers

no code implementations • LREC 2016 • Zhiwei Yu, David Mare{\v{c}}ek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Daniel Zeman

Part-of-speech (POS) induction is one of the most popular tasks in research on unsupervised NLP.

POS TAG

Merging Data Resources for Inflectional and Derivational Morphology in Czech

no code implementations • LREC 2016 • Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Magda {\v{S}}ev{\v{c}}{\'\i}kov{\'a}, Milan Straka, Jon{\'a}{\v{s}} Vidra, Ad{\'e}la Limbursk{\'a}

The paper deals with merging two complementary resources of morphological data previously existing for Czech, namely the inflectional dictionary MorfFlex CZ and the recently developed lexical network DeriNet.

Lemmatization Morphological Analysis

KLcpos3 - a Language Similarity Measure for Delexicalized Parser Transfer

no code implementations • IJCNLP 2015 • Rudolf Rosa, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Information Retrieval

MSTParser Model Interpolation for Multi-Source Delexicalized Transfer

no code implementations • WS 2015 • Rudolf Rosa, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Information Retrieval

Cross-lingual Coreference Resolution of Pronouns

no code implementations • COLING 2014 • Michal Nov{\'a}k, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

coreference-resolution Machine Translation +1

Word-Formation Network for Czech

no code implementations • LREC 2014 • Magda {\v{S}}ev{\v{c}}{\'\i}kov{\'a}, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

In the present paper, we describe the development of the lexical network DeriNet, which captures core word-formation relations on the set of around 266 thousand Czech lexemes.

Lemmatization Machine Translation +1

HamleDT 2.0: Thirty Dependency Treebanks Stanfordized

no code implementations • LREC 2014 • Rudolf Rosa, Jan Ma{\v{s}}ek, David Mare{\v{c}}ek, Martin Popel, Daniel Zeman, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

We present HamleDT 2. 0 (HArmonized Multi-LanguagE Dependency Treebank).

Two Case Studies on Translating Pronouns in a Deep Syntax Framework

no code implementations • IJCNLP 2013 • Michal Nov{\'a}k, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Anna Nedoluzhko

Coreference Resolution Machine Translation +1

Coordination Structures in Dependency Treebanks

no code implementations • ACL 2013 • Martin Popel, David Mare{\v{c}}ek, Jan {\v{S}}t{\v{e}}p{\'a}nek, Daniel Zeman, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Dependency Parsing Machine Translation

Improvements to Syntax-based Machine Translation using Ensemble Dependency Parsers

no code implementations • WS 2013 • Nathan Green, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Dependency Parsing Machine Translation +1

Translation of ``It'' in a Deep Syntax Framework

no code implementations • WS 2013 • Michal Nov{\'a}k, Anna Nedoluzhko, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Machine Translation Translation

Prague Dependency Treebank 2.5 -- a Revisited Version of PDT 2.0

no code implementations • COLING 2012 • Eduard Bej{\v{c}}ek, Jarmila Panevov{\'a}, Jan Popelka, Pavel Stra{\v{n}}{\'a}k, Magda {\v{S}}ev{\v{c}}{\'\i}kov{\'a}, Jan {\v{S}}t{\v{e}}p{\'a}nek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Morphological Processing for English-Tamil Statistical Machine Translation

no code implementations • WS 2012 • Loganathan Ramasamy, Ond{\v{r}}ej Bojar, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Machine Translation Translation

Exploiting Reducibility in Unsupervised Dependency Parsing

no code implementations • EMNLP 2012 • David Mare{\v{c}}ek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Bayesian Inference Unsupervised Dependency Parsing

Using an SVM Ensemble System for Improved Tamil Dependency Parsing

no code implementations • WS 2012 • Nathan Green, Loganathan Ramasamy, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Dependency Parsing

The Study of Effect of Length in Morphological Segmentation of Agglutinative Languages

no code implementations • WS 2012 • Loganathan Ramasamy, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Sowmya Vajjala

Dependency Parsing Information Retrieval +2

Unsupervised Dependency Parsing using Reducibility and Fertility features

no code implementations • WS 2012 • David Mare{\v{c}}ek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Unsupervised Dependency Parsing

Formemes in English-Czech Deep Syntactic MT

no code implementations • WS 2012 • Ond{\v{r}}ej Du{\v{s}}ek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Martin Popel, Martin Majli{\v{s}}, Michal Nov{\'a}k, David Mare{\v{c}}ek

Machine Translation

Language Richness of the Web

no code implementations • LREC 2012 • Martin Majli{\v{s}}, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

The W2C Web Corpus contains more than 100{\textasciitilde}MB of text available for 75 languages.

The Joy of Parallelism with CzEng 1.0

no code implementations • LREC 2012 • Ond{\v{r}}ej Bojar, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Ond{\v{r}}ej Du{\v{s}}ek, Petra Galu{\v{s}}{\v{c}}{\'a}kov{\'a}, Martin Majli{\v{s}}, David Mare{\v{c}}ek, Ji{\v{r}}{\'\i} Mar{\v{s}}{\'\i}k, Michal Nov{\'a}k, Martin Popel, Ale{\v{s}} Tamchyna

CzEng 1. 0 is automatically aligned at the level of sentences as well as words.

Machine Translation Sentence

Announcing Prague Czech-English Dependency Treebank 2.0

no code implementations • LREC 2012 • Jan Haji{\v{c}}, Eva Haji{\v{c}}ov{\'a}, Jarmila Panevov{\'a}, Petr Sgall, Ond{\v{r}}ej Bojar, Silvie Cinkov{\'a}, Eva Fu{\v{c}}{\'\i}kov{\'a}, Marie Mikulov{\'a}, Petr Pajas, Jan Popelka, Ji{\v{r}}{\'\i} Semeck{\'y}, Jana {\v{S}}indlerov{\'a}, Jan {\v{S}}t{\v{e}}p{\'a}nek, Josef Toman, Zde{\v{n}}ka Ure{\v{s}}ov{\'a}, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

We introduce a substantial update of the Prague Czech-English Dependency Treebank, a parallel corpus manually annotated at the deep syntactic layer of linguistic representation.

Coreference Resolution Sentence

HamleDT: To Parse or Not to Parse?

no code implementations • LREC 2012 • Daniel Zeman, David Mare{\v{c}}ek, Martin Popel, Loganathan Ramasamy, Jan {\v{S}}t{\v{e}}p{\'a}nek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Jan Haji{\v{c}}

We propose HamleDT ― HArmonized Multi-LanguagE Dependency Treebank.

Dependency Parsing

Prague Dependency Style Treebank for Tamil

no code implementations • LREC 2012 • Loganathan Ramasamy, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Annotated corpora such as treebanks are important for the development of parsers, language applications as well as understanding of the language itself.

Dependency Parsing

Hybrid Combination of Constituency and Dependency Trees into an Ensemble Dependency Parser

no code implementations • WS 2012 • Nathan Green, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}

Dependency Parsing