Derivational Morphological Relations in Word Embeddings

no code implementations • WS 2019 • Tom{\'a}{\v{s}} Musil, Jon{\'a}{\v{s}} Vidra, David Mare{\v{c}}ek

Derivation is a type of a word-formation process which creates new words from existing ones by adding, changing or deleting affixes.

Clustering Word Embeddings

Extracting Syntactic Trees from Transformer Encoder Self-Attentions

no code implementations • WS 2018 • David Mare{\v{c}}ek, Rudolf Rosa

This is a work in progress about extracting the sentence tree structures from the encoder{'}s self-attention weights, when translating into another language using the Transformer neural network architecture.

Machine Translation Sentence

CUNI x-ling: Parsing Under-Resourced Languages in CoNLL 2018 UD Shared Task

no code implementations • CONLL 2018 • Rudolf Rosa, David Mare{\v{c}}ek

This is a system description paper for the CUNI x-ling submission to the CoNLL 2018 UD Shared Task.

Translation

Input Combination Strategies for Multi-Source Transformer Decoder

no code implementations • WS 2018 • Jind{\v{r}}ich Libovick{\'y}, Jind{\v{r}}ich Helcl, David Mare{\v{c}}ek

In multi-source sequence-to-sequence tasks, the attention mechanism can be modeled in several ways.

Image Captioning Multimodal Machine Translation +2

CUNI Experiments for WMT17 Metrics Task

no code implementations • WS 2017 • David Mare{\v{c}}ek, Ond{\v{r}}ej Bojar, Ond{\v{r}}ej H{\"u}bsch, Rudolf Rosa, Du{\v{s}}an Vari{\v{s}}

Dependency Parsing Machine Translation +1

CUNI submission in WMT17: Chimera goes neural

no code implementations • WS 2017 • Roman Sudarikov, David Mare{\v{c}}ek, Tom Kocmi, Du{\v{s}}an Vari{\v{s}}, Ond{\v{r}}ej Bojar

Machine Translation

Communication with Robots using Multilayer Recurrent Networks

no code implementations • WS 2017 • Bed{\v{r}}ich Pi{\v{s}}l, David Mare{\v{c}}ek

In this paper, we describe an improvement on the task of giving instructions to robots in a simulated block world using unrestricted natural language commands.

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

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

Moses \& Treex Hybrid MT Systems Bestiary

no code implementations • WS 2016 • Rudolf Rosa, Martin Popel, Ond{\v{r}}ej Bojar, David Mare{\v{c}}ek, Ond{\v{r}}ej Du{\v{s}}ek

Language Modelling Machine Translation +1

Merged bilingual trees based on Universal Dependencies in Machine Translation

no code implementations • WS 2016 • David Mare{\v{c}}ek

Language Modelling Machine Translation +1

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

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).

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

Stop-probability estimates computed on a large corpus improve Unsupervised Dependency Parsing

no code implementations • ACL 2013 • David Mare{\v{c}}ek, Milan Straka

Unsupervised Dependency Parsing

Deepfix: Statistical Post-editing of Statistical Machine Translation Using Deep Syntactic Analysis

no code implementations • ACL 2013 • Rudolf Rosa, David Mare{\v{c}}ek, Ale{\v{s}} Tamchyna

Automatic Post-Editing Translation

Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors

no code implementations • WS 2012 • Rudolf Rosa, Ond{\v{r}}ej Du{\v{s}}ek, David Mare{\v{c}}ek, Martin Popel

Machine Translation Morphological Inflection

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

DEPFIX: A System for Automatic Correction of Czech MT Outputs

no code implementations • WS 2012 • Rudolf Rosa, David Mare{\v{c}}ek, Ond{\v{r}}ej Du{\v{s}}ek

Machine Translation Word Alignment

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

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

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