539 research outputs found
Sort by
Effects of Noun Phrase Bracketing in Dependency Parsing and Machine Translation
No full textFlat noun phrase structure was, up until recently,
the standard in annotation for the Penn
Treebanks. With the recent addition of internal
noun phrase annotation, dependency parsing
and applications down the NLP pipeline
are likely affected. Some machine translation
systems, such as TectoMT, use deep syntax
as a language transfer layer. It is proposed
that changes to the noun phrase dependency
parse will have a cascading effect down the
NLP pipeline and in the end, improve machine
translation output, even with a reduction
in parser accuracy that the noun phrase
structure might cause. This paper examines
this noun phrase structure’s effect on dependency
parsing, in English, with a maximum
spanning tree parser and shows a 2.43%, 0.23
Bleu score, improvement for English to Czech
machine translation
Named Entities from Wikipedia for Machine Translation
No full textIn this paper we present our attempt to improve machine translation of named entities by using Wikipedia. We recognize named entities based on categories of English Wikipedia articles, extract their potential translations from corresponding Czech articles and incorporate them into a statistical machine translation system as translation options. Our results show a decrease of translation quality in terms of automatic metrics but positive results from human annotators. We conclude that this approach can lead to many errors in translation and therefore should always be combined with the standard statistical translation model and weighted appropriately
eppex: Epochal Phrase Table Extraction for Statistical Machine Translation
No full textWe present a tool that extracts phrase pairs from a word-aligned parallel corpus and filters
them on the fly based on a user-defined frequency threshold. The bulk of phrase pairs to be
scored is much reduced, making the whole phrase table construction process faster with no
significant harm to the ultimate phrase table quality as measured by BLEU. Technically, our
tool is an alternative to the extract component of the phrase-extract toolkit bundled with Moses
SMT software and covers some of the functionality of sigfilter
Two-step translation with grammatical post-processing
No full textThis paper describes an experiment in which
we try to automatically correct mistakes in
grammatical agreement in English to Czech
MT outputs. We perform several rule-based
corrections on sentences parsed to dependency
trees. We prove that it is possible to improve
the MT quality of majority of the systems participating
in WMT shared task. We made both
automatic (BLEU) and manual evaluations
TamilTB: An Effort Towards Building a Dependency Treebank for Tamil
Get PDFAnnotated corpora such as treebanks are important for the development
of parsers, language applications as well as understanding of the language itself.
Only very few languages possess these scarce resources. In this paper, we describe
our effort in syntactically annotating a small corpora (600 sentences) of Tamil
language. Our annotation is similar to Prague Dependency Treebank (PDT 2.0)
and consists of 2 levels or layers: (i) morphological layer (m-layer) and (ii) analytical
layer (a-layer). For both the layers, we introduce annotation schemes i.e. positional
tagging for m-layer and dependency relations (and how dependency structures
should be drawn) for a-layers. Finally, we evaluate our corpora in the tagging and
parsing task using well known taggers and parsers and discuss some general issues
in annotation for Tamil language
TrEd 2.0 - newly refactored tree editor
No full textTrEd 2.0 is a newly refactored version of the TrEd tree editor. TrEd is used in a number of research projects, at the Institute of Formal and Applied Linguistics as well as in several foreign research institutions. Recent changes in its design will substantially facilitate its future development, testing and distribution
CzEng 1.0
No full textA new release of the parallel corpus CzEng, this time with a focus on the removal of bad sentence pairs
Syntax and Rich Morphology in MT
Get PDFThe talk describes in detail the issues specific to English-to-Czech MT: sentence syntax and target-side rich morphology
Representing Layered and Structured Data in the CoNLL-ST Format
No full textIn this paper, we investigate the CoNLL Shared Task format, its properties and possibility of its use for complex annotations. We argue that, perhaps despite the original intent, it is one of the most important current formats for syntactically annotated data.
We show the limits of the CoNLL-ST data format in its current form and propose several simple enhancements that push those limits further and make the format more robust and future proof. We analyse several different linguistic
annotations as examples of varying complexity and show how they can be efficiently stored in the CoNLL-ST format
TectoMT: Modular NLP Framework
No full textIn the present paper we describe TectoMT, a multi-purpose open-source NLP framework. It allows for fast and efficient development of NLP applications
by exploiting a wide range of software modules already integrated in TectoMT, such as tools for
sentence segmentation, tokenization, morphological analysis, POS tagging, shallow and deep syntax parsing, named entity recognition, anaphora resolution, tree-to-tree translation, natural language generation, word-level alignment of parallel corpora, and other tasks. One of the most complex applications of TectoMT is the English-Czech machine translation system with transfer on deep syntactic (tectogrammatical) layer. Several modules are available also for other languages (German, Russian, Arabic). Where possible, modules are implemented in a language-independent way, so they can be reused in many applications