System-oriented and text-oriented comparative linguistic research: Cross-linguistic variation in translation

E Teich - Languages in Contrast, 1999 - jbe-platform.com
The main concern of this paper is to develop a model of cross-linguistic variation that is
applicable to various kinds of comparative linguistic research. The motivation for this lies in …

Developing a GeM (genre and multimodality) model

JA Bateman - Interactions, images and texts: A reader in …, 2014 - degruyter.com
My involvement with multimodality as a resource for communicative expression began with a
general development that took place at the beginning of the 1990s. At that time, several …

Using natural language generation to bootstrap missing Wikipedia articles: A human-centric perspective

LA Kaffee, P Vougiouklis, E Simperl - Semantic Web, 2022 - content.iospress.com
Nowadays natural language generation (NLG) is used in everything from news reporting
and chatbots to social media management. Recent advances in machine learning have …

Natural language generation and semantic technologies

K Staykova - Cybernetics and Information Technologies, 2014 - sciendo.com
The paper presents a survey of the domain of Natural Language Generation (NLG) with its
models, techniques, applications, and investigates how the semantic technologies are …

GUM: The generalized upper model

JA Bateman - Applied Ontology, 2022 - content.iospress.com
GUM is a linguistically-motivated ontology originally developed to support natural language
processing systems by offering a level of representation intermediate between linguistic …

[图书][B] Controlled Document Authoring in a Machine Translation Age

R Miyata - 2021 - library.oapen.org
Controlled Document Authoring in a Machine Translation Age Page 1 Controlled Document
Authoring in a Machine Translation Age Rei Miyata First published in 2021 ISBN: 978-0-367-50019-1 …

Multilingual resource sharing across both related and unrelated languages: An implemented, open-source framework for practical natural language generation

JA Bateman, I Kruijff-Korbayová, GJ Kruijff - Research on Language and …, 2005 - Springer
This article reports on our experience with developing multilingual grammar resources for
natural language generation (NLG). We employ a strong notion of multilinguality:(i) …

Generating multilingual personalized descriptions of museum exhibits-The M-PIRO project

I Androutsopoulos, V Kokkinaki… - arXiv preprint cs …, 2001 - arxiv.org
This paper provides an overall presentation of the M-PIRO project. M-PIRO is developing
technology that will allow museums to generate automatically textual or spoken descriptions …

A common solution for tokenization and part-of-speech tagging: One-pass Viterbi algorithm vs. iterative approaches

J Grana, MA Alonso, M Vilares - International Conference on Text, Speech …, 2002 - Springer
Current taggers assume that input texts are already tokenized, ie correctly segmented in
tokens or high level information units that identify each individual component of the texts …

[PDF][PDF] Scientific registers and disciplinary diversification: a comparable corpus approach

E Teich, S Degaetano-Ortlieb, H Kermes… - Proceedings of the …, 2013 - aclanthology.org
We present a study on linguistic contrast and commonality in English scientific discourse on
the basis of a monolingually comparable corpus. The focus is on selected scientific …