Linguistic Features of Genre and Method Variation in Translation: A Computational Perspective

Authors: Ekaterina Lapshninova-Koltunski, Marcos Zampieri

Submitted to arXiv on 13 Sep. 2017
Abstract

In this paper we describe the use of text classification methods to investigate genre and method variation in an English - German translation corpus. For this purpose we use linguistically motivated features representing texts using a combination of part-of-speech tags arranged in bigrams, trigrams, and 4-grams. The classification method used in this paper is a Bayesian classifier with Laplace smoothing. We use the output of the classifiers to carry out an extensive feature analysis on the main difference between genres and methods of translation.

The papers around it, by date and closeness

Higher is closer to this paper; left is older. Lines join papers close to each other: groups of lines are sub-topics. Select a point to see why it is there. Back to the summary of this paper

How to read this map? Illustrated guide

Closest papers Prior work it builds on Papers that cite it

Papers around this one

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

  1. Very close* Cited by this paper Used in depth by this paper A method it uses
    Investigating Genre and Method Variation in Translation Using Text Classification
    Marcos Zampieri, Ekaterina Lapshinova-Koltunski · 2015 · International Conference on Text, Speech and Dialogue · cited 4 times · Not summarized yet
  2. Close*
    Stylistic Variation as a Basis for Genre-Based Text Classification
    S. Fatima, R. Krishnan · 2001 · IETE Journal of Research · cited 1 time · Not summarized yet
  3. Close
    Text Genre Classification Using only Parts of Speech
    Alan Schulman, Salvador E. Barbosa · 2018 · 2018 International Conference on Computational Science and Computational Intelligence (CSCI) · cited 4 times · Not summarized yet
    Abstract

    This paper discusses a unique approach to English text classification. A topic that the authors have not found to be explicitly explored is the role that parts of speech (POS) have on text classification. This paper aims to answer whether POS patterns exist within a text that can distinguish it from one of a different genre. The experiments were carried out in two phases: using the Natural Language Toolkit, input texts are processed into feature vectors reflecting their POS patterns. These feature vectors are then passed to a separate program that virtually maps them into a coordinate space, ultimately clustering them based on spatial proximity through the non-parametric K-means algorithm. A…

  4. Close
    Modeling Communicative Purpose with Functional Style: Corpus and Features for German Genre and Register Analysis
    T. Haider, Alexis Palmer · 2017 · cited 3 times · Not summarized yet
    Abstract

    While there is wide acknowledgement in NLP of the utility of document characterization by genre, it is quite difficult to determine a definitive set of features or even a comprehensive list of genres. This paper addresses both issues. First, with prototype semantics, we develop a hierarchical taxonomy of discourse functions. We implement the taxonomy by developing a new text genre corpus of contemporary German to perform a text based comparative register analysis. Second, we extract a host of style features, both deep and shallow, aiming beyond linguistically motivated features at situational correlates in texts. The feature sets are used for supervised text genre classification, on which ou…

  5. Close
    Exploring the Use of Linguistic Features in Domain and Genre Classification
    M. Wolters, Mathias Kirsten · 1999 · Conference of the European Chapter of the Association for Computational Linguistics · cited 46 times · Not summarized yet
    Abstract

    The central questions are: How useful is information about part-of-speech frequency for text categorisation? Is it feasible to limit word features to content words for text classifications? This is examined for 5 domain and 4 genre classification tasks using LIMAS, the German equivalent of the Brown corpus. Because LIMAS is too heterogeneous, neither question can be answered reliably for any of the tasks. However, the results suggest that both questions have to be examined separately for each task at hand, because in some cases, the additional information can indeed improve performance.

  6. Close*
    Text Genre - An Unexplored Parameter in Statistical Machine Translation
    M. Gavrila, C. Vertan · 2011 · Language and Technology Conference · Not summarized yet
  7. Close Cited by this paper A method it uses
    Measuring ‘Registerness’ in Human and Machine Translation: A Text Classification Approach
    Ekaterina Lapshinova-Koltunski, M. Vela · 2015 · DiscoMT@EMNLP · cited 13 times · Not summarized yet
    Abstract

    In this paper, we apply text classification techniques to prove how well translated texts obey linguistic conventions of the target language measured in terms of registers, which are characterised by particular distributions of lexico-grammatical features according to a given contextual configuration. The classifiers are trained on German original data and tested on comparable English-to-German translations. Our main goal is to see if both human and machine translations comply with the nontranslated target originals. The results of the present analysis provide evidence for our assumption that the usage of parallel corpora in machine translation should be treated with caution, as human transl…

  8. Close* Cited by this paper
    Cross-linguistic variation in system and text : a methodology for the investigation of translations and comparable texts
    E. Teich · 2003 · cited 255 times · Not summarized yet

Prior work it builds on

  1. Related* Used in depth by this paper A method it uses
    'Corpus Linguistics and Translation Studies: Implications and Applications'
    Mona Baker, G. Francis, E. Tognini-Bonelli · 1993 · cited 1,152 times · Not summarized yet
  2. Related* A method it uses
    A New Approach to the Study of Translationese: Machine-learning the Difference between Original and Translated Text
    M. Baroni, Silvia Bernardini · 2005 · Literary and Linguistic Computing · cited 249 times · Not summarized yet
  3. Related Used in depth by this paper A method it uses
    Discriminating Similar Languages: Evaluations and Explorations
    Cyril Goutte, Serge Léger, S. Malmasi et al. · 2016 · International Conference on Language Resources and Evaluation · cited 73 times · Not summarized yet
    Abstract

    We present an analysis of the performance of machine learning classifiers on discriminating between similar languages and language varieties. We carried out a number of experiments using the results of the two editions of the Discriminating between Similar Languages (DSL) shared task. We investigate the progress made between the two tasks, estimate an upper bound on possible performance using ensemble and oracle combination, and provide learning curves to help us understand which languages are more challenging. A number of difficult sentences are identified and investigated further with human annotation

  4. Related Used in depth by this paper A method it uses
    Contrastive Register Variation: A Quantitative Approach to the Comparison of English and German
    Stella Neumann · 2013 · Modern Language Review · cited 74 times · Not summarized yet
    Abstract

    The book provides the first comparison of usage preferences across registers in the language pair English-German. Due to the innovative quantitative approach and broad coverage, the volume is an excellent resource for scholars working in contrastive linguistics and translation studies as well as for corpus linguists.

  5. Related*
    Cross-Linguistic Corpora for the Study of Translations: Insights from the Language Pair English-German
    E. Steiner, S. Hansen-Schirra, Stella Neumann · 2012 · cited 95 times · Not summarized yet

Papers that cite it

  1. Related
    Light verb variations and varieties of Mandarin Chinese: Comparable corpus driven approaches to grammatical variations
    Hong-Zhi Xu, M. Jiang, Jing-Xia Lin et al. · 2020 · Corpus Linguistics and Linguistic Theory · cited 17 times · Not summarized yet
    Abstract

    Abstract This article presents a classification and clustering based study to account for the differences among five Chinese light verbs (congshi, gao, jiayi, jinxing, and zuo) as well as their variations in Mainland China Mandarin (ML) and Taiwan Mandarin (TW). Based on 13 linguistic features, both competition and co-development of these light verbs are studied in terms of their distinct and shared collocates. The proposed method discovers significant new grammatical differences in addition to confirming previously reported ones. Most significant discoveries include selectional restrictions differentiating deverbal nominals and event nouns, and degrees of transitivity of VO compounds. We al…

  2. Related
    Contextualising the Notion of Context in Jurilinguistic Studies
    Edyta Więcławska · 2020 · International Journal for the Semiotics of Law · cited 3 times · Not summarized yet
    Abstract

    Context is a notion that is commonly invoked in many linguistic studies, either with very general reference or, more specifically, in the light of one of a number of research approaches which assign distinct definitions to context, ranging from factors that can be recovered from a text, through social parameters serving as an index for the appropriation of discursive performance, to factors that bring texts into being and give them meaning. This exploratory and descriptive research problematises the notion of context specifically on the grounds of English/Polish translation of corporate documentation processed in company registration proceedings, touching upon factors that are presumed to be…

  3. Related
    EXPLORING WORD CLASS RELATIONS IN CHINESE-ENGLISH POLITICAL TRANSLATION: A CORPUS-BASED STUDY OF XI JINPING: THE GOVERNANCE OF CHINA II
    Qi-Jun Song, Yucheng Zhong, En-Ci Huang · 2024 · International Journal of Humanities Technology and Civilization · cited 6 times · Not summarized yet
    Abstract

    Translation universal has been an important domain of research in corpus-based translation studies. While previous studies have examined word class relations in prose translation and the diachronic change of explicitation in translation, there is a relative lack of research on word class relations in political translation. To address this gap, the study delves into word class relations in political translation using self-built comparable corpora of, specifically, the Chinese source texts (ST) and English target texts (TT) of Xi Jinping: The Governance of China II, as well as the original English texts (OET) of State of the Union Address 2013-2016. The results demonstrate that significant dif…

  4. Related
    Bridging Boundaries between Systemic Functional Linguistics and Translation Studies: An Interview with Erich Steiner (Part I)
    E. Steiner, Bo Wang, C. Matthiessen et al. · 2019 · Linguistics and the Human Sciences · Not summarized yet
    Abstract

    Erich Steiner, as a leading scholar in systemic functional linguistics (SFL), has been involved in various important strands of research on SFL and translation. This transcript is based on the second part of the interview during his visit to Hong Kong. We continue to discuss the application of SFL to translation, covering topics like SFL and other functionalist theories of translation, the tools for translation contributed by functionally-oriented work, and translation as a method for language teaching. In addition, Steiner summarizes the contributions of SFL to translation, and introduces some possibilities for future research.

  5. Related*
    A Study of Publicity Translation Strategies from Multiple Perspectives
    Yang Du · 2020 · Not summarized yet
How are these papers found?

We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.

Updated on 6 November 2026.

The illustrated guide to the papers around a paper