Browse

You are looking at 1 - 10 of 2,604 items for :

  • Linguistics and Semiotics x
Clear All
Open access

Berta González Saavedra and Marco Passarotti

Abstract

In the context of the Index Thomisticus Treebank project, we have enhanced the full text of Bellum Catilinae by Sallust with semantic annotation. The annotation style resembles the one used for the so called “tectogrammatical” layer of the Prague Dependency Treebank. By exploiting the results of semantic role labeling, ellipsis resolution and coreference analysis, this paper presents a network-based study of the main Actors and Actions (and their relations) in Bellum Catilinae.

Open access

Tim vor der Brück

Abstract

Rule-based natural language generation denotes the process of converting a semantic input structure into a surface representation by means of a grammar. In the following, we assume that this grammar is handcrafted and not automatically created for instance by a deep neural network. Such a grammar might comprise of a large set of rules. A single error in these rules can already have a large impact on the quality of the generated sentences, potentially causing even a complete failure of the entire generation process. Searching for errors in these rules can be quite tedious and time-consuming due to potentially complex and recursive dependencies. This work proposes a statistical approach to recognizing errors and providing suggestions for correcting certain kinds of errors by cross-checking the grammar with the semantic input structure. The basic assumption is the correctness of the latter, which is usually a valid hypothesis due to the fact that these input structures are often automatically created.

Our evaluation reveals that in many cases an automatic error detection and correction is indeed possible.

Open access

Lauriane Aufrant and Guillaume Wisniewski

Abstract

We present PanParser, a Python framework dedicated to transition-based structured prediction, and notably suitable for dependency parsing. On top of providing an easy way to train state-of-the-art parsers, as empirically validated on UD 2.0, PanParser is especially useful for research purposes: its modular architecture enables to implement most state-of-the-art transition-based methods under the same unified framework (out of which several are already built-in), which facilitates fair benchmarking and allows for an exhaustive exploration of slight variants of those methods. PanParser additionally includes a number of fine-grained evaluation utilities, which have already been successfully leveraged in several past studies, to perform extensive error analysis of monolingual as well as cross-lingual parsing.

Open access

Thomas Zenkel, Matthias Sperber, Jan Niehues, Markus Müller, Ngoc-Quan Pham, Sebastian Stüker and Alex Waibel

Abstract

In this paper we introduce an open source toolkit for speech translation. While there already exists a wide variety of open source tools for the essential tasks of a speech translation system, our goal is to provide an easy to use recipe for the complete pipeline of translating speech. We provide a Docker container with a ready to use pipeline of the following components: a neural speech recognition system, a sentence segmentation system and an attention-based translation system. We provide recipes for training and evaluating models for the task of translating English lectures and TED talks to German. Additionally, we provide pre-trained models for this task. With this toolkit we hope to facilitate the development of speech translation systems and to encourage researchers to improve the overall performance of speech translation systems.

Open access

Álvaro Peris and Francisco Casacuberta

Abstract

We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via continuous learning. NMT-Keras is based on an extended version of the popular Keras library, and it runs on Theano and TensorFlow. State-of-the-art neural machine translation models are deployed and used following the high-level framework provided by Keras. Given its high modularity and flexibility, it also has been extended to tackle different problems, such as image and video captioning, sentence classification and visual question answering.

Open access

Václava Kettnerová, Markéta Lopatková, Eduard Bejček and Petra Barančíková

Abstract

This paper summarizes results of a theoretical analysis of syntactic behavior of Czech light verb constructions and their verification in the linguistic annotation of a large amount of these constructions. The concept of LVCs is based on the observation that nouns denoting actions, states, or properties have a strong tendency to select semantically underspecified verbs, which leads to a specific rearrangement of valency complementations of both nouns and verbs in the syntactic structure. On the basis of the description of deep and surface syntactic properties of LVCs, a formal model of their lexicographic representation is proposed here. In addition, the resulting data annotation, capturing almost 1,500 LVCs, is described in detail. This annotation has been integrated in a new version of the VALLEX lexicon, release 3.5.

Open access

Jetic Gū, Anahita Mansouri Bigvand and Anoop Sarkar

Abstract

In this paper, we present a new word aligner with built-in support for alignment types, as well as comparisons between various models and existing aligner systems. It is an open source software that can be easily extended to use models of users’ own design. We expect it to suffice the academics as well as scientists working in the industry to do word alignment, as well as experimenting on their own new models. Here in the present paper, the basic designs and structures will be introduced. Examples and demos of the system are also provided.

Open access

Bekim Baliqi

Abstract

This research aims to explore the relationship between the universities and political elite formation based on the case study of Kosovo. The key questions raised throughout the research are; how do the universities influence the formation of the political elites and how were the elites changed throughout time? Analysing these relationships in different periods, each with a different impact on the elite building processes, namely from the establishment of the University of Prishtina until recently. Central assumption here is that higher education institutions were the catalyst in the transformation of the political elites. Being a vital source of power, a control over it represents also a struggle for power between the rival forces with different political outcomes. Theoretical framework consists of John Higley approach on the elite formation, based in the context of post-conflict and divided society, such as Kosovo case.

Open access

Fatemeh Ahmadi Azar and Farid Parvaneh

Abstract

This paper aims to focus on the subject of N. Katherine Hayles’s nonlinearity in Audrey Niffenegger’s The Time Traveler’s Wife as a postmodern work. Niffenegger published her debut novel, The Time Traveler’s Wife in 2003. This novel is a romance and science fiction which narrates the love story of Henry DeTamble – a man with genetic disorder that forces him to time travel unwillingly – and his artist wife, Clare Anne Abshire – who has to deal with his absence and dangerous experiences. Since Henry is a time traveler and experiences life in a non-linear manner, the main question of this research is that to what extent the characteristic of nonlinearity shapes the personality and un-consciences of Henry and Clare in a society which has been defined with Newtonian/Cartesian or linear thinking. To answer this question, N. Katherine Hayles’s Chaos theory can be applicable. Hayles considers nonlinearity as one of the most important and fundamental characteristics of chaotic systems. One of the findings of this research is the inapplicability of Newtonian thinking in post-modern literature.

Open access

Hajdin Berisha, Saxhide Mustafa and Yusof Ismail

Abstract

Organizational members perceive top management as the sole authority for strategy making. Whilst this has been true for a number of years, the last decade has provided a shift to this traditional strategy practice in some sectors in the society. This paper attempts to address two major questions: firstly, whether the classical view of strategy as a property of organizations and the sole responsibility of top management in strategy making holds true in one of the higher education institutions in Kosovo as a member of western Balkan and eastern European countries. Secondly, how top management influences strategy practices of sense-making and sense-giving through organizational culture. The research analyses organizational culture and its effect on strategy as practice before and after a shift of institution’s top management based on its six strategy dimensions. The study employs multiple sources of data to address the research questions: secondary sources, semi-structured interviews, informal discussions with institution’s staff members, two-week of shadowing, observations and viewing artefacts of the institution. Results reveal three threads: organizational culture plays an important role on strategy as practice; top management is perceived to primarily provide sense through face-to-face interaction and procedural measures of strategy practices; and staff members are mostly involved in implementation. Moreover, clan and hierarchical types of organizational culture are identified to shape strategy practices of the institution. The study suggests that while the strategy making practice should be at the core of institution, a pleasant and non-confronting organizational culture is crucial to attract new students and retain elite staff.