Abstract Data-to-Text Generation (DTG) is a subfield of Natural Language aiming at transcribing structured data in natural language descriptions. The field has been recently boosted by the use neural-based generators which exhibit on one side great syntactic skills without need hand-crafted pipelines; other side, quality generated text reflects training data, realistic settings only offer imper...

The evaluation of Handwritten Text Recognition (HTR) systems has traditionally used metrics based on the edit distance between HTR and ground truth (GT) transcripts, at both character word levels. This is very adequate when experimental protocol assumes that GT text lines are same, which allows distances to be independently computed each given line. Driven by recent advances in pattern recognit...

Sentiment analysis is the processing of textual data and giving positive or negative opinions to sentences. In ABSA dataset, most sentences contain one aspect sentiment polarity, have multiple identical polarities, which weakens polarity dataset. Therefore, this paper uses SemEval 14 Restaurant Review in each document symmetrically divided into individual sentences, two versions datasets ATSA A...

The goal of singing voice separation is to recover the vocals signal from music mixtures. State-of-the-art performance achieved by deep neural networks trained in a supervised fashion. Since training data are scarce and signals extremely diverse, it remains challenging achieve high quality across various recording mixing conditions as well styles. In this paper, we investigate which extent can ...

The  present  study  aimed  at  investigating  DIF  sources  on  an  EFL  reading  comprehension test.  Accordingly,  2  DIF  detection  methods,  logistic  regression  (LR)  and  item  response theory  (IRT),  were  used  to  flag  emergent  DIF  of  203  (110  females  &  93  males)  Iranian EFL examinees’ performance on a reading comprehension test. Seven hypothetical DIF sources were examin...

among factors that might manipulate translators’ mind while producing a text is the notion of ideology transmission through text or talk. adopting critical discourse analysis (cda) with particular emphasis on the framework of van dijk (1999), the present investigation is an attempt to shed light on the relationship between language and ideology involved in translation in general, and more speci...

The paper focuses on selecting an optimal set of the Multiword Expressions Extraction methods used as a tool during wordnet expansion. Wordnet multiword lexical units are a broad class and it is difficult to find a single extraction method fulfilling the task. Many extraction association measures were tested on very large corpora and a very large wordnet, namely plWordNet. Several new measures ...

We describe the construction of two corpora in the domain of Swiss legal texts: The DS21 corpus is based on the Collection of Swiss Law Sources and contains historical legal texts from the early Middle Ages up to 1798; the Swiss Legislation Corpus (SLC) is based on the Classified Compilation of Swiss Federal Legislation and contains all current Swiss federal laws. The paper summarizes the key p...