AER: do we need to "improve" our alignments?
نویسندگان
چکیده
Currently most statistical machine translation systems make use of alignments as a first step in the process of training the actual translation models. Several researchers have investigated how to improve the alignment quality, with the (intuitive) assumption that better alignments increase the translation quality. In this paper we will investigate this assumption and show that this is not always the case.
منابع مشابه
Better Word Alignments with Supervised ITG Models
This work investigates supervised word alignment methods that exploit inversion transduction grammar (ITG) constraints. We consider maximum margin and conditional likelihood objectives, including the presentation of a new normal form grammar for canonicalizing derivations. Even for non-ITG sentence pairs, we show that it is possible learn ITG alignment models by simple relaxations of structured...
متن کاملGoing Beyond AER: An Extensive Analysis of Word Alignments and Their Impact on MT
This paper presents an extensive evaluation of five different alignments and investigates their impact on the corresponding MT system output. We introduce new measures for intrinsic evaluations and examine the distribution of phrases and untranslated words during decoding to identify which characteristics of different alignments affect translation. We show that precision-oriented alignments yie...
متن کاملGraph-based alignment of narratives for automated neurological assessment
Narrative recall tasks are widely used in neuropsychological evaluation protocols in order to detect symptoms of disorders such as autism, language impairment, and dementia. In this paper, we propose a graph-based method commonly used in information retrieval to improve word-level alignments in order to align a source narrative to narrative retellings elicited in a clinical setting. From these ...
متن کاملEnhancing Phrase Extraction from Word Alignments Using Morphology
We propose a technique for effective extraction of bilingual phrases from word alignments using morphological processing. Morphological processing leads to an increase of the frequency of words in the corpus, consequently reduces Alignment Error Rate (AER). Intuitively, better word alignments enhance the quality of bilingual phrases extracted. Using alignments of a stemmed corpus for phrase ext...
متن کاملFrequency of fimH, papC, and aer in E. coli Strains Isolated from Patients with Urinary Tract Infection, and their Antibiotic Resistance Pattern
Introduction: E. coli is the predominant causes of urinary tract infection. Several virulence factors for bacterial infections in the urinary tract are required. In this study, we have considered several virulence factors in strains isolated from the patients with UTI in Yazd. Methods: In this cross-sectional study in 1394-1395, 146 strains isolated were collected from the patients with urinar...
متن کامل