Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing
A FALTA DE PAN، Buenas Son Tortas: فعالية UPOS المتوقعة علامات التحليل UD Resource
72
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقوم بتقييم فعالية علامات UPOS المتوقعة كيزات مدخلات لمحللات التبعية في إعدادات الموارد المنخفضة لتقييم كيفية تأثير حجم TreeBank على دقة وضع العلامات على أداء التحليل.نقوم بذلك للحصول على Treebanks Universal TreeBanks Universal Resource Universal Desultency، وبيانات الموارد منخفضة مصطنع بأحجام متفاوتة من TreeBank، وللغة Treebanks الصغيرة جدا بكميات متفاوتة من البيانات المعززة.نجد أن علامات UPOS المتوقعة مفيدة إلى حد ما بالنسبة إلى جانب Lowerbanks Lower Treebanks، خاصة عند توفر المزيد من الأشجار المشروح بالكامل.نجد أيضا أن هذا التأثير الإيجابي يقلل من زيادات البيانات.
We evaluate the efficacy of predicted UPOS tags as input features for dependency parsers in lower resource settings to evaluate how treebank size affects the impact tagging accuracy has on parsing performance. We do this for real low resource universal dependency treebanks, artificially low resource data with varying treebank sizes, and for very small treebanks with varying amounts of augmented data. We find that predicted UPOS tags are somewhat helpful for low resource treebanks, especially when fewer fully-annotated trees are available. We also find that this positive impact diminishes as the amount of data increases.
References used
https://aclanthology.org/
rate research
Read More
This paper presents our multilingual dependency parsing system as used in the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies. Our system consists of an unfactorized biaffine classifier that operates directly on fine-tuned XLM-R
embeddings and generates enhanced UD graphs by predicting the best dependency label (or absence of a dependency) for each pair of tokens. To avoid sparsity issues resulting from lexicalized dependency labels, we replace lexical items in relations with placeholders at training and prediction time, later retrieving them from the parse via a hybrid rule-based/machine-learning system. In addition, we utilize model ensembling at prediction time. Our system achieves high parsing accuracy on the blind test data, ranking 3rd out of 9 with an average ELAS F1 score of 86.97.
We describe the EdinSaar submission to the shared task of Multilingual Low-Resource Translation for North Germanic Languages at the Sixth Conference on Machine Translation (WMT2021). We submit multilingual translation models for translations to/from
Icelandic (is), Norwegian-Bokmal (nb), and Swedish (sv). We employ various experimental approaches, including multilingual pre-training, back-translation, fine-tuning, and ensembling. In most translation directions, our models outperform other submitted systems.
Incorporating multiple input modalities in a machine translation (MT) system is gaining popularity among MT researchers. Unlike the publicly available dataset for Multimodal Machine Translation (MMT) tasks, where the captions are short image descript
ions, the news captions provide a more detailed description of the contents of the images. As a result, numerous named entities relating to specific persons, locations, etc., are found. In this paper, we acquire two monolingual news datasets reported in English and Hindi paired with the images to generate a synthetic English-Hindi parallel corpus. The parallel corpus is used to train the English-Hindi Neural Machine Translation (NMT) and an English-Hindi MMT system by incorporating the image feature paired with the corresponding parallel corpus. We also conduct a systematic analysis to evaluate the English-Hindi MT systems with 1) more synthetic data and 2) by adding back-translated data. Our finding shows improvement in terms of BLEU scores for both the NMT (+8.05) and MMT (+11.03) systems.
This paper describes a freely available web-based demonstrator called HB Deid. HB Deid identifies so-called protected health information, PHI, in a text written in Swedish and removes, masks, or replaces them with surrogates or pseudonyms. PHIs are n
amed entities such as personal names, locations, ages, phone numbers, dates. HB Deid uses a CRF model trained on non-sensitive annotated text in Swedish, as well as a rule-based post-processing step for finding PHI. The final step in obscuring the PHI is then to either mask it, show only the class name or use a rule-based pseudonymisation system to replace it.
Multimodal Machine Translation (MMT) enriches the source text with visual information for translation. It has gained popularity in recent years, and several pipelines have been proposed in the same direction. Yet, the task lacks quality datasets to i
llustrate the contribution of visual modality in the translation systems. In this paper, we propose our system under the team name Volta for the Multimodal Translation Task of WAT 2021 from English to Hindi. We also participate in the textual-only subtask of the same language pair for which we use mBART, a pretrained multilingual sequence-to-sequence model. For multimodal translation, we propose to enhance the textual input by bringing the visual information to a textual domain by extracting object tags from the image. We also explore the robustness of our system by systematically degrading the source text. Finally, we achieve a BLEU score of 44.6 and 51.6 on the test set and challenge set of the multimodal task.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
