Search Results for author:
Found 37 papers, 3 papers with code
Applying Natural Annotation and Curriculum Learning to Named Entity Recognition for Under-Resourced Languages
In this study we test the possibility of (1) using natural annotation to build synthetic training sets from resources not initially designed for the target downstream task and (2) employing curriculum learning methods to select the most suitable examples from synthetic training sets.
BERTology for Machine Translation: What BERT Knows about Linguistic Difficulties for Translation
Pre-trained transformer-based models, such as BERT, have shown excellent performance in most natural language processing benchmark tests, but we still lack a good understanding of the linguistic knowledge of BERT in Neural Machine Translation (NMT).
Estimating Confidence of Predictions of Individual Classifiers and TheirEnsembles for the Genre Classification Task
Genre identification is a kind of non-topic text classification.
BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification
While performance of many text classification tasks has been recently improved due to Pre-trained Language Models (PLMs), in this paper we show that they still suffer from a performance gap when the underlying distribution of topics changes.
Beyond Images: An Integrative Multi-modal Approach to Chest X-Ray Report Generation
Image-to-text radiology report generation aims to automatically produce radiology reports that describe the findings in medical images.
GATology for Linguistics: What Syntactic Dependencies It Knows
Moreover, GAT is more competitive in training speed and syntactic dependency prediction than MT-B, which may reveal a better incorporation of modeling explicit syntactic knowledge and the possibility of combining GAT and BERT in the MT tasks.
Syntactic Knowledge via Graph Attention with BERT in Machine Translation
Although the Transformer model can effectively acquire context features via a self-attention mechanism, deeper syntactic knowledge is still not effectively modeled.
Estimating Confidence of Predictions of Individual Classifiers and Their Ensembles for the Genre Classification Task
We can evaluate robustness via the confidence gap between the correctly classified texts and the misclassified ones on a labeled test corpus, higher gaps make it easier to improve our confidence that our classifier made the right decision.
Towards Arabic Sentence Simplification via Classification and Generative Approaches
This paper presents an attempt to build a Modern Standard Arabic (MSA) sentence-level simplification system.
Experiments with adversarial attacks on text genres
Neural models based on pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTA results in many NLP tasks, including non-topical classification, such as genre identification.
Automatic Difficulty Classification of Arabic Sentences
In this paper, we present a Modern Standard Arabic (MSA) Sentence difficulty classifier, which predicts the difficulty of sentences for language learners using either the CEFR proficiency levels or the binary classification as simple or complex.
Overview of the Fourth BUCC Shared Task: Bilingual Dictionary Induction from Comparable Corpora
The shared task of the 13th Workshop on Building and Using Comparable Corpora was devoted to the induction of bilingual dictionaries from comparable rather than parallel corpora.
Recognizing Semantic Relations by Combining Transformers and Fully Connected Models
Current approaches to automatically telling if a relation exists between two given concepts X and Y can be grouped into two types: 1) those modeling word-paths connecting X and Y in text and 2) those modeling distributional properties of X and Y separately, not necessary in the proximity to each other.
Know thy corpus! Robust methods for digital curation of Web corpora
This paper proposes a novel framework for digital curation of Web corpora in order to provide robust estimation of their parameters, such as their composition and the lexicon.
Sentence Level Human Translation Quality Estimation with Attention-based Neural Networks
This paper explores the use of Deep Learning methods for automatic estimation of quality of human translations.
Towards Functionally Similar Corpus Resources for Translation
We exploit a text-external approach, based on a set of Functional Text Dimensions to model text functions, so that each text can be represented as a vector in a multidimensional space of text functions.
Overview of the Second BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora
We examined manually a small sample of the false negative sentence pairs for the most precise French-English runs and estimated the number of parallel sentence pairs not yet in the provided gold standard.
Toward Pan-Slavic NLP: Some Experiments with Language Adaptation
In this talk I will discuss a general approach, which can be called Language Adaptation, similarly to Domain Adaptation.
MoBiL: A Hybrid Feature Set for Automatic Human Translation Quality Assessment
We compare MoBiL with the QuEst baseline set by using them in classifiers trained with support vector machine and relevance vector machine learning algorithms on the same data set.
Designing and Evaluating a Reliable Corpus of Web Genres via Crowd-Sourcing
In this paper, we present the first web genre corpus which is reliably annotated.
Identifying Word Translations from Comparable Documents Without a Seed Lexicon
The extraction of dictionaries from parallel text corpora is an established technique.
