arXiv subjects

Ismail Berrada

Publications and source records attributed to Ismail Berrada.

23 records · Page 2Linked to original sources

arXiv2022

UM6P-CS at SemEval-2022 Task 11: Enhancing Multilingual and Code-Mixed Complex Named Entity Recognition via Pseudo Labels using Multilingual Transformer

Building real-world complex Named Entity Recognition (NER) systems is a challenging task. This is due to the complexity and ambiguity of named entities that appear in various contexts such as short input sentences, emerging entities, and complex entities. Besides, real-world queries are mostly malformed, as they can be code-mixed or multilingual, among other scenarios. In this paper, we introduce our submitted system to the Multilingual Complex Named Entity Recognition (MultiCoNER) shared task. We approach the complex NER for multilingual and code-mixed queries, by relying on the contextualized representation provided by the multilingual Transformer XLM-RoBERTa. In addition to the CRF-based token classification layer, we incorporate a span classification loss to recognize named entities spans. Furthermore, we use a self-training mechanism to generate weakly-annotated data from a large unlabeled dataset. Our proposed system is ranked 6th and 8th in the multilingual and code-mixed MultiCoNER's tracks respectively.

cs.CL↗

arXiv2021

Deep Multi-Task Model for Sarcasm Detection and Sentiment Analysis in Arabic Language

The prominence of figurative language devices, such as sarcasm and irony, poses serious challenges for Arabic Sentiment Analysis (SA). While previous research works tackle SA and sarcasm detection separately, this paper introduces an end-to-end deep Multi-Task Learning (MTL) model, allowing knowledge interaction between the two tasks. Our MTL model's architecture consists of a Bidirectional Encoder Representation from Transformers (BERT) model, a multi-task attention interaction module, and two task classifiers. The overall obtained results show that our proposed model outperforms its single-task counterparts on both SA and sarcasm detection sub-tasks.

cs.CL↗

arXiv2021

BERT-based Multi-Task Model for Country and Province Level Modern Standard Arabic and Dialectal Arabic Identification

Dialect and standard language identification are crucial tasks for many Arabic natural language processing applications. In this paper, we present our deep learning-based system, submitted to the second NADI shared task for country-level and province-level identification of Modern Standard Arabic (MSA) and Dialectal Arabic (DA). The system is based on an end-to-end deep Multi-Task Learning (MTL) model to tackle both country-level and province-level MSA/DA identification. The latter MTL model consists of a shared Bidirectional Encoder Representation Transformers (BERT) encoder, two task-specific attention layers, and two classifiers. Our key idea is to leverage both the task-discriminative and the inter-task shared features for country and province MSA/DA identification. The obtained results show that our MTL model outperforms single-task models on most subtasks.

cs.CL↗

arXiv2021

An open access NLP dataset for Arabic dialects : Data collection, labeling, and model construction

Natural Language Processing (NLP) is today a very active field of research and innovation. Many applications need however big sets of data for supervised learning, suitably labelled for the training purpose. This includes applications for the Arabic language and its national dialects. However, such open access labeled data sets in Arabic and its dialects are lacking in the Data Science ecosystem and this lack can be a burden to innovation and research in this field. In this work, we present an open data set of social data content in several Arabic dialects. This data was collected from the Twitter social network and consists on +50K twits in five (5) national dialects. Furthermore, this data was labeled for several applications, namely dialect detection, topic detection and sentiment analysis. We publish this data as an open access data to encourage innovation and encourage other works in the field of NLP for Arabic dialects and social media. A selection of models were built using this data set and are presented in this paper along with their performances.

cs.CL↗

arXiv2019

A Hypergraph Based Approach for the 4-Constraint Satisfaction Problem Tractability

Constraint Satisfaction Problem (CSP) is a framework for modeling and solving a variety of real-world problems. Once the problem is expressed as a finite set of constraints, the goal is to find the variables' values satisfying them. Even though the problem is in general NP-complete, there are some approximation and practical techniques to tackle its intractability. One of the most widely used techniques is the Constraint Propagation. It consists in explicitly excluding values or combination of values for some variables whenever they make a given subset of constraints unsatisfied. In this paper, we deal with a CSP subclass which we call 4-CSP and whose constraint network infers relations of the form: $\{ x \sim α, x-y \sim β, (x-y) - (z-t) \sim λ\}$, where $x, y, z$ and $t$ are real variables, $α, β$ and $ λ$ are real constants and $ \sim \in \{\leq , \geq \} $. The paper provides the first graph-based proofs of the 4-CSP tractability and elaborates algorithms for 4-CSP resolution based on the positive linear dependence theory, the hypergraph closure and the constraint propagation technique. Time and space complexities of the resolution algorithms are proved to be polynomial.

cs.DM↗