Search Results for author:
Found 36 papers, 4 papers with code
Implicit representations of event properties within contextual language models: Searching for “causativity neurons”
This paper addresses the question to which extent neural contextual language models such as BERT implicitly represent complex semantic properties.
QADI: Arabic Dialect Identification in the Wild
For extrinsic evaluation, we are able to build effective country level dialect identification on tweets with a macro-averaged F1-score of 60. 6% across 18 classes.
Multilingual Nonce Dependency Treebanks: Understanding how LLMs represent and process syntactic structure
We replicate the findings of M\"uller-Eberstein et al. (2022) on nonce test data and show that the performance declines on both MLMs and ALMs wrt.
Probing for Constituency Structure in Neural Language Models
We find that 4 pretrained transfomer LMs obtain high performance on our probing tasks even on manipulated data, suggesting that semantic and syntactic knowledge in their representations can be separated and that constituency information is in fact learned by the LM.
Automatic Expansion and Retargeting of Arabic Offensive Language Training
Rampant use of offensive language on social media led to recent efforts on automatic identification of such language.
A Few Topical Tweets are Enough for Effective User Stance Detection
We show that this approach outperforms two strong baselines and achieves 89. 6{\%} accuracy and 91. 3{\%} macro F-measure on eight controversial topics.
Pre-Training BERT on Arabic Tweets: Practical Considerations
The experiments highlight the centrality of data diversity and the efficacy of linguistically aware segmentation.
ALT at SemEval-2020 Task 12: Arabic and English Offensive Language Identification in Social Media
This paper describes the systems submitted by the Arabic Language Technology group (ALT) at SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media.
Arabic Dialect Identification in the Wild
We present QADI, an automatically collected dataset of tweets belonging to a wide range of country-level Arabic dialects -covering 18 different countries in the Middle East and North Africa region.
ALT Submission for OSACT Shared Task on Offensive Language Detection
In this paper, we describe our efforts at OSACT Shared Task on Offensive Language Detection.
A Few Topical Tweets are Enough for Effective User-Level Stance Detection
We show that this approach outperforms two strong baselines and achieves 89. 6% accuracy and 91. 3% macro F-measure on eight controversial topics.
Arabic Offensive Language on Twitter: Analysis and Experiments
Detecting offensive language on Twitter has many applications ranging from detecting/predicting bullying to measuring polarization.
A System for Diacritizing Four Varieties of Arabic
Short vowels, aka diacritics, are more often omitted when writing different varieties of Arabic including Modern Standard Arabic (MSA), Classical Arabic (CA), and Dialectal Arabic (DA).
QC-GO Submission for MADAR Shared Task: Arabic Fine-Grained Dialect Identification
This paper describes the QC-GO team submission to the MADAR Shared Task Subtask 1 (travel domain dialect identification) and Subtask 2 (Twitter user location identification).
POS Tagging for Improving Code-Switching Identification in Arabic
When speakers code-switch between their native language and a second language or language variant, they follow a syntactic pattern where words and phrases from the embedded language are inserted into the matrix language.
Highly Effective Arabic Diacritization using Sequence to Sequence Modeling
Arabic text is typically written without short vowels (or diacritics).
Diacritization of Maghrebi Arabic Sub-Dialects
Diacritization process attempt to restore the short vowels in Arabic written text; which typically are omitted.
Mumpitz at PARSEME Shared Task 2018: A Bidirectional LSTM for the Identification of Verbal Multiword Expressions
We submitted results for seven languages in the closed track of the task and for one language in the open track.
GHHT at CALCS 2018: Named Entity Recognition for Dialectal Arabic Using Neural Networks
This paper describes our system submission to the CALCS 2018 shared task on named entity recognition on code-switched data for the language variant pair of Modern Standard Arabic and Egyptian dialectal Arabic.
German and French Neural Supertagging Experiments for LTAG Parsing
We present ongoing work on data-driven parsing of German and French with Lexicalized Tree Adjoining Grammars.
GHH at SemEval-2018 Task 10: Discovering Discriminative Attributes in Distributional Semantics
This paper describes our system submission to the SemEval 2018 Task 10 on Capturing Discriminative Attributes.
Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM
Arabic word segmentation is essential for a variety of NLP applications such as machine translation and information retrieval.
Ranked #1 on
Sentiment Analysis
on DynaSent
(using extra training data)
Learning from Relatives: Unified Dialectal Arabic Segmentation
Arabic dialects do not just share a common koin{\'e}, but there are shared pan-dialectal linguistic phenomena that allow computational models for dialects to learn from each other.
A Neural Architecture for Dialectal Arabic Segmentation
The automated processing of Arabic Dialects is challenging due to the lack of spelling standards and to the scarcity of annotated data and resources in general.
CogALex-V Shared Task: GHHH - Detecting Semantic Relations via Word Embeddings
The evaluation results of our system on the test set is 88. 1{\%} (79. 0{\%} for TRUE only) f-measure for Task-1 on detecting semantic similarity, and 76. 0{\%} (42. 3{\%} when excluding RANDOM) for Task-2 on identifying finer-grained semantic relations.
An Arabic-Moroccan Darija Code-Switched Corpus
In this paper, we describe our effort in the development and annotation of a large scale corpus containing code-switched data.
Une m\'etagrammaire de l'interface morpho-s\'emantique dans les verbes en arabe
Dans cet article, nous pr{\'e}sentons une mod{\'e}lisation de la morphologie d{\'e}rivationnelle de l{'}arabe utilisant le cadre m{\'e}tagrammatical offert par XMG.
Arabic Word Generation and Modelling for Spell Checking
Furthermore, from a large list of valid forms and invalid forms we create a character-based tri-gram language model to approximate knowledge about permissible character clusters in Arabic, creating a novel method for detecting spelling errors.
