Related papers: Toward Micro-Dialect Identification in Diaglossic …

As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inference budgets remains…

Idiomatic expressions can be problematic for natural language processing applications as their meaning cannot be inferred from their constituting words. A lack of successful methodological approaches and sufficiently large datasets prevents…

We probe the layers in multilingual BERT (mBERT) for phylogenetic and geographic language signals across 100 languages and compute language distances based on the mBERT representations. We 1) employ the language distances to infer and…

We present state-of-the-art results on morphosyntactic tagging across different varieties of Arabic using fine-tuned pre-trained transformer language models. Our models consistently outperform existing systems in Modern Standard Arabic and…

Language identification of social media text has been an interesting problem of study in recent years. Social media messages are predominantly in code mixed in non-English speaking states. Prior knowledge by pre-training contextual…

Twitter is a well-known microblogging social site where users express their views and opinions in real-time. As a result, tweets tend to contain valuable information. With the advancements of deep learning in the domain of natural language…

Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly. In this work, we use Gaussian models for density…

Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to. We propose a new model, named Dialogue…

In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. Specifically, previous studies have reported multiple modeling biases that the…

Machine translation in low-resource language pairs faces significant challenges due to the scarcity of parallel corpora and linguistic resources. This study focuses on the case of English-Marathi language pairs, where existing datasets are…

We introduce Atlas-Chat, the first-ever collection of LLMs specifically developed for dialectal Arabic. Focusing on Moroccan Arabic, also known as Darija, we construct our instruction dataset by consolidating existing Darija language…

We report our models for detecting age, language variety, and gender from social media data in the context of the Arabic author profiling and deception detection shared task (APDA). We build simple models based on pre-trained bidirectional…

This study presents systems submitted by the University of Texas at Dallas, Center for Robust Speech Systems (UTD-CRSS) to the MGB-3 Arabic Dialect Identification (ADI) subtask. This task is defined to discriminate between five dialects of…

Making an informed choice of pre-trained language model (LM) is critical for performance, yet environmentally costly, and as such widely underexplored. The field of Computer Vision has begun to tackle encoder ranking, with promising forays…

Detecting fine-grained differences in content conveyed in different languages matters for cross-lingual NLP and multilingual corpora analysis, but it is a challenging machine learning problem since annotation is expensive and hard to scale.…

Arabic is one of the oldest languages still in use today. As a result, several Arabic-speaking regions have developed dialects that are unique to them. Dialect and emotion recognition have various uses in Arabic text analysis, such as…

Speech foundation models, such as HuBERT and its variants, are pre-trained on large amounts of unlabeled speech data and then used for a range of downstream tasks. These models use a masked prediction objective, where the model learns to…

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…

With an evergrowing number of LLMs reporting superlative performance for English, their ability to perform equitably for different dialects of English ($\textit{i.e.}$, dialect robustness) needs to be ascertained. Specifically, we use…

With the rapid development of artificial intelligence, conversational bots have became prevalent in mainstream E-commerce platforms, which can provide convenient customer service timely. To satisfy the user, the conversational bots need to…