Related papers: Cross-lingual Data Augmentation for Document-groun…
Efforts to leverage deep learning models in low-resource regimes have led to numerous augmentation studies. However, the direct application of methods such as mixup and cutout to text data, is limited due to their discrete characteristics.…
Pre-trained large language models (LLMs) have become a cornerstone of modern natural language processing, with their capabilities extending across a wide range of applications and languages. However, the fine-tuning of multilingual LLMs,…
The drafting of documents in the procurement field has progressively become more complex and diverse, driven by the need to meet legal requirements, adapt to technological advancements, and address stakeholder demands. While large language…
Data scarcity in low-resource languages can be addressed with word-to-word translations from labeled task data in high-resource languages using bilingual lexicons. However, bilingual lexicons often have limited lexical overlap with task…
This paper presents a novel Dialect Identification (DID) system developed for the Fifth Edition of the Multi-Genre Broadcast challenge, the task of Fine-grained Arabic Dialect Identification (MGB-5 ADI Challenge). The system improves upon…
Despite strong performance in data-rich regimes, deep learning often underperforms in the data-scarce settings common in practice. While foundation models (FMs) trained on massive datasets demonstrate strong generalization by extracting…
Dialogue data has been a key source for understanding learning processes, offering critical insights into how students engage in collaborative discussions and how these interactions shape their knowledge construction. The advent of Large…
As social-media platforms emerge and evolve faster than the regulations meant to oversee them, automated detoxification might serve as a timely tool for moderators to enforce safe discourse at scale. We here describe our submission to the…
Recently, using large language models (LLMs) for data augmentation has led to considerable improvements in unsupervised sentence embedding models. However, existing methods encounter two primary challenges: limited data diversity and high…
Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena…
Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that, by manipulating and optimizing their…
Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate…
Text documents are structured on multiple levels of detail: individual words are related by syntax, but larger units of text are related by discourse structure. Existing language models generally fail to account for discourse structure, but…
We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior…
Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However, cross-lingual data…
Crowdsourced dialogue corpora are usually limited in scale and topic coverage due to the expensive cost of data curation. This would hinder the generalization of downstream dialogue models to open-domain topics. In this work, we leverage…
The application of on-device language models (ODLMs) on resource-constrained edge devices is a multi-dimensional problem that strikes a fine balance between computational effectiveness, memory, power usage, and linguistic capacity across…
Multi-document grounded dialogue systems (DGDS) belong to a class of conversational agents that answer users' requests by finding supporting knowledge from a collection of documents. Most previous studies aim to improve the knowledge…
Conversational recommendation systems (CRS) engage with users by inferring user preferences from dialog history, providing accurate recommendations, and generating appropriate responses. Previous CRSs use knowledge graph (KG) based…
Large language models (LLMs), such as ChatGPT, have demonstrated impressive performance in the text generation task, showing the ability to understand and respond to complex instructions. However, the performance of naive LLMs in speciffc…