相关论文: AP18-OLR Challenge: Three Tasks and Their Baseline…

Transliterating related languages that use different scripts into a common script is effective for improving crosslingual transfer in downstream tasks. However, this methodology often makes pretraining a model from scratch unavoidable, as…

Natural Language Inference (NLI) is the task of inferring whether the hypothesis can be justified by the given premise. Basically, we classify the hypothesis into three labels(entailment, neutrality and contradiction) given the premise. NLI…

Cross-lingual word embeddings (CLEs) enable multilingual modeling of meaning and facilitate cross-lingual transfer of NLP models. Despite their ubiquitous usage in downstream tasks, recent increasingly popular projection-based CLE models…

In multi-lingual societies, where multiple languages are spoken in a small geographic vicinity, informal conversations often involve mix of languages. Existing speech technologies may be inefficient in extracting information from such…

Advancements in deep neural networks have allowed automatic speech recognition (ASR) systems to attain human parity on several publicly available clean speech datasets. However, even state-of-the-art ASR systems experience performance…

Automatic Speech Recognition (ASR) error correction aims to correct recognition errors while preserving accurate text. Although traditional approaches demonstrate moderate effectiveness, LLMs offer a paradigm that eliminates the need for…

Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking advantage of low amounts of labeled corpora in multiple…

As language and visual understanding by machines progresses rapidly, we are observing an increasing interest in holistic architectures that tightly interlink both modalities in a joint learning and inference process. This trend has allowed…

Natural language inference (NLI) data has proven useful in benchmarking and, especially, as pretraining data for tasks requiring language understanding. However, the crowdsourcing protocol that was used to collect this data has known issues…

Deep neural models have repeatedly proved excellent at memorizing surface patterns from large datasets for various ML and NLP benchmarks. They struggle to achieve human-like thinking, however, because they lack the skill of iterative…

Language model post-training is applied to refine behaviors and unlock new skills across a wide range of recent language models, but open recipes for applying these techniques lag behind proprietary ones. The underlying training data and…

Open Set Recognition (OSR) is about dealing with unknown situations that were not learned by the models during training. In this paper, we provide a survey of existing works about OSR and distinguish their respective advantages and…

Open-set recognition (OSR) aims to simultaneously detect unknown-class samples and classify known-class samples. Most of the existing OSR methods are inductive methods, which generally suffer from the domain shift problem that the learned…

We describe the CoNLL-2003 shared task: language-independent named entity recognition. We give background information on the data sets (English and German) and the evaluation method, present a general overview of the systems that have taken…

This paper presents our solution for the Elderly Action Recognition (EAR) Challenge, part of the Computer Vision for Smalls Workshop at WACV 2025. The competition focuses on recognizing Activities of Daily Living (ADLs) performed by the…

This paper describes the Arabic Multi-Genre Broadcast (MGB-2) Challenge for SLT-2016. Unlike last year's English MGB Challenge, which focused on recognition of diverse TV genres, this year, the challenge has an emphasis on handling the…

Active learning (AL) aims to enhance model performance by selectively collecting highly informative data, thereby minimizing annotation costs. However, in practical scenarios, unlabeled data may contain out-of-distribution (OOD) samples,…

Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and…

Spoken language understanding (SLU) tasks have been studied for many decades in the speech research community, but have not received as much attention as lower-level tasks like speech and speaker recognition. In particular, there are not…

We introduce a new task, Map and Locate, which unifies the traditionally distinct objectives of open-vocabulary segmentation - detecting and segmenting object instances based on natural language queries - and 3D reconstruction, the process…