Related papers: Improved Out-of-Scope Intent Classification with D…

Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific…

Textual open intent classification is crucial for real-world dialogue systems, enabling robust detection of unknown user intents without prior knowledge and contributing to the robustness of the system. While adaptive decision boundary…

Out-of-distribution (OOD) detection plays a crucial role in ensuring the safe deployment of deep neural network (DNN) classifiers. While a myriad of methods have focused on improving the performance of OOD detectors, a critical gap remains…

Dialogue Topic Segmentation (DTS) aims to divide dialogues into coherent segments. DTS plays a crucial role in various NLP downstream tasks, but suffers from chronic problems: data shortage, labeling ambiguity, and incremental complexity of…

Recurrent neural network (RNN) based joint intent classification and slot tagging models have achieved tremendous success in recent years for building spoken language understanding and dialog systems. However, these models suffer from poor…

Intent-detection and slot-filling are the two main tasks in natural language understanding. In this study, we propose CTRAN, a novel encoder-decoder CNN-Transformer-based architecture for intent-detection and slot-filling. In the encoder,…

In this paper, we study the problem of text line recognition. Unlike most approaches targeting specific domains such as scene-text or handwritten documents, we investigate the general problem of developing a universal architecture that can…

Stance detection aims to determine the attitude expressed in text towards a given target. Zero-shot stance detection (ZSSD) has emerged to classify stances towards unseen targets during inference. Recent data augmentation techniques for…

Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed…

Despite continuous advancements in the capabilities of large language models (LLMs), numerical reasoning remains a challenging area. Techniques like chain-of-thought prompting, tree-of-thought prompting, and program-of-thought prompting…

In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformers, we propose a…

Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor security risks. Existing defenses, particularly input-level…

Deep neural networks suffer from the overconfidence issue in the open world, meaning that classifiers could yield confident, incorrect predictions for out-of-distribution (OOD) samples. Thus, it is an urgent and challenging task to detect…

DETR is the first end-to-end object detector using a transformer encoder-decoder architecture and demonstrates competitive performance but low computational efficiency on high resolution feature maps. The subsequent work, Deformable DETR,…

Named entity recognition (NER) for identifying proper nouns in unstructured text is one of the most important and fundamental tasks in natural language processing. However, despite the widespread use of NER models, they still require a…

We present DualNER, a simple and effective framework to make full use of both annotated source language corpus and unlabeled target language text for zero-shot cross-lingual named entity recognition (NER). In particular, we combine two…

In this paper, we are interested in Detection Transformer (DETR), an end-to-end object detection approach based on a transformer encoder-decoder architecture without hand-crafted postprocessing, such as NMS. Inspired by Conditional DETR, an…

Sentence embedding models aim to provide general purpose embeddings for sentences. Most of the models studied in this paper claim to perform well on STS tasks - but they do not report on their suitability for clustering. This paper looks at…

Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches…

Neural machine translation (NMT) has achieved new state-of-the-art performance in translating ambiguous words. However, it is still unclear which component dominates the process of disambiguation. In this paper, we explore the ability of…