Related papers: ConVEx: Data-Efficient and Few-Shot Slot Labeling

We introduce Span-ConveRT, a light-weight model for dialog slot-filling which frames the task as a turn-based span extraction task. This formulation allows for a simple integration of conversational knowledge coded in large pretrained…

General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train. We propose ConveRT (Conversational Representations from…

Slot labelling is an essential component of any dialogue system, aiming to find important arguments in every user turn. Common approaches involve large pre-trained language models (PLMs) like BERT or RoBERTa, but they face challenges such…

Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms. Although promising results have been achieved, these models often suffer from slow inference or…

Sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing. Large-scale pre-trained language models…

With the advent of conversational assistants, like Amazon Alexa, Google Now, etc., dialogue systems are gaining a lot of traction, especially in industrial setting. These systems typically consist of Spoken Language understanding component…

We describe ConvMemory, a small 3.6M-parameter learned reranker for conversational long-term memory retrieval, trained with cross-encoder teacher supervision over fused dense and lexical features. On the LongMemEval memory family,…

This paper tackles the problem of few-shot learning, which aims to learn new visual concepts from a few examples. A common problem setting in few-shot classification assumes random sampling strategy in acquiring data labels, which is…

Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue. Existing approaches use hand-crafted templates and…

The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the…

Finding valuable training data points for deep neural networks has been a core research challenge with many applications. In recent years, various techniques for calculating the "value" of individual training datapoints have been proposed…

We present SegNeXt, a simple convolutional network architecture for semantic segmentation. Recent transformer-based models have dominated the field of semantic segmentation due to the efficiency of self-attention in encoding spatial…

Globalization and multiculturalism continue to produce increasingly diverse speech varieties. Yet current spoken dialogue systems frequently fail on under-represented dialects and accents, often misidentifying the input language and causing…

Few-shot dialogue state tracking (DST) is a realistic problem that trains the DST model with limited labeled data. Existing few-shot methods mainly transfer knowledge learned from external labeled dialogue data (e.g., from question…

We present ConvoCache, a conversational caching system that solves the problem of slow and expensive generative AI models in spoken chatbots. ConvoCache finds a semantically similar prompt in the past and reuses the response. In this paper…

Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets. In this paper, we propose LocTex that takes advantage of the low-cost localized textual…

Unsupervised text embeddings extraction is crucial for text understanding in machine learning. Word2Vec and its variants have received substantial success in mapping words with similar syntactic or semantic meaning to vectors close to each…

Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which…

Vision-language models have recently shown great potential on many tasks in computer vision. Meanwhile, prior work demonstrates prompt tuning designed for vision-language models could acquire superior performance on few-shot image…

Existing task-oriented conversational search systems heavily rely on domain ontologies with pre-defined slots and candidate value sets. In practical applications, these prerequisites are hard to meet, due to the emerging new user…