Related papers: IntenDD: A Unified Contrastive Learning Approach f…

Intent classification is crucial for conversational agents (chatbots), and deep learning models perform well in this area. However, little research has been done on the explainability of intent classification due to the absence of suitable…

In an era where social media platforms abound, individuals frequently share images that offer insights into their intents and interests, impacting individual life quality and societal stability. Traditional computer vision tasks, such as…

Semantic typing aims at classifying tokens or spans of interest in a textual context into semantic categories such as relations, entity types, and event types. The inferred labels of semantic categories meaningfully interpret how machines…

Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin…

In this paper, we study the few-shot multi-label classification for user intent detection. For multi-label intent detection, state-of-the-art work estimates label-instance relevance scores and uses a threshold to select multiple associated…

Context modeling plays a significant role in building multi-turn dialogue systems. In order to make full use of context information, systems can use Incomplete Utterance Rewriting(IUR) methods to simplify the multi-turn dialogue into…

Intent classification is a fundamental task in the spoken language understanding field that has recently gained the attention of the scientific community, mainly because of the feasibility of approaching it with end-to-end neural models. In…

The ability to detect intent in dialogue systems has become increasingly important in modern technology. These systems often generate a large amount of unlabeled data, and manually labeling this data requires substantial human effort.…

Intent classification is an important task in natural language understanding systems. Existing approaches have achieved perfect scores on the benchmark datasets. However they are not suitable for deployment on low-resource devices like…

High-quality phrase representations are essential to finding topics and related terms in documents (a.k.a. topic mining). Existing phrase representation learning methods either simply combine unigram representations in a context-free manner…

News Discourse Profiling seeks to scrutinize the event-related role of each sentence in a news article and has been proven useful across various downstream applications. Specifically, within the context of a given news discourse, each…

Text classification, a core component of task-oriented dialogue systems, attracts continuous research from both the research and industry community, and has resulted in tremendous progress. However, existing method does not consider the use…

Intent classification is an important component of a functional Information Retrieval ecosystem. Many current approaches to intent classification, typically framed as a classification problem, can be problematic as intents are often hard to…

Generalized intent discovery aims to extend a closed-set in-domain intent classifier to an open-world intent set including in-domain and out-of-domain intents. The key challenges lie in pseudo label disambiguation and representation…

Intent-based recommender systems have garnered significant attention for uncovering latent fine-grained preferences. Intents, as underlying factors of interactions, are crucial for improving recommendation interpretability. Most methods…

In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a challenging case of OOD detection, where no labels for in-domain…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…

Learning vectors that capture the meaning of concepts remains a fundamental challenge. Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled modest improvements to the quality of such concept embeddings.…

Recent advanced methods in Natural Language Understanding for Task-oriented Dialogue (TOD) Systems (e.g., intent detection and slot filling) require a large amount of annotated data to achieve competitive performance. In reality,…

Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable…