Related papers: IDAS: Intent Discovery with Abstractive Summarizat…

Despite the remarkable success of Large Language Models (LLMs) in text understanding and generation, their potential for text clustering tasks remains underexplored. We observed that powerful closed-source LLMs provide good quality…

Fake news detection is an important and challenging task for defending online information integrity. Existing state-of-the-art approaches typically extract news semantic clues, such as writing patterns that include emotional words,…

In this paper, we propose Selection and Pooling with Large Language Models (SPILL), an intuitive and domain-adaptive method for intent clustering without fine-tuning. Existing embeddings-based clustering methods rely on a few labeled…

Suicidal ideation detection is critical for real-time suicide prevention, yet its progress faces two under-explored challenges: limited language coverage and unreliable annotation practices. Most available datasets are in English, but even…

Causal discovery is fundamental to scientific research, yet traditional statistical algorithms face significant challenges, including expensive data collection, redundant computation for known relations, and unrealistic assumptions. While…

Word sense induction (WSI) is the task of unsupervised clustering of word usages within a sentence to distinguish senses. Recent work obtain strong results by clustering lexical substitutes derived from pre-trained RNN language models…

This work shows how to improve and interpret the commonly used dual encoder model for response suggestion in dialogue. We present an attentive dual encoder model that includes an attention mechanism on top of the extracted word-level…

Semi-supervised dialogue summarization (SSDS) leverages model-generated summaries to reduce reliance on human-labeled data and improve the performance of summarization models. While addressing label noise, previous works on semi-supervised…

Unsupervised clustering is widely used to explore large corpora, but existing formulations neither consider the users' goals nor explain clusters' meanings. We propose a new task formulation, "Goal-Driven Clustering with Explanations"…

We describe our language-independent unsupervised word sense induction system. This system only uses topic features to cluster different word senses in their global context topic space. Using unlabeled data, this system trains a latent…

Construction of human-curated annotated datasets for abstractive text summarization (ATS) is very time-consuming and expensive because creating each instance requires a human annotator to read a long document and compose a shorter summary…

Unsupervised domain adaptation for semantic segmentation (DASS) aims to transfer knowledge from a label-rich source domain to a target domain with no labels. Two key approaches in DASS are (1) vision-only approaches using masking or…

Recent research shows that in-context learning (ICL) can be effective even when demonstrations have missing or incorrect labels. To shed light on this capability, we examine a canonical setting where the demonstrations are drawn according…

We propose a self-supervised Gaussian ATtention network for image Clustering (GATCluster). Rather than extracting intermediate features first and then performing the traditional clustering algorithm, GATCluster directly outputs semantic…

Conversational systems often rely on embedding models for intent classification and intent clustering tasks. The advent of Large Language Models (LLMs), which enable instructional embeddings allowing one to adjust semantics over the…

Instruction-following LLMs have recently allowed systems to discover hidden concepts from a collection of unstructured documents based on a natural language description of the purpose of the discovery (i.e., goal). Still, the quality of the…

Intent modelling has become an important part of modern dialogue systems. With the rapid expansion of practical dialogue systems and virtual assistants, such as Amazon Alexa, Apple Siri, and Google Assistant, the interest has only…

Recognizing speaker intent in long audio dialogues among speakers has a wide range of applications, but is a non-trivial AI task due to complex inter-dependencies in speaker utterances and scarce annotated data. To address these challenges,…

We introduce a dataset of concept learning tasks that helps uncover implicit biases in large language models. Using in-context concept learning experiments, we found that language models may have a bias toward upward monotonicity in…

Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples for each user intent. We propose a novel pre-training…