Spain

pseudo-labels

few-shot learning

text classification

intent detection

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

This paper introduces a state-of-the-art pseudo-labeling technique for few-shot intent detection. Our folding/unfolding hierarchical clustering algorithm, which assigns weighted pseudo-labels to unlabeled user utterances, is a two-step method yielding significant improvement over existing solutions. This performance is achieved on multiple intent detection datasets, as well as the more general text classification task. Our approach nicely complements existing solutions, thereby providing an even stronger state-of-the-art ensemble method.

Few-Shot Pseudo-Labeling for Intent Detection

poster

A High Precision Pipeline for Financial Knowledge Graph Construction

How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT's Attention

Neural text normalization leveraging similarities of strings and sounds

Mama/Papa, Is this Text for Me?

Specializing Word Vectors by Spectral Decomposition on Heterogeneously Twisted Graphs

Hy-NLI: a Hybrid system for Natural Language Inference

Unsupervised Deep Language and Dialect Identification for Short Texts

Generating Diverse Corrections with Local Beam Search \\ for Grammatical Error Correction

Few-Shot Text Classification with Edge-Labeling Graph NeuralNetwork-Based Prototypical Network

Morphological Disambiguation from Stemming Data

Few-Shot Pseudo-Labeling for Intent Detection

Downloads

Next from COLING 2020

A High Precision Pipeline for Financial Knowledge Graph Construction

Similar lecture

Few-Shot Text Classification with Edge-Labeling Graph NeuralNetwork-Based Prototypical Network