Spain

explainability methods

native-like english

complementary labels

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

We propose a novel task of native-like expression identification, and a propose a classifier-based solution for it which involves (a) training three-way classifier on originally binary labelled data, and (b) applying an explainability method to the forward computation of the trained model to extract native-like expressions from identified sentences. Our crowdsourcing-based evaluation and in-depth analysis suggest that our method successfully uncovers linguistically interesting usages distinctive of native speech.

Native-like Expression Identification by Contrasting Native and Proficient Second Language Speakers

technical paper

Multi-Word Lexical Simplification

Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation

"Judge me by my size (noun), do you?" YodaLib: A Demographic-Aware Humor Generation Framework

Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

MEISD: A Multimodal Multi-Label Emotion, Intensity and Sentiment Dialogue Dataset for Emotion Recognition and Sentiment Analysis in Conversations

Joint Chinese Word Segmentation and Part-of-speech Tagging via Multi-channel Attention of Character N-grams

Towards the First Machine Translation System for Sumerian Transliterations

Meet Changes with Constancy: Learning Invariance in Multi-Source Translation

Context Dependent Semantic Parsing: A Survey

Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet

https://d3smihljt9218e.cloudfront.net/transcript/4614/subtitle/fefcfd2da46382d1b57954600487b603.vtt

English (automatic)

Native-like Expression Identification by Contrasting Native and Proficient Second Language Speakers

Downloads

Next from COLING 2020

Multi-Word Lexical Simplification

Similar lecture

Robust System based on Transformer for Code-Mixed Sentiment Classification