The success of data mixing augmentations in image classification tasks has been well-received.
Our first key insight is that MultiTask Learning (MTL) and hardware-aware Neural Architecture Search (NAS) can work in synergy to greatly benefit on-device Dense Predictions (DP).
Ranked #96 on Semantic Segmentation on NYU Depth v2
Automatic post-editing (APE) is an important remedy for reducing errors of raw translated texts that are produced by machine translation (MT) systems or software-aided translation.
To address these constraints, we propose the Any-Width Network (AWN), an adjustable-width CNN architecture and associated training routine that allow for fine-grained control over speed and accuracy during inference.
In this paper, we provide an overview of the WNUT-2020 shared task on the identification of informative COVID-19 English Tweets.
We propose a simple yet effective embedding model to learn quaternion embeddings for entities and relations in knowledge graphs.
The paper describes the organisation of the "HateSpeech Detection" (HSD) task at the VLSP workshop 2019 on detecting the fine-grained presence of hate speech in Vietnamese textual items (i. e., messages) extracted from Facebook, which is the most popular social network site (SNS) in Vietnam.
In this paper, we propose a new label attention model for automatic ICD coding, which can handle both the various lengths and the interdependence of the ICD code related text fragments.
Ranked #6 on Medical Code Prediction on MIMIC-III
We present BERTweet, the first public large-scale pre-trained language model for English Tweets.
Ranked #1 on Sentiment Analysis on TweetEval
Pain is the main symptom that patients present with to the emergency department (ED).
We demonstrate the effectiveness of the proposed approach on our pre-trained word embedding models in Vietnamese to select which models are suitable for a named entity recognition (NER) task.
In this paper, we introduce an embedding model, named CapsE, exploring a capsule network to model relationship triples (subject, relation, object).
Ranked #39 on Link Prediction on WN18RR
In this work we propose the new, subjective task of quantifying perceived face similarity between a pair of faces.
After that, the 3-column matrix is fed into a deep learning architecture to re-rank the search results returned by a basis ranker.
This paper describes our NIHRIO system for SemEval-2018 Task 3 "Irony detection in English tweets".
We present an easy-to-use and fast toolkit, namely VnCoreNLP---a Java NLP annotation pipeline for Vietnamese.
This paper presents an empirical comparison of two strategies for Vietnamese Part-of-Speech (POS) tagging from unsegmented text: (i) a pipeline strategy where we consider the output of a word segmenter as the input of a POS tagger, and (ii) a joint strategy where we predict a combined segmentation and POS tag for each syllable.
Recent research has shown that the performance of search personalization depends on the richness of user profiles which normally represent the user's topical interests.