Search Results for author:
Found 14 papers, 5 papers with code
KOAS: Korean Text Offensiveness Analysis System
Warning: This manuscript contains a certain level of offensive expression.
Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference
Commonsense inference poses a unique challenge to reason and generate the physical, social, and causal conditions of a given event.
Improving Bias Mitigation through Bias Experts in Natural Language Understanding
To mitigate the detrimental effect of the bias on the networks, previous works have proposed debiasing methods that down-weight the biased examples identified by an auxiliary model, which is trained with explicit bias labels.
Data Distillation for Neural Network Potentials toward Foundational Dataset
Furthermore, the data can be translated to other metallic systems (aluminum and niobium), without repeating the sampling and distillation processes.
Dynamic Structure Pruning for Compressing CNNs
In this work, we introduce a novel structure pruning method, termed as dynamic structure pruning, to identify optimal pruning granularities for intra-channel pruning.
Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking
Masked language modeling (MLM) has been widely used for pre-training effective bidirectional representations, but incurs substantial training costs.
Handling Out-Of-Vocabulary Problem in Hangeul Word Embeddings
Word embedding is considered an essential factor in improving the performance of various Natural Language Processing (NLP) models.
Multi-pretraining for Large-scale Text Classification
In addition, we propose a weakly supervised pretraining, where labels for text classification are obtained automatically from an existing approach.
Adaptive Compression of Word Embeddings
However, unlike prior works that assign the same length of codes to all words, we adaptively assign different lengths of codes to each word by learning downstream tasks.
Representation Learning for Unseen Words by Bridging Subwords to Semantic Networks
In the first stage, we learn subword embeddings from the pre-trained word embeddings by using an additive composition function of subwords.
Adaptive Convolution for Text Classification
We show the efficacy of our approach in existing CNNs based on the performance evaluation.
Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding
In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding.
Ranked #44 on
Natural Language Inference
on SNLI
Learning to Generate Word Representations using Subword Information
Unlike previous models that learn word representations from a large corpus, we take a set of pre-trained word embeddings and generalize it to word entries, including OOV words.
Incorporating Word Embeddings into Open Directory Project based Large-scale Classification
However, these approaches are limited to small- or moderate-scale text classification.
