TaCL: Improving BERT pre-training with token-aware contrastive learning
Masked language models (MLMs) such as BERT and RoBERTa have revolutionized the
field of Natural Language Understanding in the past few years. However, existing pre …
field of Natural Language Understanding in the past few years. However, existing pre …
Improving word translation via two-stage contrastive learning
Word translation or bilingual lexicon induction (BLI) is a key cross-lingual task, aiming to
bridge the lexical gap between different languages. In this work, we propose a robust and …
bridge the lexical gap between different languages. In this work, we propose a robust and …
Rewire-then-probe: A contrastive recipe for probing biomedical knowledge of pre-trained language models
Knowledge probing is crucial for understanding the knowledge transfer mechanism behind
the pre-trained language models (PLMs). Despite the growing progress of probing …
the pre-trained language models (PLMs). Despite the growing progress of probing …
Distilling semantic concept embeddings from contrastively fine-tuned language models
Learning vectors that capture the meaning of concepts remains a fundamental challenge.
Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled …
Somewhat surprisingly, perhaps, pre-trained language models have thus far only enabled …
Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks
Textual label names (descriptions) are typically semantically rich in many natural language
understanding (NLU) tasks. In this paper, we incorporate the prompting methodology, which …
understanding (NLU) tasks. In this paper, we incorporate the prompting methodology, which …
Automatically suggesting diverse example sentences for l2 japanese learners using pre-trained language models
Providing example sentences that are diverse and aligned with learners {'} proficiency levels
is essential for fostering effective language acquisition. This study examines the use of Pre …
is essential for fostering effective language acquisition. This study examines the use of Pre …
Modelling multi-modal cross-interaction for multi-label few-shot image classification based on local feature selection
The aim of multi-label few-shot image classification (ML-FSIC) is to assign semantic labels to
images, in settings where only a small number of training examples are available for each …
images, in settings where only a small number of training examples are available for each …
Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems
End-to-end (E2E) task-oriented dialogue (ToD) systems are prone to fall into the so-called"
likelihood trap", resulting in generated responses which are dull, repetitive, and often …
likelihood trap", resulting in generated responses which are dull, repetitive, and often …
Modelling Multi-modal Cross-interaction for ML-FSIC Based on Local Feature Selection
The aim of multi-label few-shot image classification (ML-FSIC) is to assign semantic labels to
images, in settings where only a small number of training examples are available for each …
images, in settings where only a small number of training examples are available for each …
Distilling Monolingual and Crosslingual Word-in-Context Representations
In this study, we propose a method that distils representations of word meaning in context
from a pre-trained masked language model in both monolingual and crosslingual settings …
from a pre-trained masked language model in both monolingual and crosslingual settings …