Сөйлем Кодтаушы
Related Papers
Learning Visually Grounded Sentence Representations
AbstractWe investigate grounded sentence representations, where we train a sentence encoder to predict the image features of a given caption—i.e., we try to “imagine” how a sentence would be depicted …...
NLITrans at SemEval-2018 Task 12: Transfer of Semantic Knowledge for Argument Comprehension
AbstractThe Argument Reasoning Comprehension Task is a difficult challenge requiring significant language understanding and complex reasoning over world knowledge. We focus on transfer of a sentence encoder to bootstrap more …...
Continual Learning for Sentence Representations Using Conceptors
AbstractDistributed representations of sentences have become ubiquitous in natural language processing tasks. In this paper, we consider a continual learning scenario for sentence representations: Given a sequence of corpora, we …...
On Measuring Social Biases in Sentence Encoders
AbstractThe Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research …...
Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation
AbstractReview rating prediction of text reviews is a rapidly growing technology with a wide range of applications in natural language processing. However, most existing methods either use hand-crafted features or …...
Intermediate Self-supervised Learning for Machine Translation Quality Estimation
AbstractPre-training sentence encoders is effective in many natural language processing tasks including machine translation (MT) quality estimation (QE), due partly to the scarcity of annotated QE data required for supervised …...
CXR Data Annotation and Classification with Pre-trained Language Models
AbstractClinical data annotation has been one of the major obstacles for applying machine learning approaches in clinical NLP. Open-source tools such as NegBio and CheXpert are usually designed on data …...
Effective and Efficient Query-aware Snippet Extraction for Web Search
AbstractQuery-aware webpage snippet extraction is widely used in search engines to help users better understand the content of the returned webpages before clicking. The extracted snippet is expected to summarize …...
Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders
AbstractPrevious works have demonstrated the effectiveness of utilising pre-trained sentence encoders based on their sentence representations for meaning comparison tasks. Though such representations are shown to capture hidden syntax structures, …...