Теріс Үлгілеу
Related Papers
Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling
Syntactic features play an essential role in identifying relationship in a sentence. Pre- vious neural network models directly work on raw word sequences or constituent parse trees, thus often suffer …...
A Simple Language Model based on PMI Matrix Approximations
AbstractIn this study, we introduce a new approach for learning language models by training them to estimate word-context pointwise mutual information (PMI), and then deriving the desired conditional probabilities from …...
Incremental Skip-gram Model with Negative Sampling
AbstractThis paper explores an incremental training strategy for the skip-gram model with negative sampling (SGNS) from both empirical and theoretical perspectives. Existing methods of neural word embeddings, including SGNS, are …...
ADAPT at SemEval-2018 Task 9: Skip-Gram Word Embeddings for Unsupervised Hypernym Discovery in Specialised Corpora
AbstractThis paper describes a simple but competitive unsupervised system for hypernym discovery. The system uses skip-gram word embeddings with negative sampling, trained on specialised corpora. Candidate hypernyms for an input …...
MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network
AbstractSemEval 2018 Task 7 tasked participants to build a system to classify two entities within a sentence into one of the 6 possible relation types. We tested 3 classes of …...
Improving Cross-Domain Chinese Word Segmentation with Word Embeddings
AbstractCross-domain Chinese Word Segmentation (CWS) remains a challenge despite recent progress in neural-based CWS. The limited amount of annotated data in the target domain has been the key obstacle to …...
DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding
AbstractForm understanding depends on both textual contents and organizational structure. Although modern OCR performs well, it is still challenging to realize general form understanding because forms are commonly used and …...
Cross-language Sentence Selection via Data Augmentation and Rationale Training
AbstractThis paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a …...
Multi-stage Training with Improved Negative Contrast for Neural Passage Retrieval
AbstractIn the context of neural passage retrieval, we study three promising techniques: synthetic data generation, negative sampling, and fusion. We systematically investigate how these techniques contribute to the performance of …...
CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion
AbstractKnowledge graphs store a large number of factual triples while they are still incomplete, inevitably. The previous knowledge graph completion (KGC) models predict missing links between entities merely relying on …...
OpticE: A Coherence Theory-Based Model for Link Prediction
AbstractKnowledge representation learning is a key step required for link prediction tasks with knowledge graphs (KGs). During the learning process, the semantics of each entity are embedded by a vector …...
Rethinking Negative Sampling for Handling Missing Entity Annotations
AbstractNegative sampling is highly effective in handling missing annotations for named entity recognition (NER). One of our contributions is an analysis on how it makes sense through introducing two insightful …...
Exploring Data-Centric Strategies for French Patent Classification: A Baseline and Comparisons
AbstractThis paper proposes a novel approach to French patent classification leveraging data-centric strategies. We compare different approaches for the two deepest levels of the IPC hierarchy: the IPC group and …...
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
AbstractEmbedding models have shown great power in knowledge graph completion (KGC) task. By learning structural constraints for each training triple, these methods implicitly memorize intrinsic relation rules to infer missing …...