40 citations · 152 across the 36 of their papers we have counts for
31 papers · 1 filter
Learning to Predict Concept Ordering for Common Sense Generation
Tianhui Zhang, Danushka Bollegala, Bei Peng
Prior work has shown that the ordering in which concepts are shown to a commonsense generator plays an important role, affecting the quality of the generated sentence. However, it…
Unsupervised Semantic Variation Prediction using the Distribution of Sibling Embeddings
Taichi Aida, Danushka Bollegala
Languages are dynamic entities, where the meanings associated with words constantly change with time. Detecting the semantic variation of words is an important task for various NLP…
Learning to Borrow -- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion
Huda Hakami, Mona Hakami, Angrosh Mandya +1
Prior work on integrating text corpora with knowledge graphs (KGs) to improve Knowledge Graph Embedding (KGE) have obtained good performance for entities that co-occur in sentences…
Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings
Danushka Bollegala
Given multiple source word embeddings learnt using diverse algorithms and lexical resources, meta word embedding learning methods attempt to learn more accurate and wide-coverage w…
Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy
Yi Zhou, Danushka Bollegala
Contextualised word embeddings generated from Neural Language Models (NLMs), such as BERT, represent a word with a vector that considers the semantics of the target word as well it…
RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding
Danushka Bollegala, Huda Hakami, Yuichi Yoshida +1
Embedding entities and relations of a knowledge graph in a low-dimensional space has shown impressive performance in predicting missing links between entities. Although progresses…
Dictionary-based Debiasing of Pre-trained Word Embeddings
Masahiro Kaneko, Danushka Bollegala
Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionar…
Debiasing Pre-trained Contextualised Embeddings
Masahiro Kaneko, Danushka Bollegala
In comparison to the numerous debiasing methods proposed for the static non-contextualised word embeddings, the discriminative biases in contextualised embeddings have received rel…
-Neighbor Based Curriculum Sampling for Sequence Prediction
James O' Neill, Danushka Bollegala
Multi-step ahead prediction in language models is challenging due to the discrepancy between training and test time processes. At test time, a sequence predictor is required to mak…
Autoencoding Improves Pre-trained Word Embeddings
Masahiro Kaneko, Danushka Bollegala
Prior work investigating the geometry of pre-trained word embeddings have shown that word embeddings to be distributed in a narrow cone and by centering and projecting using princi…
Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents
Asir Saeed, Khai Mai, Pham Minh +2
Dialogue engines that incorporate different types of agents to converse with humans are popular. However, conversations are dynamic in the sense that a selected response will chang…
Contextualised Graph Attention for Improved Relation Extraction
Angrosh Mandya, Danushka Bollegala, Frans Coenen
This paper presents a contextualized graph attention network that combines edge features and multiple sub-graphs for improving relation extraction. A novel method is proposed to us…
Multi-source Attention for Unsupervised Domain Adaptation
Xia Cui, Danushka Bollegala
Domain adaptation considers the problem of generalising a model learnt using data from a particular source domain to a different target domain. Often it is difficult to find a suit…
Language-Independent Tokenisation Rivals Language-Specific Tokenisation for Word Similarity Prediction
Danushka Bollegala, Ryuichi Kiryo, Kosuke Tsujino +1
Language-independent tokenisation (LIT) methods that do not require labelled language resources or lexicons have recently gained popularity because of their applicability in resour…
Query Obfuscation Semantic Decomposition
Danushka Bollegala, Tomoya Machide, Ken-ichi Kawarabayashi
We propose a method to protect the privacy of search engine users by decomposing the queries using semantically \emph{related} and unrelated \emph{distractor} terms. Instead of a s…
Gender-preserving Debiasing for Pre-trained Word Embeddings
Masahiro Kaneko, Danushka Bollegala
Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the d…
Multi-Task Learning with Contextualized Word Representations for Extented Named Entity Recognition
Thai-Hoang Pham, Khai Mai, Nguyen Minh Trung +4
Fine-Grained Named Entity Recognition (FG-NER) is critical for many NLP applications. While classical named entity recognition (NER) has attracted a substantial amount of research,…
Analysing Dropout and Compounding Errors in Neural Language Models
James O' Neill, Danushka Bollegala
This paper carries out an empirical analysis of various dropout techniques for language modelling, such as Bernoulli dropout, Gaussian dropout, Curriculum Dropout, Variational Drop…
Meta-Embedding as Auxiliary Task Regularization
James O' Neill, Danushka Bollegala
Word embeddings have been shown to benefit from ensambling several word embedding sources, often carried out using straightforward mathematical operations over the set of word vect…
Angular-Based Word Meta-Embedding Learning
James O' Neill, Danushka Bollegala
Ensembling word embeddings to improve distributed word representations has shown good success for natural language processing tasks in recent years. These approaches either carry o…
Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings
Joshua Coates, Danushka Bollegala
Creating accurate meta-embeddings from pre-trained source embeddings has received attention lately. Methods based on global and locally-linear transformation and concatenation have…
ClassiNet -- Predicting Missing Features for Short-Text Classification
Danushka Bollegala, Vincent Atanasov, Takanori Maehara +1
The fundamental problem in short-text classification is \emph{feature sparseness} -- the lack of feature overlap between a trained model and a test instance to be classified. We pr…
Think Globally, Embed Locally --- Locally Linear Meta-embedding of Words
Danushka Bollegala, Kohei Hayashi, Ken-ichi Kawarabayashi
Distributed word embeddings have shown superior performances in numerous Natural Language Processing (NLP) tasks. However, their performances vary significantly across different ta…
Using -way Co-occurrences for Learning Word Embeddings
Danushka Bollegala, Yuichi Yoshida, Ken-ichi Kawarabayashi
Co-occurrences between two words provide useful insights into the semantics of those words. Consequently, numerous prior work on word embedding learning have used co-occurrences be…