no code implementations • GWC 2019 • Filip Klubička, Alfredo Maldonado, Abhijit Mahalunkar, John Kelleher
Creating word embeddings that reflect semantic relationships encoded in lexical knowledge resources is an open challenge.
no code implementations • ACL (MWE) 2021 • Vasudevan Nedumpozhimana, John Kelleher
Sentence embeddings encode information relating to the usage of idioms in a sentence.
1 code implementation • ACL 2021 • Peru Bhardwaj, John Kelleher, Luca Costabello, Declan O'Sullivan
We study the problem of generating data poisoning attacks against Knowledge Graph Embedding (KGE) models for the task of link prediction in knowledge graphs.
1 code implementation • EMNLP 2021 • Peru Bhardwaj, John Kelleher, Luca Costabello, Declan O'Sullivan
These attacks craft adversarial additions or deletions at training time to cause model failure at test time.
no code implementations • COLING 2020 • Somayeh Jafaritazehjani, Gw{\'e}nol{\'e} Lecorv{\'e}, Damien Lolive, John Kelleher
Due to the lack of parallel data for style transfer we employ a variety of adversarial encoder-decoder networks in our experiments.
no code implementations • LREC 2020 • Filip Klubi{\v{c}}ka, Alfredo Maldonado, Abhijit Mahalunkar, John Kelleher
Our WordNet taxonomic random walk implementation allows the exploration of different random walk hyperparameters and the generation of a variety of different pseudo-corpora.
no code implementations • RANLP 2019 • Giancarlo Salton, John Kelleher
Recurrent Neural Network Language Models composed of LSTM units, especially those augmented with an external memory, have achieved state-of-the-art results in Language Modeling.
no code implementations • WS 2019 • Anh Duong Trinh, Robert Ross, John Kelleher
The uncertainties of language and the complexity of dialogue contexts make accurate dialogue state tracking one of the more challenging aspects of dialogue processing.
no code implementations • 5 Jul 2018 • Aram Ter-Sarkisov, Robert Ross, John Kelleher, Bernadette Earley, Michael Keane
We present an instance segmentation algorithm trained and applied to a CCTV recording of beef cattle during a winter finishing period.
no code implementations • WS 2018 • Simon Dobnik, Mehdi Ghanimifard, John Kelleher
The challenge for computational models of spatial descriptions for situated dialogue systems is the integration of information from different modalities.
no code implementations • IJCNLP 2017 • Giancarlo Salton, Robert Ross, John Kelleher
In this paper, we extend Recurrent Neural Network Language Models (RNN-LMs) with an attention mechanism.
no code implementations • RANLP 2017 • Giancarlo Salton, Robert Ross, John Kelleher
In our work we address limitations in the state-of-the-art in idiom type identification.
no code implementations • 30 Mar 2017 • Aram Ter-Sarkisov, Robert Ross, John Kelleher
This paper introduces a new approach to the long-term tracking of an object in a challenging environment.