Search Results for author:
Found 20 papers, 2 papers with code
Synthetic, yet natural: Properties of WordNet random walk corpora and the impact of rare words on embedding performance
Creating word embeddings that reflect semantic relationships encoded in lexical knowledge resources is an open challenge.
Finding BERT’s Idiomatic Key
Sentence embeddings encode information relating to the usage of idioms in a sentence.
Poisoning Knowledge Graph Embeddings via Relation Inference Patterns
We study the problem of generating data poisoning attacks against Knowledge Graph Embedding (KGE) models for the task of link prediction in knowledge graphs.
Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods
These attacks craft adversarial additions or deletions at training time to cause model failure at test time.
Style versus Content: A distinction without a (learnable) difference?
Due to the lack of parallel data for style transfer we employ a variety of adversarial encoder-decoder networks in our experiments.
English WordNet Random Walk Pseudo-Corpora
Our WordNet taxonomic random walk implementation allows the exploration of different random walk hyperparameters and the generation of a variety of different pseudo-corpora.
Persistence pays off: Paying Attention to What the LSTM Gating Mechanism Persists
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.
Energy-Based Modelling for Dialogue State Tracking
The uncertainties of language and the complexity of dialogue contexts make accurate dialogue state tracking one of the more challenging aspects of dialogue processing.
Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network
We present an instance segmentation algorithm trained and applied to a CCTV recording of beef cattle during a winter finishing period.
Exploring the Functional and Geometric Bias of Spatial Relations Using Neural Language Models
The challenge for computational models of spatial descriptions for situated dialogue systems is the integration of information from different modalities.
Attentive Language Models
In this paper, we extend Recurrent Neural Network Language Models (RNN-LMs) with an attention mechanism.
Idiom Type Identification with Smoothed Lexical Features and a Maximum Margin Classifier
In our work we address limitations in the state-of-the-art in idiom type identification.
Bootstrapping Labelled Dataset Construction for Cow Tracking and Behavior Analysis
This paper introduces a new approach to the long-term tracking of an object in a challenging environment.
