Search Results for author:
Found 26 papers, 11 papers with code
A Sequence Modelling Approach to Question Answering in Text-Based Games
Interactive Question Answering (IQA) requires an intelligent agent to interact with a dynamic environment in order to gather information necessary to answer a question.
RepGraph: Visualising and Analysing Meaning Representation Graphs
We present RepGraph, an open source visualisation and analysis tool for meaning representation graphs.
Generic Overgeneralization in Pre-trained Language Models
The generic overgeneralization effect refers to the inclination to accept false universal generalizations such as “all ducks lay eggs” or “all lions have manes” as true.
A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation
Multilingual modelling can improve machine translation for low-resource languages, partly through shared subword representations.
Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation
In this paper we tackle data-to-text for isiXhosa, which is low-resource and agglutinative.
Multipath parsing in the brain
Humans understand sentences word-by-word, in the order that they hear them.
Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation
We propose a departure from this paradigm, called subword segmental machine translation (SSMT).
University of Cape Town's WMT22 System: Multilingual Machine Translation for Southern African Languages
The paper describes the University of Cape Town's submission to the constrained track of the WMT22 Shared Task: Large-Scale Machine Translation Evaluation for African Languages.
Subword Segmental Language Modelling for Nguni Languages
We also train our model as a word-level sequence model, resulting in an unsupervised morphological segmenter that outperforms existing methods by a large margin for all 4 languages.
Low-Resource Language Modelling of South African Languages
Language models are the foundation of current neural network-based models for natural language understanding and generation.
Canonical and Surface Morphological Segmentation for Nguni Languages
In this paper, we investigate supervised and unsupervised models for two variants of morphological segmentation: canonical and surface segmentation.
BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle
In this paper, we propose a novel approach to unsupervised sentence summarization by mapping the Information Bottleneck principle to a conditional language modelling objective: given a sentence, our approach seeks a compressed sentence that can best predict the next sentence.
Discourse Understanding and Factual Consistency in Abstractive Summarization
We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary.
Benchmarking Hierarchical Script Knowledge
Understanding procedural language requires reasoning about both hierarchical and temporal relations between events.
Neural Text Generation from Rich Semantic Representations
We propose neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS).
The Curious Case of Neural Text Degeneration
Despite considerable advancements with deep neural language models, the enigma of neural text degeneration persists when these models are tested as text generators.
Neural Syntactic Generative Models with Exact Marginalization
We present neural syntactic generative models with exact marginalization that support both dependency parsing and language modeling.
Learning to Write with Cooperative Discriminators
Recurrent Neural Networks (RNNs) are powerful autoregressive sequence models, but when used to generate natural language their output tends to be overly generic, repetitive, and self-contradictory.
Learning to Write by Learning the Objective
Human evaluation demonstrates that text generated by the resulting generator is preferred over that of baselines by a large margin and significantly enhances the overall coherence, style, and information content of the generated text.
Oxford at SemEval-2017 Task 9: Neural AMR Parsing with Pointer-Augmented Attention
We present a neural encoder-decoder AMR parser that extends an attention-based model by predicting the alignment between graph nodes and sentence tokens explicitly with a pointer mechanism.
Ranked #27 on
AMR Parsing
on LDC2017T10
Robust Incremental Neural Semantic Graph Parsing
Parsing sentences to linguistically-expressive semantic representations is a key goal of Natural Language Processing.
Online Segment to Segment Neural Transduction
We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read.
Cross-Lingual Morphological Tagging for Low-Resource Languages
We propose a tagging model using Wsabie, a discriminative embedding-based model with rank-based learning.
A Bayesian Model for Generative Transition-based Dependency Parsing
We propose a simple, scalable, fully generative model for transition-based dependency parsing with high accuracy.
