Search Results for author:
Found 46 papers, 23 papers with code
GoURMET – Machine Translation for Low-Resourced Languages
The GoURMET project, funded by the European Commission’s H2020 program (under grant agreement 825299), develops models for machine translation, in particular for low-resourced languages.
Surprise Language Challenge: Developing a Neural Machine Translation System between Pashto and English in Two Months
We find that starting from an existing large model pre-trained on 50languages leads to far better BLEU scores than pretraining on one high-resource language pair with a smaller model.
Explanation Regularisation through the Lens of Attributions
Explanation regularisation (ER) has been introduced as a way to guide models to make their predictions in a manner more akin to humans, i. e., making their attributions "plausible".
Predict the Next Word: Humans exhibit uncertainty in this task and language models _____
This can be seen as assessing a form of calibration, which, in the context of text classification, Baan et al. (2022) termed calibration to human uncertainty.
Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?
With the rise of increasingly powerful and user-facing NLP systems, there is growing interest in assessing whether they have a good representation of uncertainty by evaluating the quality of their predictive distribution over outcomes.
Uncertainty in Natural Language Generation: From Theory to Applications
Recent advances of powerful Language Models have allowed Natural Language Generation (NLG) to emerge as an important technology that can not only perform traditional tasks like summarisation or translation, but also serve as a natural language interface to a variety of applications.
What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability
In Natural Language Generation (NLG) tasks, for any input, multiple communicative goals are plausible, and any goal can be put into words, or produced, in multiple ways.
VISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking
The lack of interpretability of the Vision Transformer may hinder its use in critical real-world applications despite its effectiveness.
Stop Measuring Calibration When Humans Disagree
Calibration is a popular framework to evaluate whether a classifier knows when it does not know - i. e., its predictive probabilities are a good indication of how likely a prediction is to be correct.
Statistical Model Criticism of Variational Auto-Encoders
We propose a framework for the statistical evaluation of variational auto-encoders (VAEs) and test two instances of this framework in the context of modelling images of handwritten digits and a corpus of English text.
Highly Parallel Autoregressive Entity Linking with Discriminative Correction
Generative approaches have been recently shown to be effective for both Entity Disambiguation and Entity Linking (i. e., joint mention detection and disambiguation).
Ranked #5 on
Entity Linking
on AIDA-CoNLL
Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
The mode and other high-probability translations found by beam search have been shown to often be inadequate in a number of ways.
Sparse Communication via Mixed Distributions
Neural networks and other machine learning models compute continuous representations, while humans communicate mostly through discrete symbols.
Editing Factual Knowledge in Language Models
We present KnowledgeEditor, a method which can be used to edit this knowledge and, thus, fix 'bugs' or unexpected predictions without the need for expensive re-training or fine-tuning.
Disease Normalization with Graph Embeddings
The detection and normalization of diseases in biomedical texts are key biomedical natural language processing tasks.
Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
In this paper, we propose a new training strategy which replaces these estimators by an exact yet efficient marginalization.
Latent Transformations for Discrete-Data Normalising Flows
Normalising flows (NFs) for discrete data are challenging because parameterising bijective transformations of discrete variables requires predicting discrete/integer parameters.
The Power Spherical distribution
We propose a novel distribution, the Power Spherical distribution, which retains some of the important aspects of the vMF (e. g., support on the hyper-sphere, symmetry about its mean direction parameter, known KL from other vMF distributions) while addressing its main drawbacks (i. e., scalability and numerical stability).
Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation
We argue that the evidence corroborates the inadequacy of MAP decoding more than casts doubt on the model and its training algorithm.
How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking
Attribution methods assess the contribution of inputs to the model prediction.
A Latent Morphology Model for Open-Vocabulary Neural Machine Translation
Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic.
Interpretable Neural Predictions with Differentiable Binary Variables
The success of neural networks comes hand in hand with a desire for more interpretability.
Effective Estimation of Deep Generative Language Models
We concentrate on one such model, the variational auto-encoder, which we argue is an important building block in hierarchical probabilistic models of language.
Block Neural Autoregressive Flow
Recently, as an alternative to hand-crafted bijections, Huang et al. (2018) proposed neural autoregressive flow (NAF) which is a universal approximator for density functions.
Ranked #1 on
Density Estimation
on UCI MINIBOONE
Modeling Latent Sentence Structure in Neural Machine Translation
Recently it was shown that linguistic structure predicted by a supervised parser can be beneficial for neural machine translation (NMT).
Latent Variable Model for Multi-modal Translation
In this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model.
Ranked #9 on
Multimodal Machine Translation
on Multi30K
Question Answering by Reasoning Across Documents with Graph Convolutional Networks
Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs.
Auto-Encoding Variational Neural Machine Translation
We present a deep generative model of bilingual sentence pairs for machine translation.
Variational Inference and Deep Generative Models
Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks.
A Stochastic Decoder for Neural Machine Translation
The process of translation is ambiguous, in that there are typically many valid trans- lations for a given sentence.
Deep Generative Model for Joint Alignment and Word Representation
This work exploits translation data as a source of semantically relevant learning signal for models of word representation.
Graph Convolutional Encoders for Syntax-aware Neural Machine Translation
We present a simple and effective approach to incorporating syntactic structure into neural attention-based encoder-decoder models for machine translation.
Fast Collocation-Based Bayesian HMM Word Alignment
In order to make our model useful in practice, we devise an auxiliary variable Gibbs sampler that allows us to resample alignment links in constant time independently of the target sentence length.
Cohere: A Toolkit for Local Coherence
We describe COHERE, our coherence toolkit which incorporates various complementary models for capturing and measuring different aspects of text coherence.
The USFD Spoken Language Translation System for IWSLT 2014
The USFD primary system incorporates state-of-the-art ASR and MT techniques and gives a BLEU score of 23. 45 and 14. 75 on the English-to-French and English-to-German speech-to-text translation task with the IWSLT 2014 data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
PET: a Tool for Post-editing and Assessing Machine Translation
Given the significant improvements in Machine Translation (MT) quality and the increasing demand for translations, post-editing of automatic translations is becoming a popular practice in the translation industry.
