arXiv subjects

Wilker Aziz

Publications and source records attributed to Wilker Aziz.

At least 37 records · Page 2Linked to original sources

arXiv2021

Editing Factual Knowledge in Language Models

The factual knowledge acquired during pre-training and stored in the parameters of Language Models (LMs) can be useful in downstream tasks (e.g., question answering or textual inference). However, some facts can be incorrectly induced or become obsolete over time. 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. Besides being computationally efficient, KnowledgeEditordoes not require any modifications in LM pre-training (e.g., the use of meta-learning). In our approach, we train a hyper-network with constrained optimization to modify a fact without affecting the rest of the knowledge; the trained hyper-network is then used to predict the weight update at test time. We show KnowledgeEditor's efficacy with two popular architectures and knowledge-intensive tasks: i) a BERT model fine-tuned for fact-checking, and ii) a sequence-to-sequence BART model for question answering. With our method, changing a prediction on the specific wording of a query tends to result in a consistent change in predictions also for its paraphrases. We show that this can be further encouraged by exploiting (e.g., automatically-generated) paraphrases during training. Interestingly, our hyper-network can be regarded as a 'probe' revealing which components need to be changed to manipulate factual knowledge; our analysis shows that the updates tend to be concentrated on a small subset of components. Source code available at https://github.com/nicola-decao/KnowledgeEditor

cs.CL↗

arXiv2021

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). However, the previously proposed autoregressive formulation for EL suffers from i) high computational cost due to a complex (deep) decoder, ii) non-parallelizable decoding that scales with the source sequence length, and iii) the need for training on a large amount of data. In this work, we propose a very efficient approach that parallelizes autoregressive linking across all potential mentions and relies on a shallow and efficient decoder. Moreover, we augment the generative objective with an extra discriminative component, i.e., a correction term which lets us directly optimize the generator's ranking. When taken together, these techniques tackle all the above issues: our model is >70 times faster and more accurate than the previous generative method, outperforming state-of-the-art approaches on the standard English dataset AIDA-CoNLL. Source code available at https://github.com/nicola-decao/efficient-autoregressive-EL

cs.CL↗

arXiv2021

How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking

Attribution methods assess the contribution of inputs to the model prediction. One way to do so is erasure: a subset of inputs is considered irrelevant if it can be removed without affecting the prediction. Though conceptually simple, erasure's objective is intractable and approximate search remains expensive with modern deep NLP models. Erasure is also susceptible to the hindsight bias: the fact that an input can be dropped does not mean that the model `knows' it can be dropped. The resulting pruning is over-aggressive and does not reflect how the model arrives at the prediction. To deal with these challenges, we introduce Differentiable Masking. DiffMask learns to mask-out subsets of the input while maintaining differentiability. The decision to include or disregard an input token is made with a simple model based on intermediate hidden layers of the analyzed model. First, this makes the approach efficient because we predict rather than search. Second, as with probing classifiers, this reveals what the network `knows' at the corresponding layers. This lets us not only plot attribution heatmaps but also analyze how decisions are formed across network layers. We use DiffMask to study BERT models on sentiment classification and question answering.

cs.CL↗

arXiv2020

Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically resorts to sampling-based approximations of the true marginal, requiring noisy gradient estimators (e.g., score function estimator) or continuous relaxations with lower-variance reparameterized gradients (e.g., Gumbel-Softmax). In this paper, we propose a new training strategy which replaces these estimators by an exact yet efficient marginalization. To achieve this, we parameterize discrete distributions over latent assignments using differentiable sparse mappings: sparsemax and its structured counterparts. In effect, the support of these distributions is greatly reduced, which enables efficient marginalization. We report successful results in three tasks covering a range of latent variable modeling applications: a semisupervised deep generative model, a latent communication game, and a generative model with a bit-vector latent representation. In all cases, we obtain good performance while still achieving the practicality of sampling-based approximations.

cs.LG↗

arXiv2020

Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation

Recent studies have revealed a number of pathologies of neural machine translation (NMT) systems. Hypotheses explaining these mostly suggest there is something fundamentally wrong with NMT as a model or its training algorithm, maximum likelihood estimation (MLE). Most of this evidence was gathered using maximum a posteriori (MAP) decoding, a decision rule aimed at identifying the highest-scoring translation, i.e. the mode. We argue that the evidence corroborates the inadequacy of MAP decoding more than casts doubt on the model and its training algorithm. In this work, we show that translation distributions do reproduce various statistics of the data well, but that beam search strays from such statistics. We show that some of the known pathologies and biases of NMT are due to MAP decoding and not to NMT's statistical assumptions nor MLE. In particular, we show that the most likely translations under the model accumulate so little probability mass that the mode can be considered essentially arbitrary. We therefore advocate for the use of decision rules that take into account the translation distribution holistically. We show that an approximation to minimum Bayes risk decoding gives competitive results confirming that NMT models do capture important aspects of translation well in expectation.

cs.CL↗

arXiv2020

Disease Normalization with Graph Embeddings

The detection and normalization of diseases in biomedical texts are key biomedical natural language processing tasks. Disease names need not only be identified, but also normalized or linked to clinical taxonomies describing diseases such as MeSH. In this paper we describe deep learning methods that tackle both tasks. We train and test our methods on the known NCBI disease benchmark corpus. We propose to represent disease names by leveraging MeSH's graphical structure together with the lexical information available in the taxonomy using graph embeddings. We also show that combining neural named entity recognition models with our graph-based entity linking methods via multitask learning leads to improved disease recognition in the NCBI corpus.

cs.CL↗

arXiv2020

Interpretable Neural Predictions with Differentiable Binary Variables

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach this problem by jointly training two neural network models: a latent model that selects a rationale (i.e. a short and informative part of the input text), and a classifier that learns from the words in the rationale alone. Previous work proposed to assign binary latent masks to input positions and to promote short selections via sparsity-inducing penalties such as L0 regularisation. We propose a latent model that mixes discrete and continuous behaviour allowing at the same time for binary selections and gradient-based training without REINFORCE. In our formulation, we can tractably compute the expected value of penalties such as L0, which allows us to directly optimise the model towards a pre-specified text selection rate. We show that our approach is competitive with previous work on rationale extraction, and explore further uses in attention mechanisms.

cs.CL↗

arXiv2020

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. We rely on graph-convolutional networks (GCNs), a recent class of neural networks developed for modeling graph-structured data. Our GCNs use predicted syntactic dependency trees of source sentences to produce representations of words (i.e. hidden states of the encoder) that are sensitive to their syntactic neighborhoods. GCNs take word representations as input and produce word representations as output, so they can easily be incorporated as layers into standard encoders (e.g., on top of bidirectional RNNs or convolutional neural networks). We evaluate their effectiveness with English-German and English-Czech translation experiments for different types of encoders and observe substantial improvements over their syntax-agnostic versions in all the considered setups.

cs.CL↗

arXiv2020

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). In this work we investigate a more challenging setup: we incorporate sentence structure as a latent variable in a standard NMT encoder-decoder and induce it in such a way as to benefit the translation task. We consider German-English and Japanese-English translation benchmarks and observe that when using RNN encoders the model makes no or very limited use of the structure induction apparatus. In contrast, CNN and word-embedding-based encoders rely on latent graphs and force them to encode useful, potentially long-distance, dependencies.

cs.CL↗

arXiv2020

The Power Spherical distribution

There is a growing interest in probabilistic models defined in hyper-spherical spaces, be it to accommodate observed data or latent structure. The von Mises-Fisher (vMF) distribution, often regarded as the Normal distribution on the hyper-sphere, is a standard modeling choice: it is an exponential family and thus enjoys important statistical results, for example, known Kullback-Leibler (KL) divergence from other vMF distributions. Sampling from a vMF distribution, however, requires a rejection sampling procedure which besides being slow poses difficulties in the context of stochastic backpropagation via the reparameterization trick. Moreover, this procedure is numerically unstable for certain vMFs, e.g., those with high concentration and/or in high dimensions. 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). We demonstrate the stability of Power Spherical distributions with a numerical experiment and further apply it to a variational auto-encoder trained on MNIST. Code at: https://github.com/nicola-decao/power_spherical

stat.ML↗

arXiv2020

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. Having a neural network architecture predict discrete parameters takes a non-differentiable activation function (eg, the step function) which precludes gradient-based learning. To circumvent this non-differentiability, previous work has employed biased proxy gradients, such as the straight-through estimator. We present an unbiased alternative where rather than deterministically parameterising one transformation, we predict a distribution over latent transformations. With stochastic transformations, the marginal likelihood of the data is differentiable and gradient-based learning is possible via score function estimation. To test the viability of discrete-data NFs we investigate performance on binary MNIST. We observe great challenges with both deterministic proxy gradients and unbiased score function estimation. Whereas the former often fails to learn even a shallow transformation, the variance of the latter could not be sufficiently controlled to admit deeper NFs.

cs.LG↗

arXiv2020

Effective Estimation of Deep Generative Language Models

Advances in variational inference enable parameterisation of probabilistic models by deep neural networks. This combines the statistical transparency of the probabilistic modelling framework with the representational power of deep learning. Yet, due to a problem known as posterior collapse, it is difficult to estimate such models in the context of language modelling effectively. We concentrate on one such model, the variational auto-encoder, which we argue is an important building block in hierarchical probabilistic models of language. This paper contributes a sober view of the problem, a survey of techniques to address it, novel techniques, and extensions to the model. To establish a ranking of techniques, we perform a systematic comparison using Bayesian optimisation and find that many techniques perform reasonably similar, given enough resources. Still, a favourite can be named based on convenience. We also make several empirical observations and recommendations of best practices that should help researchers interested in this exciting field.

cs.CL↗

arXiv2020

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. This problem is typically addressed by either pre-processing words into subword units or performing translation directly at the level of characters. The former is based on word segmentation algorithms optimized using corpus-level statistics with no regard to the translation task. The latter learns directly from translation data but requires rather deep architectures. In this paper, we propose to translate words by modeling word formation through a hierarchical latent variable model which mimics the process of morphological inflection. Our model generates words one character at a time by composing two latent representations: a continuous one, aimed at capturing the lexical semantics, and a set of (approximately) discrete features, aimed at capturing the morphosyntactic function, which are shared among different surface forms. Our model achieves better accuracy in translation into three morphologically-rich languages than conventional open-vocabulary NMT methods, while also demonstrating a better generalization capacity under low to mid-resource settings.

cs.CL↗

arXiv2019

Auto-Encoding Variational Neural Machine Translation

We present a deep generative model of bilingual sentence pairs for machine translation. The model generates source and target sentences jointly from a shared latent representation and is parameterised by neural networks. We perform efficient training using amortised variational inference and reparameterised gradients. Additionally, we discuss the statistical implications of joint modelling and propose an efficient approximation to maximum a posteriori decoding for fast test-time predictions. We demonstrate the effectiveness of our model in three machine translation scenarios: in-domain training, mixed-domain training, and learning from a mix of gold-standard and synthetic data. Our experiments show consistently that our joint formulation outperforms conditional modelling (i.e. standard neural machine translation) in all such scenarios.

cs.CL↗

arXiv2019

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. This latent variable can be seen as a multi-modal stochastic embedding of an image and its description in a foreign language. It is used in a target-language decoder and also to predict image features. Importantly, our model formulation utilises visual and textual inputs during training but does not require that images be available at test time. We show that our latent variable MMT formulation improves considerably over strong baselines, including a multi-task learning approach (Elliott and Kádár, 2017) and a conditional variational auto-encoder approach (Toyama et al., 2016). Finally, we show improvements due to (i) predicting image features in addition to only conditioning on them, (ii) imposing a constraint on the minimum amount of information encoded in the latent variable, and (iii) by training on additional target-language image descriptions (i.e. synthetic data).

cs.CL↗

arXiv2019

Block Neural Autoregressive Flow

Normalising flows (NFS) map two density functions via a differentiable bijection whose Jacobian determinant can be computed efficiently. 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. Their flow is a neural network (NN) whose parameters are predicted by another NN. The latter grows quadratically with the size of the former and thus an efficient technique for parametrization is needed. We propose block neural autoregressive flow (B-NAF), a much more compact universal approximator of density functions, where we model a bijection directly using a single feed-forward network. Invertibility is ensured by carefully designing each affine transformation with block matrices that make the flow autoregressive and (strictly) monotone. We compare B-NAF to NAF and other established flows on density estimation and approximate inference for latent variable models. Our proposed flow is competitive across datasets while using orders of magnitude fewer parameters.

stat.ML↗

arXiv2018

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. This gives rise to significant variation in parallel cor- pora, however, most current models of machine translation do not account for this variation, instead treating the prob- lem as a deterministic process. To this end, we present a deep generative model of machine translation which incorporates a chain of latent variables, in order to ac- count for local lexical and syntactic varia- tion in parallel corpora. We provide an in- depth analysis of the pitfalls encountered in variational inference for training deep generative models. Experiments on sev- eral different language pairs demonstrate that the model consistently improves over strong baselines.

stat.ML↗

arXiv2018

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. In particular, we exploit equivalence through translation as a form of distributed context and jointly learn how to embed and align with a deep generative model. Our EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments. Besides, it embeds words as posterior probability densities, rather than point estimates, which allows us to compare words in context using a measure of overlap between distributions (e.g. KL divergence). We investigate our model's performance on a range of lexical semantics tasks achieving competitive results on several standard benchmarks including natural language inference, paraphrasing, and text similarity.

cs.CL↗