Search

We scale perceived distances of the core-set algorithm by a factor of uncertainty and search for low-confidence configurations, finding significant improvements in sample efficiency across CIFAR10/100 and SVHN image classification, especially in larger acquisition sizes. We show the necessity of our modifications and explain how the improvement is due to a probabilistic quadratic speed-up in the convergence of core-set loss, under assumptions about the relationship of model uncertainty and misclassification.

Large pretrained language models (LMs) like BERT have improved performance in many disparate natural language processing (NLP) tasks. However, fine tuning such models requires a large number of training examples for each target task. Simultaneously, many realistic NLP problems are "few shot", without a sufficiently large training set. In this work, we propose a novel conditional neural process-based approach for few-shot text classification that learns to transfer from other diverse tasks with rich annotation. Our key idea is to represent each task using gradient information from a base model and to train an adaptation network that modulates a text classifier conditioned on the task representation. While previous task-aware few-shot learners represent tasks by input encoding, our novel task representation is more powerful, as the gradient captures input-output relationships of a task. Experimental results show that our approach outperforms traditional fine-tuning, sequential transfer learning, and state-of-the-art meta learning approaches on a collection of diverse few-shot tasks. We further conducted analysis and ablations to justify our design choices., Comment: NeurIPS 2021

Recently, neural natural language models have attained state-of-the-art performance on a wide variety of tasks, but the high performance can result from superficial, surface-level cues (Bender and Koller, 2020; Niven and Kao, 2020). These surface cues, as the ``shortcuts'' inherent in the datasets, do not contribute to the *task-specific information* (TSI) of the classification tasks. While it is essential to look at the model performance, it is also important to understand the datasets. In this paper, we consider this question: Apart from the information introduced by the shortcut features, how much task-specific information is required to classify a dataset? We formulate this quantity in an information-theoretic framework. While this quantity is hard to compute, we approximate it with a fast and stable method. TSI quantifies the amount of linguistic knowledge modulo a set of predefined shortcuts -- that contributes to classifying a sample from each dataset. This framework allows us to compare across datasets, saying that, apart from a set of ``shortcut features'', classifying each sample in the Multi-NLI task involves around 0.4 nats more TSI than in the Quora Question Pair.

We consider language modelling (LM) as a multi-label structured prediction task by re-framing training from solely predicting a single ground-truth word to ranking a set of words which could continue a given context. To avoid annotating top-$k$ ranks, we generate them using pre-trained LMs: GPT-2, BERT, and Born-Again models. This leads to a rank-based form of knowledge distillation (KD). We also develop a method using $N$-grams to create a non-probabilistic teacher which generates the ranks without the need of a pre-trained LM. We confirm the hypotheses that we can treat LMing as a ranking task and that we can do so without the use of a pre-trained LM. We show that rank-based KD generally improves perplexity (PPL), often with statistical significance, when compared to Kullback-Leibler-based KD. Surprisingly, given the simplicity of the method, $N$-grams act as competitive teachers and achieve similar performance as using either BERT or a Born-Again model teachers. GPT-2 always acts as the best teacher, though, and using it and a Transformer-XL student on Wiki-02, rank-based KD reduces a cross-entropy baseline from 65.27 to 55.94 and against a KL-based KD of 56.70., Comment: Accepted to AAAI22. Minor writing fixes

Morality plays an important role in social well-being, but people's moral perception is not stable and changes over time. Recent advances in natural language processing have shown that text is an effective medium for informing moral change, but no attempt has been made to quantify the origins of these changes. We present a novel unsupervised framework for tracing textual sources of moral change toward entities through time. We characterize moral change with probabilistic topical distributions and infer the source text that exerts prominent influence on the moral time course. We evaluate our framework on a diverse set of data ranging from social media to news articles. We show that our framework not only captures fine-grained human moral judgments, but also identifies coherent source topics of moral change triggered by historical events. We apply our methodology to analyze the news in the COVID-19 pandemic and demonstrate its utility in identifying sources of moral change in high-impact and real-time social events.

As the numbers of submissions to conferences grow quickly, the task of assessing the quality of academic papers automatically, convincingly, and with high accuracy attracts increasing attention. We argue that studying interpretable dimensions of these submissions could lead to scalable solutions. We extract a collection of writing features, and construct a suite of prediction tasks to assess the usefulness of these features in predicting citation counts and the publication of AI-related papers. Depending on the venues, the writing features can predict the conference vs. workshop appearance with F1 scores up to 60-90, sometimes even outperforming the content-based tf-idf features and RoBERTa. We show that the features describe writing style more than content. To further understand the results, we estimate the causal impact of the most indicative features. Our analysis on writing features provides a perspective to assessing and refining the writing of academic articles at scale., Comment: 15 pages, 4 figures

Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly. In this work, we use Gaussian models for density estimation at intermediate layers of three language models (BERT, RoBERTa, and XLNet), and evaluate our method on BLiMP, a grammaticality judgement benchmark. In lower layers, surprisal is highly correlated to low token frequency, but this correlation diminishes in upper layers. Next, we gather datasets of morphosyntactic, semantic, and commonsense anomalies from psycholinguistic studies; we find that the best performing model RoBERTa exhibits surprisal in earlier layers when the anomaly is morphosyntactic than when it is semantic, while commonsense anomalies do not exhibit surprisal at any intermediate layer. These results suggest that language models employ separate mechanisms to detect different types of linguistic anomalies., Comment: ACL 2021 (Long Paper)

Eye movement data during reading is a useful source of information for understanding language comprehension processes. In this paper, we describe our submission to the CMCL 2021 shared task on predicting human reading patterns. Our model uses RoBERTa with a regression layer to predict 5 eye-tracking features. We train the model in two stages: we first fine-tune on the Provo corpus (another eye-tracking dataset), then fine-tune on the task data. We compare different Transformer models and apply ensembling methods to improve the performance. Our final submission achieves a MAE score of 3.929, ranking 3rd place out of 13 teams that participated in this shared task., Comment: Cognitive Modeling and Computational Linguistics Workshop (CMCL) at NAACL 2021

Automatically evaluating text-based, non-task-oriented dialogue systems (i.e., `chatbots') remains an open problem. Previous approaches have suffered challenges ranging from poor correlation with human judgment to poor generalization and have often required a gold standard reference for comparison or human-annotated data. Extending existing evaluation methods, we propose that a metric based on linguistic features may be able to maintain good correlation with human judgment and be interpretable, without requiring a gold-standard reference or human-annotated data. To support this proposition, we measure and analyze various linguistic features on dialogues produced by multiple dialogue models. We find that the features' behaviour is consistent with the known properties of the models tested, and is similar across domains. We also demonstrate that this approach exhibits promising properties such as zero-shot generalization to new domains on the related task of evaluating response relevance.

Many healthcare decisions involve navigating through a multitude of treatment options in a sequential and iterative manner to find an optimal treatment pathway with the goal of an optimal patient outcome. Such optimization problems may be amenable to reinforcement learning. A reinforcement learning agent could be trained to provide treatment recommendations for physicians, acting as a decision support tool. However, a number of difficulties arise when using RL beyond benchmark environments, such as specifying the reward function, choosing an appropriate state representation and evaluating the learned policy.

Speaker attribution is required in many real-world applications, such as meeting transcription, where speaker identity is assigned to each utterance according to speaker voice profiles. In this paper, we propose to solve the speaker attribution problem by using graph-based semi-supervised learning methods. A graph of speech segments is built for each session, on which segments from voice profiles are represented by labeled nodes while segments from test utterances are unlabeled nodes. The weight of edges between nodes is evaluated by the similarities between the pretrained speaker embeddings of speech segments. Speaker attribution then becomes a semi-supervised learning problem on graphs, on which two graph-based methods are applied: label propagation (LP) and graph neural networks (GNNs). The proposed approaches are able to utilize the structural information of the graph to improve speaker attribution performance. Experimental results on real meeting data show that the graph based approaches reduce speaker attribution error by up to 68% compared to a baseline speaker identification approach that processes each utterance independently., Comment: Interspeech 2020

Deep neural networks (DNNs) used for brain-computer-interface (BCI) classification are commonly expected to learn general features when trained across a variety of contexts, such that these features could be fine-tuned to specific contexts. While some success is found in such an approach, we suggest that this interpretation is limited and an alternative would better leverage the newly (publicly) available massive EEG datasets. We consider how to adapt techniques and architectures used for language modelling (LM), that appear capable of ingesting awesome amounts of data, towards the development of encephalography modelling (EM) with DNNs in the same vein. We specifically adapt an approach effectively used for automatic speech recognition, which similarly (to LMs) uses a self-supervised training objective to learn compressed representations of raw data signals. After adaptation to EEG, we find that a single pre-trained model is capable of modelling completely novel raw EEG sequences recorded with differing hardware, and different subjects performing different tasks. Furthermore, both the internal representations of this model and the entire architecture can be fine-tuned to a variety of downstream BCI and EEG classification tasks, outperforming prior work in more task-specific (sleep stage classification) self-supervision.

Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext. We propose a novel task of exploring fairness on a multimodal clinical dataset, adopting equalized odds for the downstream medical prediction tasks. To this end, we investigate a modality-agnostic fairness algorithm - equalized odds post processing - and compare it to a text-specific fairness algorithm: debiased clinical word embeddings. Despite the fact that debiased word embeddings do not explicitly address equalized odds of protected groups, we show that a text-specific approach to fairness may simultaneously achieve a good balance of performance and classical notions of fairness. We hope that our paper inspires future contributions at the critical intersection of clinical NLP and fairness. The full source code is available here: https://github.com/johntiger1/multimodal_fairness, Comment: Best paper award at 3rd Clinical Natural Language Processing Workshop at EMNLP 2020

Semantic shifts can reflect changes in beliefs across hundreds of years, but it is less clear whether trends in fast-changing communities across a short time can be detected. We propose semantic coordinates analysis, a method based on semantic shifts, that reveals changes in language within publications of a field (we use AI as example) across a short time span. We use GloVe-style probability ratios to quantify the shifting directions and extents from multiple viewpoints. We show that semantic coordinates analysis can detect shifts echoing changes of research interests (e.g., "deep" shifted further from "rigorous" to "neural"), and developments of research activities (e,g., "collaboration" contains less "competition" than "collaboration"), based on publications spanning as short as 10 years., Comment: 15 pages, 5 figures

BERT set many state-of-the-art results over varied NLU benchmarks by pre-training over two tasks: masked language modelling (MLM) and next sentence prediction (NSP), the latter of which has been highly criticized. In this paper, we 1) clarify NSP's effect on BERT pre-training, 2) explore fourteen possible auxiliary pre-training tasks, of which seven are novel to modern language models, and 3) investigate different ways to include multiple tasks into pre-training. We show that NSP is detrimental to training due to its context splitting and shallow semantic signal. We also identify six auxiliary pre-training tasks -- sentence ordering, adjacent sentence prediction, TF prediction, TF-IDF prediction, a FastSent variant, and a Quick Thoughts variant -- that outperform a pure MLM baseline. Finally, we demonstrate that using multiple tasks in a multi-task pre-training framework provides better results than using any single auxiliary task. Using these methods, we outperform BERT Base on the GLUE benchmark using fewer than a quarter of the training tokens., Comment: Accepted to EMNLP 2020. 9 Pages + 3 Pages of References and Appendices (12 Pages total)

Recently, neural language models (LMs) have demonstrated impressive abilities in generating high-quality discourse. While many recent papers have analyzed the syntactic aspects encoded in LMs, there has been no analysis to date of the inter-sentential, rhetorical knowledge. In this paper, we propose a method that quantitatively evaluates the rhetorical capacities of neural LMs. We examine the capacities of neural LMs understanding the rhetoric of discourse by evaluating their abilities to encode a set of linguistic features derived from Rhetorical Structure Theory (RST). Our experiments show that BERT-based LMs outperform other Transformer LMs, revealing the richer discourse knowledge in their intermediate layer representations. In addition, GPT-2 and XLNet apparently encode less rhetorical knowledge, and we suggest an explanation drawing from linguistic philosophy. Our method shows an avenue towards quantifying the rhetorical capacities of neural LMs., Comment: EMNLP 2020 BlackboxNLP Workshop

Word class flexibility refers to the phenomenon whereby a single word form is used across different grammatical categories. Extensive work in linguistic typology has sought to characterize word class flexibility across languages, but quantifying this phenomenon accurately and at scale has been fraught with difficulties. We propose a principled methodology to explore regularity in word class flexibility. Our method builds on recent work in contextualized word embeddings to quantify semantic shift between word classes (e.g., noun-to-verb, verb-to-noun), and we apply this method to 37 languages. We find that contextualized embeddings not only capture human judgment of class variation within words in English, but also uncover shared tendencies in class flexibility across languages. Specifically, we find greater semantic variation when flexible lemmas are used in their dominant word class, supporting the view that word class flexibility is a directional process. Our work highlights the utility of deep contextualized models in linguistic typology., Comment: To appear in EMNLP 2020 (Long Paper)

There is increasing interest in assessing the linguistic knowledge encoded in neural representations. A popular approach is to attach a diagnostic classifier -- or "probe" -- to perform supervised classification from internal representations. However, how to select a good probe is in debate. Hewitt and Liang (2019) showed that a high performance on diagnostic classification itself is insufficient, because it can be attributed to either "the representation being rich in knowledge", or "the probe learning the task", which Pimentel et al. (2020) challenged. We show this dichotomy is valid information-theoretically. In addition, we find that the methods to construct and select good probes proposed by the two papers, *control task* (Hewitt and Liang, 2019) and *control function* (Pimentel et al., 2020), are equivalent -- the errors of their approaches are identical (modulo irrelevant terms). Empirically, these two selection criteria lead to results that highly agree with each other., Comment: EMNLP 2020

Here we discuss the four key principles of bio-medical ethics from surgical context. We elaborate on the definition of 'fairness' and its implications in AI system design, with taxonomy of algorithmic biases in AI. We discuss the shifts in ethical paradigms as the degree of autonomy in AI systems continue to evolve. We also emphasize the need for continuous revisions of ethics in AI due to evolution and dynamic nature of AI systems and technologies.

Research related to automatically detecting Alzheimer's disease (AD) is important, given the high prevalence of AD and the high cost of traditional methods. Since AD significantly affects the content and acoustics of spontaneous speech, natural language processing and machine learning provide promising techniques for reliably detecting AD. We compare and contrast the performance of two such approaches for AD detection on the recent ADReSS challenge dataset: 1) using domain knowledge-based hand-crafted features that capture linguistic and acoustic phenomena, and 2) fine-tuning Bidirectional Encoder Representations from Transformer (BERT)-based sequence classification models. We also compare multiple feature-based regression models for a neuropsychological score task in the challenge. We observe that fine-tuned BERT models, given the relative importance of linguistics in cognitive impairment detection, outperform feature-based approaches on the AD detection task., Comment: accepted to INTERSPEECH 2020

The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this information. We apply a reinforcement learning framework which emulates this format by providing explanations based on the explainee's current mental model. We conduct novel online human experiments where explanations generated by various explanation methods are selected and presented to participants, using policies which observe participants' mental models, in order to optimize an interpretability proxy. Our results suggest that mental model-based policies (anchored in our proposed state representation) may increase interpretability over multiple sequential explanations, when compared to a random selection baseline. This work provides insight into how to select explanations which increase relevant information for users, and into conducting human-grounded experimentation to understand interpretability., Comment: Accepted into ICML 2020 Workshop on Human Interpretability in Machine Learning (Spotlight)

Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be sub-optimal for distinguishing speakers locally in a specific meeting session. In this work we present the first use of graph neural networks (GNNs) for the speaker diarization problem, utilizing a GNN to refine speaker embeddings locally using the structural information between speech segments inside each session. The speaker embeddings extracted by a pre-trained model are remapped into a new embedding space, in which the different speakers within a single session are better separated. The model is trained for linkage prediction in a supervised manner by minimizing the difference between the affinity matrix constructed by the refined embeddings and the ground-truth adjacency matrix. Spectral clustering is then applied on top of the refined embeddings. We show that the clustering performance of the refined speaker embeddings outperforms the original embeddings significantly on both simulated and real meeting data, and our system achieves the state-of-the-art result on the NIST SRE 2000 CALLHOME database., Comment: ICASSP 2020 (45th International Conference on Acoustics, Speech, and Signal Processing)

Disfluent speech has been previously addressed from two main perspectives: the clinical perspective focusing on diagnostic, and the Natural Language Processing (NLP) perspective aiming at modeling these events and detect them for downstream tasks. In addition, previous works often used different metrics depending on whether the input features are text or speech, making it difficult to compare the different contributions. Here, we introduce a new evaluation framework for disfluency detection inspired by the clinical and NLP perspective together with the theory of performance from \cite{clark1996using} which distinguishes between primary and collateral tracks. We introduce a novel forced-aligned disfluency dataset from a corpus of semi-directed interviews, and present baseline results directly comparing the performance of text-based features (word and span information) and speech-based (acoustic-prosodic information). Finally, we introduce new audio features inspired by the word-based span features. We show experimentally that using these features outperformed the baselines for speech-based predictions on the present dataset., Comment: To be published in LREC 2020

Perez et al's study using the Apple Watch to identify atrial fibrillation (AF) is a watershed moment in large-scale machine learning for wearable computing. Identifying relevant patients will be tremendously important to research in healthcare. For a condition like AF, this could reduce stroke risk by two thirds. In the study by Perez et al, only 450 out of 420,000 individuals had ground truth data. Their study excluded 417,000 participants using the irregular pulse notification. This design decision means their study was only able to report positive predictive value (PPV) and unable to explore sensitivity or specificity. In this editorial, we explore the difficulty of obtaining ground truth data and its implications for study design.

Tone is a prosodic feature used to distinguish words in many languages, some of which are endangered and scarcely documented. In this work, we use unsupervised representation learning to identify probable clusters of syllables that share the same phonemic tone. Our method extracts the pitch for each syllable, then trains a convolutional autoencoder to learn a low dimensional representation for each contour. We then apply the mean shift algorithm to cluster tones in high-density regions of the latent space. Furthermore, by feeding the centers of each cluster into the decoder, we produce a prototypical contour that represents each cluster. We apply this method to spoken multi-syllable words in Mandarin Chinese and Cantonese and evaluate how closely our clusters match the ground truth tone categories. Finally, we discuss some difficulties with our approach, including contextual tone variation and allophony effects., Comment: Accepted by SIGMORPHON 2020: 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

Understanding the vulnerability of linguistic features extracted from noisy text is important for both developing better health text classification models and for interpreting vulnerabilities of natural language models. In this paper, we investigate how generic language characteristics, such as syntax or the lexicon, are impacted by artificial text alterations. The vulnerability of features is analysed from two perspectives: (1) the level of feature value change, and (2) the level of change of feature predictive power as a result of text modifications. We show that lexical features are more sensitive to text modifications than syntactic ones. However, we also demonstrate that these smaller changes of syntactic features have a stronger influence on classification performance downstream, compared to the impact of changes to lexical features. Results are validated across three datasets representing different text-classification tasks, with different levels of lexical and syntactic complexity of both conversational and written language., Comment: EMNLP Workshop on Noisy User-generated Text (W-NUT 2019)

We seek to improve the data efficiency of neural networks and present novel implementations of parameterized piece-wise polynomial activation functions. The parameters are the y-coordinates of n+1 Chebyshev nodes per hidden unit and Lagrangian interpolation between the nodes produces the polynomial on [-1, 1]. We show results for different methods of handling inputs outside [-1, 1] on synthetic datasets, finding significant improvements in capacity of expression and accuracy of interpolation in models that compute some form of linear extrapolation from either ends. We demonstrate competitive or state-of-the-art performance on the classification of images (MNIST and CIFAR-10) and minimally-correlated vectors (DementiaBank) when we replace ReLU or tanh with linearly extrapolated Chebyshev-Lagrange activations in deep residual architectures.

Generative adversarial networks (GANs) have shown considerable success, especially in the realistic generation of images. In this work, we apply similar techniques for the generation of text. We propose a novel approach to handle the discrete nature of text, during training, using word embeddings. Our method is agnostic to vocabulary size and achieves competitive results relative to methods with various discrete gradient estimators.

Machine learning has shown promise for automatic detection of Alzheimer's disease (AD) through speech; however, efforts are hampered by a scarcity of data, especially in languages other than English. We propose a method to learn a correspondence between independently engineered lexicosyntactic features in two languages, using a large parallel corpus of out-of-domain movie dialogue data. We apply it to dementia detection in Mandarin Chinese, and demonstrate that our method outperforms both unilingual and machine translation-based baselines. This appears to be the first study that transfers feature domains in detecting cognitive decline., Comment: NAACL 2019 (Short paper)

Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant performance gap between recognizing speakers in the training set and unseen speakers. The latter case corresponds to the few-shot learning task, where a trained model is evaluated on unseen classes. Here, we optimize a speaker embedding model with prototypical network loss (PNL), a state-of-the-art approach for the few-shot image classification task. The resulting embedding model outperforms the state-of-the-art triplet loss based models in both speaker verification and identification tasks, for both seen and unseen speakers., Comment: ICASSP 2019 (44th International Conference on Acoustics, Speech, and Signal Processing)

Speech datasets for identifying Alzheimer's disease (AD) are generally restricted to participants performing a single task, e.g. describing an image shown to them. As a result, models trained on linguistic features derived from such datasets may not be generalizable across tasks. Building on prior work demonstrating that same-task data of healthy participants helps improve AD detection on a single-task dataset of pathological speech, we augment an AD-specific dataset consisting of subjects describing a picture with multi-task healthy data. We demonstrate that normative data from multiple speech-based tasks helps improve AD detection by up to 9%. Visualization of decision boundaries reveals that models trained on a combination of structured picture descriptions and unstructured conversational speech have the least out-of-task error and show the most potential to generalize to multiple tasks. We analyze the impact of age of the added samples and if they affect fairness in classification. We also provide explanations for a possible inductive bias effect across tasks using model-agnostic feature anchors. This work highlights the need for heterogeneous datasets for encoding changes in multiple facets of cognition and for developing a task-independent AD detection model., Comment: Machine Learning for Health (ML4H) Workshop at NeurIPS 2018 arXiv:1811.07216

Many people are suffering from voice disorders, which can adversely affect the quality of their lives. In response, some researchers have proposed algorithms for automatic assessment of these disorders, based on voice signals. However, these signals can be sensitive to the recording devices. Indeed, the channel effect is a pervasive problem in machine learning for healthcare. In this study, we propose a detection system for pathological voice, which is robust against the channel effect. This system is based on a bidirectional LSTM network. To increase the performance robustness against channel mismatch, we integrate domain adversarial training (DAT) to eliminate the differences between the devices. When we train on data recorded on a high-quality microphone and evaluate on smartphone data without labels, our robust detection system increases the PR-AUC from 0.8448 to 0.9455 (and 0.9522 with target sample labels). To the best of our knowledge, this is the first study applying unsupervised domain adaptation to pathological voice detection. Notably, our system does not need target device sample labels, which allows for generalization to many new devices., Comment: Machine Learning for Health (ML4H) Workshop at NeurIPS 2018 arXiv:1811.07216

We propose a new architecture and training methodology for generative adversarial networks. Current approaches attempt to learn the transformation from a noise sample to a generated data sample in one shot. Our proposed generator architecture, called $\textit{ChainGAN}$, uses a two-step process. It first attempts to transform a noise vector into a crude sample, similar to a traditional generator. Next, a chain of networks, called $\textit{editors}$, attempt to sequentially enhance this sample. We train each of these units independently, instead of with end-to-end backpropagation on the entire chain. Our model is robust, efficient, and flexible as we can apply it to various network architectures. We provide rationale for our choices and experimentally evaluate our model, achieving competitive results on several datasets.

We consider a classifier whose test set is exposed to various perturbations that are not present in the training set. These test samples still contain enough features to map them to the same class as their unperturbed counterpart. Current architectures exhibit rapid degradation of accuracy when trained on standard datasets but then used to classify perturbed samples of that data. To address this, we present a novel architecture named DeepConsensus that significantly improves generalization to these test-time perturbations. Our key insight is that deep neural networks should directly consider summaries of low and high level features when making classifications. Existing convolutional neural networks can be augmented with DeepConsensus, leading to improved resistance against large and small perturbations on MNIST, EMNIST, FashionMNIST, CIFAR10 and SVHN datasets.

Linguistic features have shown promising applications for detecting various cognitive impairments. To improve detection accuracies, increasing the amount of data or the number of linguistic features have been two applicable approaches. However, acquiring additional clinical data can be expensive, and hand-crafting features is burdensome. In this paper, we take a third approach, proposing Consensus Networks (CNs), a framework to classify after reaching agreements between modalities. We divide linguistic features into non-overlapping subsets according to their modalities, and let neural networks learn low-dimensional representations that agree with each other. These representations are passed into a classifier network. All neural networks are optimized iteratively. In this paper, we also present two methods that improve the performance of CNs. We then present ablation studies to illustrate the effectiveness of modality division. To understand further what happens in CNs, we visualize the representations during training. Overall, using all of the 413 linguistic features, our models significantly outperform traditional classifiers, which are used by the state-of-the-art papers., Comment: NAACL 2019

This paper presents three hybrid models that directly combine latent Dirichlet allocation and word embedding for distinguishing between speakers with and without Alzheimer's disease from transcripts of picture descriptions. Two of our models get F-scores over the current state-of-the-art using automatic methods on the DementiaBank dataset.

We replicate a variation of the image captioning architecture by Vinyals et al. (2015), then introduce dropout during inference mode to simulate the effects of neurodegenerative diseases like Alzheimer's disease (AD) and Wernicke's aphasia (WA). We evaluate the effects of dropout on language production by measuring the KL-divergence of word frequency distributions and other linguistic metrics as dropout is added. We find that the generated sentences most closely approximate the word frequency distribution of the training corpus when using a moderate dropout of 0.4 during inference.

One of the most prevalent symptoms among the elderly population, dementia, can be detected by classifiers trained on linguistic features extracted from narrative transcripts. However, these linguistic features are impacted in a similar but different fashion by the normal aging process. Aging is therefore a confounding factor, whose effects have been hard for machine learning classifiers (especially deep neural network based models) to ignore. We show DNN models are capable of estimating ages based on linguistic features. Predicting dementia based on this aging bias could lead to potentially non-generalizable accuracies on clinical datasets, if not properly deconfounded. In this paper, we propose to address this deconfounding problem with fair representation learning. We build neural network classifiers that learn low-dimensional representations reflecting the impacts of dementia yet discarding the effects of age. To evaluate these classifiers, we specify a model-agnostic score $\Delta_{eo}^{(N)}$ measuring how classifier results are deconfounded from age. Our best models compromise accuracy by only 2.56\% and 1.54\% on two clinical datasets compared to DNNs, and their $\Delta_{eo}^{(2)}$ scores are better than statistical (residulization and inverse probability weight) adjustments., Comment: 9 pages, 2 figures

Deep learning has demonstrated abilities to learn complex structures, but they can be restricted by available data. Recently, Consensus Networks (CNs) were proposed to alleviate data sparsity by utilizing features from multiple modalities, but they too have been limited by the size of labeled data. In this paper, we extend CN to Transductive Consensus Networks (TCNs), suitable for semi-supervised learning. In TCNs, different modalities of input are compressed into latent representations, which we encourage to become indistinguishable during iterative adversarial training. To understand TCNs two mechanisms, consensus and classification, we put forward its three variants in ablation studies on these mechanisms. To further investigate TCN models, we treat the latent representations as probability distributions and measure their similarities as the negative relative Jensen-Shannon divergences. We show that a consensus state beneficial for classification desires a stable but imperfect similarity between the representations. Overall, TCNs outperform or align with the best benchmark algorithms given 20 to 200 labeled samples on the Bank Marketing and the DementiaBank datasets., Comment: NIPS IRASL Workshop 2018