Arrow Research search

Author name cluster

Stan Matwin

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers
2 author rows

Possible papers

14

AAAI Conference 2020 Conference Paper

Explaining Image Classifiers Generating Exemplars and Counter-Exemplars from Latent Representations

  • Riccardo Guidotti
  • Anna Monreale
  • Stan Matwin
  • Dino Pedreschi

We present an approach to explain the decisions of black box image classifiers through synthetic exemplar and counterexemplar learnt in the latent feature space. Our explanation method exploits the latent representations learned through an adversarial autoencoder for generating a synthetic neighborhood of the image for which an explanation is required. A decision tree is trained on a set of images represented in the latent space, and its decision rules are used to generate exemplar images showing how the original image can be modified to stay within its class. Counterfactual rules are used to generate counter-exemplars showing how the original image can “morph” into another class. The explanation also comprehends a saliency map highlighting the areas that contribute to its classification, and areas that push it into another class. A wide and deep experimental evaluation proves that the proposed method outperforms existing explainers in terms of fidelity, relevance, coherence, and stability, besides providing the most useful and interpretable explanations.

PDF Details

ICML Conference 2020 Conference Paper

Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

  • Xiang Jiang 0001
  • Qicheng Lao
  • Stan Matwin
  • Mohammad Havaei

We present an approach for unsupervised domain adaptation{—}with a strong focus on practical considerations of within-domain class imbalance and between-domain class distribution shift{—}from a class-conditioned domain alignment perspective. Current methods for class-conditioned domain alignment aim to explicitly minimize a loss function based on pseudo-label estimations of the target domain. However, these methods suffer from pseudo-label bias in the form of error accumulation. We propose a method that removes the need for explicit optimization of model parameters from pseudo-labels. Instead, we present a sampling-based implicit alignment approach, where the sample selection is implicitly guided by the pseudo-labels. Theoretical analysis reveals the existence of a domain-discriminator shortcut in misaligned classes, which is addressed by the proposed approach to facilitate domain-adversarial learning. Empirical results and ablation studies confirm the effectiveness of the proposed approach, especially in the presence of within-domain class imbalance and between-domain class distribution shift.

Details

AAAI Conference 2019 Conference Paper

Fast PMI-Based Word Embedding with Efficient Use of Unobserved Patterns

  • Behrouz Haji Soleimani
  • Stan Matwin

Continuous word representations that can capture the semantic information in the corpus are the building blocks of many natural language processing tasks. Pre-trained word embeddings are being used for sentiment analysis, text classification, question answering and so on. In this paper, we propose a new word embedding algorithm that works on a smoothed Positive Pointwise Mutual Information (PPMI) matrix which is obtained from the word-word co-occurrence counts. One of our major contributions is to propose an objective function and an optimization framework that exploits the full capacity of “negative examples”, the unobserved or insignificant wordword co-occurrences, in order to push unrelated words away from each other which improves the distribution of words in the latent space. We also propose a kernel similarity measure for the latent space that can effectively calculate the similarities in high dimensions. Moreover, we propose an approximate alternative to our algorithm using a modified Vantage Point tree and reduce the computational complexity of the algorithm to |V | log |V | with respect to the number of words in the vocabulary. We have trained various word embedding algorithms on articles of Wikipedia with 2. 1 billion tokens and show that our method outperforms the state-of-the-art in most word similarity tasks by a good margin.

PDF Details

AAAI Conference 2018 Conference Paper

Spectral Word Embedding with Negative Sampling

  • Behrouz Haji Soleimani
  • Stan Matwin

In this work, we investigate word embedding algorithms in the context of natural language processing. In particular, we examine the notion of “negative examples”, the unobserved or insignificant word-context co-occurrences, in spectral methods. we provide a new formulation for the word embedding problem by proposing a new intuitive objective function that perfectly justifies the use of negative examples. In fact, our algorithm not only learns from the important wordcontext co-occurrences, but also it learns from the abundance of unobserved or insignificant co-occurrences to improve the distribution of words in the latent embedded space. We analyze the algorithm theoretically and provide an optimal solution for the problem using spectral analysis. We have trained various word embedding algorithms on articles of Wikipedia with 2. 1 billion tokens and show that negative sampling can boost the quality of spectral methods. Our algorithm provides results as good as the state-of-the-art but in a much faster and efficient way.

PDF Details

AIIM Journal 2011 Journal Article

Exploiting the systematic review protocol for classification of medical abstracts

  • Oana Frunza
  • Diana Inkpen
  • Stan Matwin
  • William Klement
  • Peter O’Blenis

Objective To determine whether the automatic classification of documents can be useful in systematic reviews on medical topics, and specifically if the performance of the automatic classification can be enhanced by using the particular protocol of questions employed by the human reviewers to create multiple classifiers. Methods and materials The test collection is the data used in large-scale systematic review on the topic of the dissemination strategy of health care services for elderly people. From a group of 47, 274 abstracts marked by human reviewers to be included in or excluded from further screening, we randomly selected 20, 000 as a training set, with the remaining 27, 274 becoming a separate test set. As a machine learning algorithm we used complement naïve Bayes. We tested both a global classification method, where a single classifier is trained on instances of abstracts and their classification (i. e. , included or excluded), and a novel per-question classification method that trains multiple classifiers for each abstract, exploiting the specific protocol (questions) of the systematic review. For the per-question method we tested four ways of combining the results of the classifiers trained for the individual questions. As evaluation measures, we calculated precision and recall for several settings of the two methods. It is most important not to exclude any relevant documents (i. e. , to attain high recall for the class of interest) but also desirable to exclude most of the non-relevant documents (i. e. , to attain high precision on the class of interest) in order to reduce human workload. Results For the global method, the highest recall was 67. 8% and the highest precision was 37. 9%. For the per-question method, the highest recall was 99. 2%, and the highest precision was 63%. The human–machine workflow proposed in this paper achieved a recall value of 99. 6%, and a precision value of 17. 8%. Conclusion The per-question method that combines classifiers following the specific protocol of the review leads to better results than the global method in terms of recall. Because neither method is efficient enough to classify abstracts reliably by itself, the technology should be applied in a semi-automatic way, with a human expert still involved. When the workflow includes one human expert and the trained automatic classifier, recall improves to an acceptable level, showing that automatic classification techniques can reduce the human workload in the process of building a systematic review.

Details DOI

ECAI Conference 2010 Conference Paper

Classification of Dreams Using Machine Learning

  • Stan Matwin
  • Joseph De Koninck
  • Amir Hossein Razavi
  • Ray Reza Amini

We describe a project undertaken by an interdisciplinary team of researchers in sleep and in and machine learning. The goal is sentiment extraction from a corpus containing short textual descriptions of dreams. Dreams are categorized in a four-level scale of affections. The approach is based on a novel representation, taking into account the leading themes of the dream and the sequential unfolding of associated affective feelings during the dream. The dream representation is based on three combined parts, two of which are automatically produced from the description of the dream. The first part consists of co-occurrence vectors, which — unlike the standard Bag-of-words model — capture non-local relationships between meanings of word in a corpus. The second part introduces the dynamic representation that captures the change in affections throughout the progress of the dream. The third part is the self-reported assessment of the dream by the dreamer according to eight given attributes. The three representations are subject to aggressive feature selection. Using an ensemble of classifiers and the combined 3-partite representation, we have achieved 64% accuracy, which is in the range of human experts' consensus in that domain.

Details
v2026.09.13