Papers by Michael J. Paul
Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing work on document classification models mainly uses synthetic monolingual data without ground truth for author demographic attributes. |
| Approach: | They assemble and publish a multilingual Twitter corpus for the task of hate speech detection using inferred author demographic factors. |
| Outcome: | The results show that the classifiers learn human biases and can be discriminatory towards certain demographic groups. |
Analyzing Bayesian Crosslingual Transfer in Topic Models (N19-1)
Copied to clipboard
| Challenge: | a theoretical analysis of crosslingual transfer in probabilistic topic models is presented . we use Gibbs sampling to quantify the loss of knowledge across languages . |
| Approach: | They propose a method to quantify the loss of knowledge across languages during crosslingual transfer in probabilistic topic models. |
| Outcome: | The proposed model quantifies the loss of knowledge across languages during this process . it is validated on a diverse set of five languages and discusses best practices for data collection and model design . |
Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models (P19-1)
Copied to clipboard
| Challenge: | Recent studies show that document classifiers can become more stable over time when trained in ways that account for temporal variations. |
| Approach: | They propose a method for embedding diachronic word embedds into document classification models . they propose 'time-driven neural classification model' that accounts for temporal variations . |
| Outcome: | The proposed model can be trained on six corpora and make it more robust over time. |
Evaluating Topic Quality with Posterior Variability (D19-1)
Copied to clipboard
| Challenge: | Probabilistic topic models such as latent Dirichlet allocation (LDA) are widely used for NLP tasks which require the extraction of latent themes. |
| Approach: | They propose to measure topic quality using the variability of posterior distributions of probabilistic topic models. |
| Outcome: | The proposed metric achieves state-of-the-art correlations with human judgments of topic quality in experiments on three corpora. |
A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularity (P19-1)
Copied to clipboard
| Challenge: | Cross-lingual word embeddings encode the meaning of words from different languages into a shared low-dimensional space. |
| Approach: | They show that modularity can be used to improve unsupervised word embeddings . they show that it is useful for low-resource languages where one often has few bilingual pairs . |
| Outcome: | The proposed model improves unsupervised cross-lingual word embeddings on distant language pairs in low-resource settings. |
Learning Multilingual Topics from Incomparable Corpora (C18-1)
Copied to clipboard
| Challenge: | Existing models require parallel or comparable training, which limits their ability to generalize. |
| Approach: | They propose a method that demystifies the knowledge transfer mechanism behind multilingual topic models by defining an alternative but equivalent formulation. |
| Outcome: | The proposed model learns coherent multilingual topics from partially and fully incomparable corpora with limited amounts of dictionary resources. |
Lessons from the Bible on Modern Topics: Low-Resource Multilingual Topic Model Evaluation (N18-1)
Copied to clipboard
| Challenge: | Existing metrics to evaluate multilingual topic quality are inadequate for multilingual document analysis. |
| Approach: | They propose a new intrinsic evaluation metric for multilingual topic models that correlates well with human judgments of multilingual coherence and performance in downstream applications. |
| Outcome: | The proposed model improves the performance of multilingual topic models in low-resource languages and with human judgments of multilinguistic topic coherence. |
Why Overfitting Isn’t Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries (2020.acl-main)
Copied to clipboard
| Challenge: | Recent studies only evaluate cross-lingual word embeddings on bilingual lexicon induction (BLI) however, underfitting can hinder generalization to other downstream tasks. |
| Approach: | They retrofit cross-lingual word embeddings to the training dictionary and a synthetic dictionary to improve their results. |
| Outcome: | The proposed method improves accuracy on two downstream tasks, despite underfitting the training dictionary. |
Examining Temporality in Document Classification (P18-2)
Copied to clipboard
| Challenge: | a recent study examines how document classification models trained during one time period perform on documents trained during other time periods. |
| Approach: | They propose to use a domain adaptation approach to adjust for changes in time to improve document classification. |
| Outcome: | The proposed model improves on documents trained on time intervals even on future time interval intervals. |