Papers by Po-Sen Huang
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation (D19-1)
Copied to clipboard
Po-Sen Huang, Robert Stanforth, Johannes Welbl, Chris Dyer, Dani Yogatama, Sven Gowal, Krishnamurthy Dvijotham, Pushmeet Kohli
| Challenge: | Recent work has exposed the vulnerabilities of neural NLP models, e.g. with small, semantically invariant input alterations. |
| Approach: | They propose to model text classification under synonym replacements or character flip perturbations and then use a formal model verification method to verify its robustness. |
| Outcome: | The proposed models show little difference in terms of nominal accuracy, but have much improved verified accuracy under perturbations and come with an efficiently computable formal guarantee on worst case adversaries. |
Natural Language to Structured Query Generation via Meta-Learning (N18-2)
Copied to clipboard
| Challenge: | Conventional supervised training is a pervasive paradigm for NLP problems . however, examples of the same problem may vary widely . a few-shot meta-learning scenario is used to learn multiple models . |
| Approach: | They propose a learning protocol that treats each example as a unique pseudo-task . they use a few-shot meta-learning scenario to reduce the original learning problem to a single example . |
| Outcome: | The proposed learning protocol achieves 1.1%–5.4% accuracy gains over non-meta-learning counterparts on a WikiSQL dataset. |
Discourse-Aware Neural Rewards for Coherent Text Generation (N18-1)
Copied to clipboard
| Challenge: | Existing approaches to train text generation models using cross-entropy loss do not always correlate well with achieving high scores on commonly used evaluation measures. |
| Approach: | They propose to use discourse-aware rewards to model cross-sentence ordering to approximate desired discourse structure to train a model of long, coherent text. |
| Outcome: | The proposed model produces more coherent and less repetitive text than models trained with cross-entropy or with commonly used scores as rewards. |
Challenges in Detoxifying Language Models (2021.findings-emnlp)
Copied to clipboard
Johannes Welbl, Amelia Glaese, Jonathan Uesato, Sumanth Dathathri, John Mellor, Lisa Anne Hendricks, Kirsty Anderson, Pushmeet Kohli, Ben Coppin, Po-Sen Huang
| Challenge: | Prior work often relies on automatic evaluation of LM toxicity. |
| Approach: | They evaluate toxicity mitigation strategies for automated and human evaluations . they find human raters disagree with high automatic toxicity scores after strong toxicity reduction interventions . |
| Outcome: | The proposed methods reduce LM toxicity but lower coverage for marginalized texts . human raters disagree with high toxicity scores after strong toxicity reduction interventions . |
Reducing Sentiment Bias in Language Models via Counterfactual Evaluation (2020.findings-emnlp)
Copied to clipboard
Po-Sen Huang, Huan Zhang, Ray Jiang, Robert Stanforth, Johannes Welbl, Jack Rae, Vishal Maini, Dani Yogatama, Pushmeet Kohli
| Challenge: | Language modeling has advanced rapidly due to efficient model architectures and the availability of large text corpora. |
| Approach: | They propose to embed and regularize sentiment prediction-derived regularizations on the language model’s latent representations to reduce bias in the sentiment of generated text. |
| Outcome: | The proposed methods reduce bias in the sentiment of generated text by adopting individual and group fairness metrics from the fair machine learning literature. |