Papers with language understanding systems
Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking (D19-55)
Copied to clipboard
Nathanael Chambers, Timothy Forman, Catherine Griswold, Kevin Lu, Yogaish Khastgir, Stephen Steckler
| Challenge: | Illicit activity on the Web often obscures information between client and seller, such as the seller’s phone number. |
| Approach: | They propose to use a dataset to model adversarial noise in a text extraction system and propose a visual character language model to interpret unseen unicode characters. |
| Outcome: | The proposed model improves number recognition by 89% over a CRF with a CNN and shows that unicode characters can be translated to unicoding. |
Learning from Omission (P19-1)
Copied to clipboard
| Challenge: | a recent study shows that pragmatic reasoning improves language understanding systems . end-to-end training produces more accurate utterance interpretation models . |
| Approach: | They show that pragmatic reasoning can improve the quality of learned meanings . they draw pragmatic inferences from listening to what a speaker says and not to what they do . |
| Outcome: | The proposed model improves the quality of language understanding models when sparse data is used. |
Inferring Implicit Relations in Complex Questions with Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | A prominent challenge for language understanding systems is the ability to answer implicit reasoning questions where the evidence for answering the question is not mentioned explicitly. |
| Approach: | They propose to decouple inference of reasoning steps from execution by evaluating models of implicit relation inference. |
| Outcome: | The proposed model fails on the implicit reasoning QA task, but infers implicit relations . the proposed model is compared with other models that fail on the same task . |
CURE: Controlled Unlearning for Robust Embeddings — Mitigating Conceptual Shortcuts in Pre-Trained Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models are susceptible to spurious, concept-driven correlations that impair robustness and fairness. |
| Approach: | They propose a framework that disentangles and suppresses conceptual shortcuts while preserving essential content information. |
| Outcome: | The proposed framework improves on IMDB and Yelp datasets with minimal computational overhead. |