Papers with meaning preservation
Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks (N18-2)
Copied to clipboard
| Challenge: | Semantic representations have long been argued as potentially useful for enforcing meaning preservation and improving generalization performance of machine translation methods. |
| Approach: | They propose to integrate semantic representations into neural machine translation by injecting a semantic bias into sentence encoders and achieving improvements in BLEU scores. |
| Outcome: | The proposed representations achieve better BLEU scores over the linguistic-agnostic and syntax-aware versions on the English–German language pair. |
Style Obfuscation by Invariance (C18-1)
Copied to clipboard
| Challenge: | obfuscation-by-transfer is a method of obliging writing style using sequence models . a side effect of this approach is the frequent major alterations to the semantic content of the input . |
| Approach: | They propose obfuscation-by-invariance and investigate to what extent models trained to be explicitly style-independent preserve semantics. |
| Outcome: | The proposed model performs better than models trained to be explicitly style-invariant, while human evaluation shows a trade-off between the level of obfuscation and the quality of the output. |
MICo: Preventative Detoxification of Large Language Models through Inhibition Control (2024.findings-naacl)
Copied to clipboard
Roy Siegelmann, Ninareh Mehrabi, Palash Goyal, Prasoon Goyal, Lisa Bauer, Jwala Dhamala, Aram Galstyan, Rahul Gupta, Reza Ghanadan
| Challenge: | Large Language Models (LLMs) have a tendency to devolve into toxic degeneration . model may classify prompts as toxic or non-toxic and categorically refuse to respond to those deemed toxic. |
| Approach: | They propose a mechanism for LLM detoxification by labeling acceptable and unacceptable examples and including a corresponding acceptable rewrite with every unacceptable example. |
| Outcome: | The proposed model improves on the baseline model and shows that it detects and rewrites toxic and harmful examples. |
Simplified Corpus with Core Vocabulary (L18-1)
Copied to clipboard
| Challenge: | a study has found that simple Japanese is more accessible to foreigners than English. |
| Approach: | They have constructed a simplified corpus for the Japanese language and selected the core vocabulary. |
| Outcome: | The simplified corpus can be used for automatic text simplification and translating simple Japanese into English and vice-versa. |
Inducing Positive Perspectives with Text Reframing (2022.acl-long)
Copied to clipboard
| Challenge: | Sentiment transfer is a text style transfer task that aims to reverse sentiment polarity and reversal in meaning. |
| Approach: | They propose a task called positive reframing that neutralizes a negative point of view and generates 'positive' perspectives without contradicting original meaning. |
| Outcome: | The proposed model neutralizes a negative point of view and generates 'positive' perspectives without contradicting the original meaning. |
Let’s Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models demonstrate limited capability in proficiency-controlled sentence simplification when simplifying across large readability levels. |
| Approach: | They propose a framework that decomposes complex simplifications into manageable steps through dynamic path planning, semantic-aware exemplar selection, and chain-of-thought generation with conversation history for coherent reasoning. |
| Outcome: | The proposed framework reduces computational steps while improving simplification effectiveness on five languages across two benchmarks. |
Perceptual Models of Machine-Edited Text (2021.findings-acl)
Copied to clipboard
| Challenge: | a dataset of human judgments of machine-edited text is presented . we compare six different methods to create generic models of human perception . |
| Approach: | They propose to use six machine-editing methods to model human perceptions of edited text . they use a dataset of human judgments of machine-edited text and scientific abstracts . |
| Outcome: | The proposed model is based on human judgments of machine-edited text and scientific abstracts . human judgment of edited text is predicted to be within 6% of human consensus labeling . |