Papers with two-phase approach
Weakly Supervised Formula Learner for Solving Mathematical Problems (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work suggests a two-phase approach to solving mathematical reasoning tasks . however, its reliance on annotated formulas as intermediate labels throughout its training limited its application. |
| Approach: | They propose a framework that allows models to learn optimal formulas autonomously with weak supervision from the final answers to mathematical problems. |
| Outcome: | The proposed framework outperforms baselines trained on incomplete yet imperfect formula annotations and weakly supervised learning methods on two representative mathematical reasoning datasets. |
Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have focused on improving dialogue generation models that include knowledge related to the posts. |
| Approach: | They propose to use a novel method to generate responses from posts and related knowledge by injecting knowledge into dialogue generation models. |
| Outcome: | The proposed method outperforms baseline models in terms of knowledge relevance and quality. |