Papers with Markov Random Fields
Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning (N18-2)
Copied to clipboard
| Challenge: | Existing methods to recognize textual entailment use a CCG parser to process sentences . failing to recognize the similar syntactic structure results in inconsistent argument structures . |
| Approach: | They propose to extend existing CCG parsers to parse sentences consistently . they use an inter-sentence modeling with Markov Random Fields to achieve this . |
| Outcome: | The proposed method improves on English and Japanese languages. |
PhraseCTM: Correlated Topic Modeling on Phrases within Markov Random Fields (P18-2)
Copied to clipboard
| Challenge: | Recent phrase-level topic models are unable to capture the correlation structure among the discovered topics. |
| Approach: | They propose a phrase-level topic model PhraseCTM and a method to find out the correlations of topics at phrase level. |
| Outcome: | The proposed method shows that correlated topic modeling is a good way to interpret themes of corpus. |
MRF-Chat: Improving Dialogue with Markov Random Fields (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to deep learning for open-domain dialogue include training end-to-end models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts and persona of the agent and the user, among others. |
| Approach: | They propose a probabilistic approach using Markov Random Fields to augment existing deep-learning methods for improved next utterance prediction. |
| Outcome: | The proposed approach significantly improves the performance of existing state-of-the-art retrieval models for open-domain conversational agents. |