Papers with latent variable modeling
Generalization in Generation: A closer look at Exposure Bias (D19-56)
Copied to clipboard
| Challenge: | Autoregressive generative models are often criticized for using ground-truth contexts at training time but generated ones at test time. |
| Approach: | They propose that generalization is the underlying property to address and propose unconditional generation as its fundamental benchmark. |
| Outcome: | The proposed model is generalized and can handle true and generated contexts. |
Conditional Generators of Words Definitions (P18-2)
Copied to clipboard
| Challenge: | Existing definition modeling techniques for word embeddings only take into account words with multiple meanings. |
| Approach: | They propose a model that takes into account word ambiguities and polysemy and proposes a solution using latent variable modeling and soft attention mechanisms. |
| Outcome: | The proposed model improves on word ambiguity and polysemy and can be used for word sense disambiguation tasks. |
Large-Scale Bitext Corpora Provide New Evidence for Cognitive Representations of Spatial Terms (2024.eacl-long)
Copied to clipboard
| Challenge: | Recent evidence suggests that there exist two classes of cognitive representations within the spatial terms of a language. |
| Approach: | They propose a pipeline for extracting, isolating, and aligning spatial terms from parallel text . they find evidence that variability in functional terms differs significantly from that of geometric terms . |
| Outcome: | The proposed pipeline extracts, isolates, and aligns spatial terms in basic locative constructions from parallel text. |
Efficient Latent Variable Modeling for Knowledge-Grounded Dialogue Generation (2023.findings-emnlp)
Copied to clipboard
Gunsoo Han, Daejin Jo, Daniel Nam, Eunseop Yoon, Taehwan Kwon, Seungeun Rho, Kyoung-Woon On, Chang Yoo, Sungwoong Kim
| Challenge: | Existing knowledge-grounded dialogue generation algorithms require annotated knowledge to generate a response grounded on the retrieved knowledge. |
| Approach: | They propose an efficient algorithm for latent variable modeling that leverages large amount of dialogue data. |
| Outcome: | The proposed algorithm outperforms the supervised learning algorithm on knowledge-grounded dialogue datasets while maintaining efficiency and scalability. |
Variational Neural Machine Translation with Normalizing Flows (2020.acl-main)
Copied to clipboard
| Challenge: | Existing frameworks for learning informative latent variables are limited by limitations . existing models rely on strong assumptions on distribution of latent code . |
| Approach: | They propose to apply a variational neural machine translation framework to a Transformer . they propose to introduce a more flexible approximate posterior based on normalizing flows . |
| Outcome: | The proposed framework outperforms baseline models under in-domain and out-of-domain conditions. |
A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Structured belief states are crucial for goal tracking and database query in task-oriented dialog systems. |
| Approach: | They propose a probabilistic dialog model where belief states are represented as discrete latent variables and jointly modeled with system responses given user inputs. |
| Outcome: | The proposed model outperforms supervised-only and semi-supervised baselines on three benchmark datasets. |