Papers with GMM
Topic-Guided Variational Auto-Encoder for Text Generation (N19-1)
Copied to clipboard
Wenlin Wang, Zhe Gan, Hongteng Xu, Ruiyi Zhang, Guoyin Wang, Dinghan Shen, Changyou Chen, Lawrence Carin
| Challenge: | Experimental results show that our model outperforms its competitors on both unconditional and conditional text generation. |
| Approach: | They propose a topic-guided variational auto-encoder model for text generation that specifies a Gaussian mixture model and a neural topic module to generate sentences under the topic. |
| Outcome: | The proposed model outperforms existing variational auto-encoders on unconditional and conditional text generation, and can generate semantically-meaningful sentences with various topics. |
Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Dot-product attention only considers the pair-wise correlation between words, resulting in dispersion when dealing with long sentences and neglecting source neighboring relationships. |
| Approach: | They propose to model concentrated attention in cross-attention using a Gaussian Mixture Model to model cross- attention in a language model. |
| Outcome: | Experiments on three datasets show that the proposed method outperforms the baseline and has significant improvement on alignment quality, N-gram accuracy, and long sentence translation. |
EMO&LY (EMOtion and AnomaLY) : A new corpus for anomaly detection in an audiovisual stream with emotional context. (L18-1)
Copied to clipboard
| Challenge: | Anomalies in discourse are induced or acted by a machine learning algorithm. |
| Approach: | They propose to use facial and speech video to create a corpus that contains controlled anomalies. |
| Outcome: | The proposed corpus contains controlled anomalies in speech and facial video recordings of subjects. |
AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for aggregating large-form outputs overlook the nuance of neutral information and suffer from the high computational cost of fine-grained decomposition. |
| Approach: | They propose a UQ framework that uses NLI neutral probabilities as triggers to distinguish irrelevance from uncertainty, reducing computation costs. |
| Outcome: | Experiments on BIO and LongFact show that the proposed framework reduces inference time by 60% compared to full atomic decomposition. |
Evaluation of Feature-Space Speaker Adaptation for End-to-End Acoustic Models (L18-1)
Copied to clipboard
| Challenge: | Existing speaker adaptation algorithms for BLSTM-CTC AMs are lacking . TED-LIUM corpus shows speaker adaptation provides 11-20% word error rate reduction over baseline model built on raw filter-bank features. |
| Approach: | They propose to use feature-space adaptation techniques for bidirectional long short term memory (BLSTM) recurrent neural network based acoustic models trained with the connectionist temporal classification objective function to improve speaker adaptation. |
| Outcome: | The proposed approach provides up to 11-20% of word error reduction over baseline models on the TED-LIUM corpus. |