Papers with online setting
Fairness-Aware Online Positive-Unlabeled Learning (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Positive-unlabeled (PU) learning is a new approach to improve text classification by analyzing the impact of the online setting on fairness. |
| Approach: | They propose to extend Positive-Unlabeled (PU) learning to online learning by analyzing the impact of the online setting on fairness. |
| Outcome: | The proposed approach improves fairness in PU learning in both offline and online settings by using only labeled positive and unlabeled samples. |
Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning (2022.acl-short)
Copied to clipboard
Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu, Long Bai, Wei Li, Jiafeng Guo, Xueqi Cheng
| Challenge: | Existing models for TKG reasoning focus on modeling fact sequences of a fixed length, which cannot discover complex evolutional patterns that vary in length. |
| Approach: | They propose to use a length-aware Convolutional Neural Network to handle evolutional patterns of different lengths via an easy-to-difficult curriculum learning strategy. |
| Outcome: | The proposed model improves performance under both offline and online learning strategies. |
Learning an Unreferenced Metric for Online Dialogue Evaluation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing tools for dialogue evaluation do not generalize to unseen datasets and/or need a human-generated reference response during inference. |
| Approach: | They propose an unreferenced automated dialogue evaluation metric that uses large pre-trained language models to extract latent representations of utterances and leverages the temporal transitions that exist between them. |
| Outcome: | The proposed model achieves higher correlation with human annotations in an online setting, while not requiring true responses for comparison during inference. |
RoomReader: A Multimodal Corpus of Online Multiparty Conversational Interactions (2022.lrec-1)
Copied to clipboard
Justine Reverdy, Sam O’Connor Russell, Louise Duquenne, Diego Garaialde, Benjamin R. Cowan, Naomi Harte
| Challenge: | The corpus of multimodal, multiparty conversational interactions explored in RoomReader can be used to study a wide range of phenomena in online multimodal interaction. |
| Approach: | They propose to use RoomReader to explore multimodal cues of conversational engagement and behavioural aspects of collaborative interaction in online environments. |
| Outcome: | The corpus was developed within the wider RoomReader Project to explore multimodal cues of conversational engagement and behavioural aspects of collaborative interaction in online environments. |
Scalable Collapsed Inference for High-Dimensional Topic Models (N19-1)
Copied to clipboard
| Challenge: | Existing methods have achieved two out of three criteria simultaneously, but never all three at once. |
| Approach: | They propose an online inference algorithm which leverages stochasticity to scale well in the number of documents and sparsity to achieve accurate inference. |
| Outcome: | The proposed algorithm scales well in the number of documents and topics while achieving accurate inference. |
Topic Spotting using Hierarchical Networks with Self Attention (N19-1)
Copied to clipboard
| Challenge: | Existing systems struggle to have consistent long term conversations with the users and fail to build rapport. |
| Approach: | They propose a hierarchical model with self attention for topic spotting . they compare it to previous proposed techniques for topic detection . |
| Outcome: | The proposed model outperforms existing models for topic spotting and deep models for text classification in an online setting. |
Multilingual Clustering of Streaming News (D18-1)
Copied to clipboard
| Challenge: | a novel method for clustering news across languages is proposed . a key challenge in handling news streams is that they must be generated on the fly . |
| Approach: | They propose a method for clustering news across languages into monolingual and crosslingual clusters . they use real news datasets in multiple languages to find an ever growing number of cluster labels . |
| Outcome: | The proposed method produces state-of-the-art results on real news datasets in German, English and Spanish. |