Gabriele Pergola


2020

pdf bib
CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering
Junru Lu | Gabriele Pergola | Lin Gui | Binyang Li | Yulan He
Proceedings of the 28th International Conference on Computational Linguistics

We introduce CHIME, a cross-passage hierarchical memory network for question answering (QA) via text generation. It extends XLNet introducing an auxiliary memory module consisting of two components: the context memory collecting cross-passage evidences, and the answer memory working as a buffer continually refining the generated answers. Empirically, we show the efficacy of the proposed architecture in the multi-passage generative QA, outperforming the state-of-the-art baselines with better syntactically well-formed answers and increased precision in addressing the questions of the AmazonQA review dataset. An additional qualitative analysis revealed the interpretability introduced by the memory module.

2019

pdf bib
Neural Topic Model with Reinforcement Learning
Lin Gui | Jia Leng | Gabriele Pergola | Yu Zhou | Ruifeng Xu | Yulan He
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

In recent years, advances in neural variational inference have achieved many successes in text processing. Examples include neural topic models which are typically built upon variational autoencoder (VAE) with an objective of minimising the error of reconstructing original documents based on the learned latent topic vectors. However, minimising reconstruction errors does not necessarily lead to high quality topics. In this paper, we borrow the idea of reinforcement learning and incorporate topic coherence measures as reward signals to guide the learning of a VAE-based topic model. Furthermore, our proposed model is able to automatically separating background words dynamically from topic words, thus eliminating the pre-processing step of filtering infrequent and/or top frequent words, typically required for learning traditional topic models. Experimental results on the 20 Newsgroups and the NIPS datasets show superior performance both on perplexity and topic coherence measure compared to state-of-the-art neural topic models.