More Like this

1. Graph-based Extractive Explainer for Recommendations

   https://doi.org/10.1145/3485447.3512168  

   Wang, Peng; Cai, Renqin; Wang, Hongning (April 2022, Proceedings of the ACM Web Conference 2022)

   Explanations in a recommender system assist users make informed decisions among a set of recommended items. Extensive research attention has been devoted to generate natural language explanations to depict how the recommendations are generated and why the users should pay attention to them. However, due to different limitations of those solutions, e.g., template-based or generation-based, it is hard to make the explanations easily perceivable, reliable, and personalized at the same time. In this work, we develop a graph attentive neural network model that seamlessly integrates user, item, attributes and sentences for extraction-based explanation. The attributes of items are selected as the intermediary to facilitate message passing for user-item specific evaluation of sentence relevance. And to balance individual sentence relevance, overall attribute coverage and content redundancy, we solve an integer linear programming problem to make the final selection of sentences. Extensive empirical evaluations against a set of state-of-the-art baseline methods on two benchmark review datasets demonstrated the generation quality of proposed solution. 

   more » « less
2. Aspect-aware Unsupervised Extractive Opinion Summarization

   https://doi.org/10.18653/v1/2023.findings-acl.802  

   Li, Haoyuan; Basu Roy Chowdhury, Somnath; Chaturvedi, Snigdha (January 2023, Association for Computational Linguistics)
3. Unsupervised Extractive Summarization of Emotion Triggers

   Sosea, Tiberiu; Zhan, Hongli; Li, Junyi Jessy; Caragea, Cornelia (May 2023, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers))

   Understanding what leads to emotions during large-scale crises is important as it can provide groundings for expressed emotions and subsequently improve the understanding of ongoing disasters. Recent approaches trained supervised models to both detect emotions and explain emotion triggers (events and appraisals) via abstractive summarization. However, obtaining timely and qualitative abstractive summaries is expensive and extremely time-consuming, requiring highly-trained expert annotators. In time-sensitive, high-stake contexts, this can block necessary responses. We instead pursue unsupervised systems that extract triggers from text. First, we introduce CovidET-EXT, augmenting (Zhan et al., 2022)’s abstractive dataset (in the context of the COVID-19 crisis) with extractive triggers. Second, we develop new unsupervised learning models that can jointly detect emotions and summarize their triggers. Our best approach, entitled Emotion-Aware Pagerank, incorporates emotion information from external sources combined with a language understanding module, and outperforms strong baselines. We release our data and code at https://github.com/tsosea2/CovidET-EXT. 

   more » « less
4. Balancing Rare Species Conservation with Extractive Industries

   https://doi.org/10.3390/land11112012  

   Carrell, Joshua D.; Hammill, Edward; Edwards, Thomas C. (November 2022, Land)

   The Colorado Plateau has abundant oil, gas, and alternative energy potential. This energy potential is scattered among a patchwork of land ownership, with private, tribal, and public lands being actively developed for energy extraction. Elements of biodiversity (e.g., listed and sensitive plant and animal species) are distributed among all land tenures, yet the laws protecting them can vary as a function of land tenure. It is imperative to understand the spatial distributions of threatened endangered, and sensitive species in relation to land tenure to preserve habitat and conserve species populations in areas undergoing energy development. We developed species distribution models and spatial conservation optimization frameworks to explore the interactions among land ownership, existing and potential energy extraction, and biodiversity. Four management scenarios were tested to quantify how different approaches to energy extraction may impact rare plant distributions. Results show that incorporating risk and land tenure in spatially optimized frameworks it is possible to facilitate the long-term viability of rare plant species. The scenarios developed here represent a different attitude towards the value of rare plants and the risk of energy development. Results gives insight into the financial consequences of rare species protection and quantifies the biodiversity costs of energy development across landscapes. 

   more » « less
5. Continually Improving Extractive QA via Human Feedback

   https://doi.org/10.18653/v1/2023.emnlp-main.27  

   Gao, Ge; Chen, Hung-Ting; Artzi, Yoav; Choi, Eunsol (January 2023, Conference on Empirical Methods in Natural Language Processing)