To support people’s understanding of agent policies, methods for extracting summaries of an agent’s policy, i.e. informative collections of agent decisions consisting of state-action pairs, have been proposed [3 ]. One approach to summarization relies on heuristics for diversity or state importance [2 , 7 ]. Another approach assumes a computational model of how humans will generalize from a summary, and uses this model to optimize summaries to aid in reconstructing the policy [8 ]. Specifically, Huang et al. [8 ]assumed people would employ reasoning akin to inverse reinforcement learning (IRL) to understand an agent’s objective, and extract a summary that allows for accurate approximation of the agent’s reward. Our results show that in some domains, assuming the correct reconstruction model during summary extraction is necessary to accurately reconstruct an agent’s policy using that summary, but that in other domains, we can extract summaries that are robust to misspecification of the reconstruction model during summary extraction.

Summarization techniques in the medical domain 5. Conclusions Acknowledgements References Tables (4) Table Table 1 Table Table 2 Table Table 3 Table Table 4 Summary Objective: The aim of this paper is to survey the recent work in medical documents summarization.

In: IEEE Fourth international conference on computing communication control and automation (ICCUBEA), pp 1–6 Shah P, Desai N (2016) A survey of automatic text summarization techniques for Indian and foreign languages. IEEE International conference on electrical, electronics, and optimization techniques (ICEEOT), pp 4598–4601 Shimpikar S, Govilkar S (2017) A survey of text summarization techniques for Indian regional languages. int J Comp Appl, pp. 29–33 Straka M, Mediankin N, Kocmi T, Zabokrtsky Z, Hudecek V, Ha J (2018) SumeCzech: large Czech News-based summarization dataset.

From a human-centered perspective, we map the design opportunities and considerations for human-AI interaction in text summarization and broader text generation tasks. We then interviewed 16 users, aided by the prototypes, to understand their expectations, experience, and needs regarding efficiency, control, and trust with AI in text summarization and propose design considerations accordingly.

In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing, pp 553–563 Banerjee S Mitra P, Sugiyama K (2015) Multi-document abstractive summarization using ILP based multi-sentence compression. In: Proceedings of the 53rd annual meeting of the ACL and the 7th international conference on natural language processing. pp 1608–1617 Khan A, Salim N, Jaya Kumar Y (2015) A framework for multi-document abstractive summarization based on semantic role labelling.

Two methods of overcoming this limitation are (1) to apply a text processing strategy that is tolerant of unknown words and gaps in linguistics knowledge, and (2) to acquire lexical information automatically from the texts. These two methods have been implemented in a prototype intelligent information retrieval system called SCISOR (System for Conceptual Information Summarization, Organization and Retrieval). This article describes the text processing, language acquisition, and summarization components of SCISOR.

Conclusion Conflict of interest References Figures (9) Tables (6) Table Table 1 Table Table 2 Table Table 3 Table Table 4 Table Table 5 Table Table 6 Highlights • Introducing a Bayesian summarizer for biomedical text documents. • Different feature selection approaches for identifying important concepts in a biomedical text. • The efficiency of feature selection methods are evaluated on the performance of the Bayesian text summarizer. • The distribution of important concepts is used to classify the sentences of an input document. • The summarizer outperforms other frequency-based, domain-independent and baseline methods . Abstract Automatic text summarization tools help users in the biomedical domain to acquire their intended information from various textual resources more efficiently. Some of biomedical text summarization systems put the basis of their sentence selection approach on the frequency of concepts extracted from the input text.

A method of text summarization based on latent semantic indexing (LSI), which uses semantic indexing to calculate the sentence similarity, is proposed in this article. Comput Linguistics 32(1):33–64 Google Scholar Jing S, Guozhong D (2007) Text segmentation based on PLSA model (in Chinese). Comput Res Dev 44:242–248 Article Google Scholar Download references Author information Authors and Affiliations School of Applied Science, University of Science and Technology, Beijing, China Dongmei Ai School of Information Engineering, University of Science and Technology, Beijing, China Dongmei Ai, Yuchao Zheng & Dezheng Zhang Authors Dongmei Ai You can also search for this author in PubMed Google Scholar Yuchao Zheng You can also search for this author in PubMed Google Scholar Dezheng Zhang You can also search for this author in PubMed Google Scholar Corresponding author Correspondence to Dongmei Ai . Additional information This work was presented in part at the 15th International Symposium on Artificial Life and Robotics, Oita, Japan, February 4–6, 2010 About this article Cite this article Ai, D., Zheng, Y. & Zhang, D.