Multi-sentence Compression using Recursive Generation
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 손경아 | - |
dc.contributor.author | 황준선 | - |
dc.date.accessioned | 2022-11-29T02:32:18Z | - |
dc.date.available | 2022-11-29T02:32:18Z | - |
dc.date.issued | 2020-08 | - |
dc.identifier.other | 30144 | - |
dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/19818 | - |
dc.description | 학위논문(석사)--아주대학교 일반대학원 :컴퓨터공학과,2020. 8 | - |
dc.description.tableofcontents | I. Introduction 1 II. Related Works 3 A. Natural Language Understanding 3 B. Multi-Sentence Compression 3 III. Algorithm 6 A. Recursive Generation 6 B. Training Model 11 C. Generation Strategies 13 1. Myopic Generation 13 2. Stochastic Generation 13 IV. Experiments 15 A. Data 15 B. Settings 18 C. Results 19 1. Comparison with Baseline 19 2. Generation 22 3. Myopic vs. Stochastic 23 4. Application 25 5. Visualization 27 V. Conclusion and Future Works 28 VI. References 30 | - |
dc.language.iso | eng | - |
dc.publisher | The Graduate School, Ajou University | - |
dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
dc.title | Multi-sentence Compression using Recursive Generation | - |
dc.type | Thesis | - |
dc.contributor.affiliation | 아주대학교 일반대학원 | - |
dc.contributor.department | 일반대학원 컴퓨터공학과 | - |
dc.date.awarded | 2020. 8 | - |
dc.description.degree | Master | - |
dc.identifier.localId | 1151730 | - |
dc.identifier.uci | I804:41038-000000030144 | - |
dc.identifier.url | http://dcoll.ajou.ac.kr:9080/dcollection/common/orgView/000000030144 | - |
dc.subject.keyword | Multi-sentence compression | - |
dc.subject.keyword | Sequence-to-sequence learning | - |
dc.subject.keyword | Sequential processing | - |
dc.subject.keyword | Stochastic generation | - |
dc.description.alternativeAbstract | In this paper, we present a new method that summarizes multiple sentences into one sentence. Such a task is useful in domains such as short text summarization. Despite the usefulness of this issue, many studies have not been proposed on the matter. One of the reasons is the training data scarcity: it is impractical to prepare a large data set that contains a sufficiently diverse set of combinations to ensure generalization. We aim to alleviate this difficulty by reformulating the original problem into a problem that produces sentences sequentially. That is, we construct a recursive generation model that takes two sentences in order: the input sentence of the current time step and the generalized sentence so far. Since there is no need to consider the combination of the total input sentences, less complex training data is required than the original problem. Based on the recursive generation model, we propose to summarize the sequentially-input sentences in an online, stochastic manner, where the summary is updated with probability proportional to semantic similarity. Thanks to this stochastic generation scheme, our approach is more flexible for handling situations where inputs are not similar, thus produces summaries with better semantic compression. | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.