Multi-sentence Compression using Recursive Generation
- 주제(키워드) Multi-sentence compression , Sequential processing , Sequence-to-sequence learning , Stochastic generation
- 발행기관 아주대학교
- 지도교수 손경아
- 발행년도 2020
- 학위수여년월 2020. 8
- 학위명 석사
- 학과 및 전공 일반대학원 컴퓨터공학과
- 실제URI http://www.dcollection.net/handler/ajou/000000030144
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
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.
more목차
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