Digital Library[ Search Result ]
Solving for Redundant Repetition Problem of Generating Summarization using Decoding History
Jaehyun Ryu, Yunseok Noh, Su Jeong Choi, Seyoung Park, Seong-Bae Park
http://doi.org/10.5626/JOK.2019.46.6.535
Neural attentional sequence-to-sequence models have achieved great success in abstractive summarization. However, the model is limited by several challenges including repetitive generation of words, phrase and sentences in the decoding step. Many studies have attempted to address the problem by modifying the model structure. Although the consideration of actual history of word generation is crucial to reduce word repetition, these methods, however, do not consider the decoding history of generated sequence. In this paper, we propose a new loss function, called ‘Repeat Loss’ to avoid repetitions. The Repeat Loss directly prevents the model from repetitive generation of words by giving a loss penalty to the generation probability of words already generated in the decoding history. Since the propose Repeat Loss does not need a special network structure, the loss function is applicable to any existing sequence-to-sequence models. In experiments, we applied the Repeat Loss to a number of sequence-to-sequence model based summarization systems and trained them on both Korean and CNN/Daily Mail summarization datasets. The results demonstrate that the proposed method reduced repetitions and produced high-quality summarization.
Resolution of Answer-Repetition Problems in a Generative Question-Answering Chat System
http://doi.org/10.5626/JOK.2018.45.9.925
A question-answering (QA) chat system is a chatbot that responds to simple factoid questions by retrieving information from knowledge bases. Recently, many chat systems based on sequence-to-sequence neural networks have been implemented and have shown new possibilities for generative models. However, the generative chat systems have word repetition problems, in that the same words in a response are repeatedly generated. A QA chat system also has similar problems, in that the same answer expressions frequently appear for a given question and are repeatedly generated. To resolve this answer-repetition problem, we propose a new sequence-to-sequence model reflecting a coverage mechanism and an adaptive control of attention (ACA) mechanism in a decoder. In addition, we propose a repetition loss function reflecting the number of unique words in a response. In the experiments, the proposed model performed better than various baseline models on all metrics, such as accuracy, BLEU, ROUGE-1, ROUGE-2, ROUGE-L, and Distinct-1.
δ-approximate Periods and γ-approximate Periods of Strings over Integer Alphabets
(δ, γ)-matching for strings over integer alphabets can be applied to such fields as musical melody and share prices on stock markets. In this paper, we define δ-approximate periods and γ-approximate periods of strings over integer alphabets. We also present two O(n²) - time algorithms, each of which finds minimum δ-approximate periods and minimum γ-approximate periods, respectively. Then, we provide the experimental results of execution times of both algorithms.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr