LSPGS Wikipedia Long Sentences Summarization System

A LSPGS Wikipedia Long Sentences Summarization System is a Multi-Document Text Summarization System that can solve a LSPGS Wikipedia Long Sentences Summarization Task by implementing LSPGS Wikipedia Long Sentences Summarization Algorithms.

• AKA: Liu-Saleh-Pot-Goodrich-Sepassi Wikipedia Long Sentences Summarization System, Liu's Wikipedia Long Sentences Summarization System.
• Context:
  • It was developed by Liu et al. (2018).
  • GitHub Repository: https://github.com/tensorflow/tensor2tensor/tree/master/tensor2tensor/data_generators/wikisum
  • System's Architecture:
    • It is a two-stage text summarization system: Extractive Summarization + Abstractive Summarization.
    • Data representation is based on a sub-word tokenization system (Wu et al., 2016).
  • Training and other ML Tools:
    • seq2seq-attn models are trained to optimize maximum likelihood objective.
    • It uses the open-source tensor tensor library for the training of abstractive models.
    • It uses a beam search of size 4 with length alpha=0.6 during decoding (Wu et al., 2016).
• Example(s):
  • …
• Counter-Example(s):
  • CJS Neural Narrative Text Generation System,
  • LKW Data-To-Text Generation System,
  • Texygen.
• See: Abstractive Text Summarization System, Neural Abstractive Summarization System, Self-Attention Mechanism, Sequence-to-Sequence (seq2seq) Neural Network, Natural Language Generation System, Natural Language Understanding System, Natural Language Translation System, Natural Language Processing System.

---

---

References

2018

• (Liu et al., 2018) ⇒ Peter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, and Noam Shazeer. (2018). “Generating Wikipedia by Summarizing Long Sequences.” In: Proceedings of the Sixth International Conference on Learning Representations (ICLR-2018).

2017

• (Vaswani et al., 2017) ⇒ Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. (2017). “Attention is all You Need.” In: Advances in Neural Information Processing Systems.

2016a

• (Nallapati et al., 2016) ⇒ Ramesh Nallapati, Bowen Zhou, Cicero Nogueira dos Santos, Caglar Gulcehre, and Bing Xiang. (2016). “Abstractive Text Summarization Using Sequence-to-sequence RNNs and Beyond.” In: Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL 2016). DOI:10.18653/v1/K16-1028.

2016b

• (Wu et al., 2016) ⇒ Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, and 27 co-authors. (2016). "Google's Neural Machine Translation System: Bridging the Gap Between Human and Machine Translation". In: arXiv:1609.08144.

2015

• (Bahdanau et al., 2015) ⇒ Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. (2015). “Neural Machine Translation by Jointly Learning to Align and Translate.” In: Proceedings of the Third International Conference on Learning Representations, (ICLR-2015).

2005

• (Nenkova & Vanderwende, 2005) ⇒ Ani Nenkova, and Lucy Vanderwende (2005). "The Impact of Frequency on Summarization". Microsoft Research, Redmond, Washington, Tech. Rep. MSR-TR-2005, 101.

2004

• (Mihalcea & Tarau, 2004) ⇒ Rada Mihalcea, and Paul Tarau. (2004). “TextRank: Bringing Order into Texts.” In: Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP 2004)

2003a

• (Graff & Cieri, 2003) ⇒ David Graff, and Christopher Cieri (2003). "English Gigaword". Linguistic Data Consortium, Philadelphia, 2003.
  • QUOTE: English Gigaword was produced by Linguistic Data Consortium (LDC) catalog number LDC2003T05 and ISBN 1-58563-260-0, and is distributed on DVD. This is a comprehensive archive of newswire text data in English that has been acquired over several years by the LDC.

    Four distinct international sources of English newswire are represented here:

    • Agence France Press English Service (afe).
    • Associated Press Worldstream English Service (apw).
    • The New York Times Newswire Service (nyt).
    • The Xinhua News Agency English Service (xie)

2003b

• (Ramos, 2003) ⇒ Juan Ramos (2003). "Using TF-IDF to Determine Word Relevance in Document Queries". In: Proceedings of the first instructional conference on Machine Learning, volume 242, pp. 133–142.

---