Weakly Supervised Abstractive Summarization with Enhancing Factual Consistency for Chinese Complaint Reports
Source abstract
Abstract
A large variety of complaint reports reflect subjective information expressed by citizens. A key challenge of text summarization for complaint reports is to ensure the factual consistency of generated summary. Therefore, in this paper, a simple and weakly supervised framework considering factual consistency is proposed to generate a summary of city-based complaint reports without pre-labeled sentences/words. Furthermore, it considers the importance of entity in complaint reports to ensure factual consistency of summary. Experimental results on the customer review datasets (Yelp and Amazon) and complaint report dataset (complaint reports of Shenyang in China) show that the proposed framework outperforms state-of-the-art approaches in ROUGE scores and human evaluation. It unveils the effectiveness of our approach to helping in dealing with complaint reports.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Sentiment Analysis and Opinion Mining · Advanced Text Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. Diagnosing New York city’s noises with ubiquitous data ubiquitous computing
2. Investigation to the intelligence of urban management under the new situation
3. Recent trends in big data using hadoop10.11591/ijict.v8i1.pp39-49 ↗
4. Harvesting and summarizing user-generated content for advanced speech-based human-computer interaction
5. Opinion mining and summarization of hotel reviews
6. Hierarchical transformers for multi-document summarization
7. Improving transformer with sequential context representations for abstractive text summarization10.1007/978-3-030-32233-5_40 ↗
8. Compressive approaches for cross-language multi-document summarization10.1016/j.datak.2019.101763 ↗
9. A neural attention model for abstractive sentence summarization
10. Sequence level training with recurrent neural networks
11. A hierarchical neural autoencoder for paragraphs and documents
12. Extractive summarization with swap-net: Sentences and words from alternating pointer networks
13. Abstractive document summarization with a graph-based attentional neural model
14. Weakly supervised extractive summarization with attention
15. OpinionDigest: A simple framework for opinion summarization
16. Meansum: A neural model for unsupervised multi-document abstractive summarization
17. Unsupervised opinion summarization as copycat-review generation
18. Learning structured text representations10.1162/tacl_a_00005 ↗
19. Faithful to the original: Fact aware neural abstractive summarization
20. Enhancing factual consistency of abstractive summarization
21. Opinosis: A graph-based approach to abstractive summarization of highly redundant opinions
22. Semi-supervised aspect-level sentiment classification model based on variational autoencoder10.1016/j.knosys.2019.02.008 ↗
23. Unsupervised opinion summarization with content planning
24. A hybrid approach to multi-document summarization of opinions in reviews
25. Character-based LSTM-CRF with radical-level features for Chinese named entity recognition10.1007/978-3-319-50496-4_20 ↗
26. A deep learning model incorporating part of speech and self-matching attention for named entity recognition of Chinese electronic medical records10.1186/s12911-019-0762-7 ↗
27. An attention-based BiLSTM-CRF model for Chinese clinic named entity recognition10.1109/ACCESS.2019.2935223 ↗
28. An attention-based deep learning model for clinical named entity recognition of Chinese electronic medical records10.1186/s12911-019-0933-6 ↗
29. Bidirectional LSTM-CRF for named entity recognition
30. An empirical study of low-resource neural machine translation of manipuri in multilingual settings10.1007/s00521-022-07337-8 ↗
31. T-PAIR: Temporal node-pair embedding for automatic biomedical hypothesis generation
32. Text summarization with pretrained encoders
33. BERT: Pre-training of deep bidirectional transformers for language understanding
34. Unified language model pre-training for natural language understanding and generation
35. TransSum: Translating aspect and sentiment embeddings for self-supervised opinion summarization
36. Ups and downs: modeling the visual evolution of fashion trends with one-class collaborative filtering
37. Attention is all you need
38. Rouge: A package for automatic evaluation of summaries
39. Lexrank: Graph-based lexical centrality as salience in text summarization10.1613/jair.1523 ↗
40. ConsistSum: unsupervised opinion summarization with the consistency of aspect, Sentiment and Semantic
41. Contextualized rewriting for text summarization10.1609/aaai.v35i14.17487 ↗