# Answering Subjective Induction Questions on Products by Summarizing Multi-sources Multi-viewpoints Knowledge

arXiv: https://arxiv.org/abs/2309.05938 · HTML: https://mlsanity.com/paper/2309.05938/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 12 Sep 2023.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge](https://mlsanity.com/paper/1805.07858/) (2018)
- [Commonsense for Generative Multi-Hop Question Answering Tasks](https://mlsanity.com/paper/1809.06309/) (2018)
- [AmazonQA: A Review-Based Question Answering Task](https://mlsanity.com/paper/1908.04364/) (2019)
- [Neural Natural Language Inference Models Enhanced with External Knowledge](https://mlsanity.com/paper/1711.04289/) (2017)
- [Incorporating External Knowledge through Pre-training for Natural Language to Code Generation](https://mlsanity.com/paper/2004.09015/) (2020)
- [Addressing Complex and Subjective Product-Related Queries with Customer Reviews](https://mlsanity.com/paper/1512.06863/) (2015)
- [Product-Aware Answer Generation in E-Commerce Question-Answering](https://mlsanity.com/paper/1901.07696/) (2019)
- [Unsupervised Opinion Summarization with Content Planning](https://mlsanity.com/paper/2012.07808/) (2020)
- [WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarization](https://mlsanity.com/paper/2011.01421/) (2020)
- [Data Augmentation for Abstractive Query-Focused Multi-Document Summarization](https://mlsanity.com/paper/2103.01863/) (2021)
- [Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce](https://mlsanity.com/paper/2008.11972/) (2020)
- [Product Question Answering in E-Commerce: A Survey](https://mlsanity.com/paper/2302.08092/) (2023)

## Abstract (arXiv)

This paper proposes a new task in the field of Answering Subjective Induction Question on Products (SUBJPQA). The answer to this kind of question is non-unique, but can be interpreted from many perspectives. For example, the answer to 'whether the phone is heavy' has a variety of different viewpoints. A satisfied answer should be able to summarize these subjective opinions from multiple sources and provide objective knowledge, such as the weight of a phone. That is quite different from the traditional QA task, in which the answer to a factoid question is unique and can be found from a single data source. To address this new task, we propose a three-steps method. We first retrieve all answer-related clues from multiple knowledge sources on facts and opinions. The implicit commonsense facts are also collected to supplement the necessary but missing contexts. We then capture their relevance with the questions by interactive attention. Next, we design a reinforcement-based summarizer to aggregate all these knowledgeable clues. Based on a template-controlled decoder, we can output a comprehensive and multi-perspective answer. Due to the lack of a relevant evaluated benchmark set for the new task, we construct a large-scale dataset, named SupQA, consisting of 48,352 samples across 15 product domains. Evaluation results show the effectiveness of our approach.