# Semantic Sentence Composition Reasoning for Multi-Hop Question Answering

arXiv: https://arxiv.org/abs/2203.00160 · HTML: https://mlsanity.com/paper/2203.00160/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 1 Mar 2022.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [QASC: A Dataset for Question Answering via Sentence Composition](https://mlsanity.com/paper/1910.11473/) (2019)
- [Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents](https://mlsanity.com/paper/1911.00484/) (2019)
- [Careful Selection of Knowledge to solve Open Book Question Answering](https://mlsanity.com/paper/1907.10738/) (2019)
- [Multi-Hop Paragraph Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/1906.06606/) (2019)
- [A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations](https://mlsanity.com/paper/1511.08277/) (2015)
- [MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension](https://mlsanity.com/paper/1910.00458/) (2019)
- [Course Concept Expansion in MOOCs with External Knowledge and Interactive Game](https://mlsanity.com/paper/1909.07739/) (2019)
- [A Deep Cascade Model for Multi-Document Reading Comprehension](https://mlsanity.com/paper/1811.11374/) (2018)
- [Modeling Semantic Compositionality with Sememe Knowledge](https://mlsanity.com/paper/1907.04744/) (2019)
- [What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering](https://mlsanity.com/paper/1909.09253/) (2019)
- [Training a Ranking Function for Open-Domain Question Answering](https://mlsanity.com/paper/1804.04264/) (2018)

## Built on by (most cited first, 1 of 1)

- [A Comprehensive Survey on Multi-hop Machine Reading Comprehension Datasets and Metrics](https://mlsanity.com/paper/2212.04070/) (2022)

## Abstract (arXiv)

Due to the lack of insufficient data, existing multi-hop open domain question answering systems require to effectively find out relevant supporting facts according to each question. To alleviate the challenges of semantic factual sentences retrieval and multi-hop context expansion, we present a semantic sentence composition reasoning approach for a multi-hop question answering task, which consists of two key modules: a multi-stage semantic matching module (MSSM) and a factual sentence composition module (FSC). With the combination of factual sentences and multi-stage semantic retrieval, our approach can provide more comprehensive contextual information for model training and reasoning. Experimental results demonstrate our model is able to incorporate existing pre-trained language models and outperform the existing SOTA method on the QASC task with an improvement of about 9%.