# SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases

arXiv: https://arxiv.org/abs/2109.13430 · HTML: https://mlsanity.com/paper/2109.13430/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 36 references that are in the map.
- First posted on arXiv 28 Sep 2021.

## Builds on (most cited first, 11 of 11)

- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text](https://mlsanity.com/paper/1809.00782/) (2018)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [Question Answering Over Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.01515/) (2021)
- [Leveraging Abstract Meaning Representation for Knowledge Base Question Answering](https://mlsanity.com/paper/2012.01707/) (2020)
- [A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges](https://mlsanity.com/paper/2007.13069/) (2020)
- [Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering](https://mlsanity.com/paper/1808.04126/) (2018)
- [AMR Parsing with Action-Pointer Transformer](https://mlsanity.com/paper/2104.14674/) (2021)
- [Message Passing for Complex Question Answering over Knowledge Graphs](https://mlsanity.com/paper/1908.06917/) (2019)
- [Pushing the Limits of AMR Parsing with Self-Learning](https://mlsanity.com/paper/2010.10673/) (2020)
- [CFO: A Framework for Building Production NLP Systems](https://mlsanity.com/paper/1908.06121/) (2019)

## Built on by (most cited first, 8 of 8)

- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [TempoQR: Temporal Question Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2112.05785/) (2021)
- [A Two-Stage Approach towards Generalization in Knowledge Base Question Answering](https://mlsanity.com/paper/2111.05825/) (2021)
- [A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases](https://mlsanity.com/paper/2201.05793/) (2022)
- [Temporal Knowledge Graph Question Answering: A Survey](https://mlsanity.com/paper/2406.14191/) (2024)
- [GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering](https://mlsanity.com/paper/2303.13284/) (2023)
- [Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning](https://mlsanity.com/paper/2601.18296/) (2026)
- [Learning to Transpile AMR into SPARQL](https://mlsanity.com/paper/2112.07877/) (2021)

## Abstract (arXiv)

Knowledge Base Question Answering (KBQA) tasks that in-volve complex reasoning are emerging as an important re-search direction. However, most KBQA systems struggle withgeneralizability, particularly on two dimensions: (a) acrossmultiple reasoning types where both datasets and systems haveprimarily focused on multi-hop reasoning, and (b) across mul-tiple knowledge bases, where KBQA approaches are specif-ically tuned to a single knowledge base. In this paper, wepresent SYGMA, a modular approach facilitating general-izability across multiple knowledge bases and multiple rea-soning types. Specifically, SYGMA contains three high levelmodules: 1) KB-agnostic question understanding module thatis common across KBs 2) Rules to support additional reason-ing types and 3) KB-specific question mapping and answeringmodule to address the KB-specific aspects of the answer ex-traction. We demonstrate effectiveness of our system by evalu-ating on datasets belonging to two distinct knowledge bases,DBpedia and Wikidata. In addition, to demonstrate extensi-bility to additional reasoning types we evaluate on multi-hopreasoning datasets and a new Temporal KBQA benchmarkdataset on Wikidata, namedTempQA-WD1, introduced in thispaper. We show that our generalizable approach has bettercompetetive performance on multiple datasets on DBpediaand Wikidata that requires both multi-hop and temporal rea-soning