# Neural Machine Translation for Query Construction and Composition

arXiv: https://arxiv.org/abs/1806.10478 · HTML: https://mlsanity.com/paper/1806.10478/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2018.

## Built on by (most cited first, 7 of 7)

- [Knowledge Graph Question Answering using Graph-Pattern Isomorphism](https://mlsanity.com/paper/2103.06752/) (2021)
- [SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding](https://mlsanity.com/paper/2407.01626/) (2024)
- [MST5 -- Multilingual Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2407.06041/) (2024)
- [Conversational Lexicography: Querying Lexicographic Data on Knowledge Graphs with SPARQL through Natural Language](https://mlsanity.com/paper/2505.19971/) (2025)
- [Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering](https://mlsanity.com/paper/2205.12768/) (2022)
- [Towards Natural Language Question Answering over Earth Observation Linked Data using Attention-based Neural Machine Translation](https://mlsanity.com/paper/2101.09427/) (2021)
- [Towards Researcher Agents for Knowledge-Graph Question Answering](https://mlsanity.com/paper/2608.07700/) (2026)

## Abstract (arXiv)

Research on question answering with knowledge base has recently seen an increasing use of deep architectures. In this extended abstract, we study the application of the neural machine translation paradigm for question parsing. We employ a sequence-to-sequence model to learn graph patterns in the SPARQL graph query language and their compositions. Instead of inducing the programs through question-answer pairs, we expect a semi-supervised approach, where alignments between questions and queries are built through templates. We argue that the coverage of language utterances can be expanded using late notable works in natural language generation.