# Bridging Background Knowledge Gaps in Translation with Automatic Explicitation

arXiv: https://arxiv.org/abs/2312.01308 · HTML: https://mlsanity.com/paper/2312.01308/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 56 references that are in the map.
- First posted on arXiv 3 Dec 2023.

## Builds on (most cited first, 17 of 17)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia](https://mlsanity.com/paper/1907.05791/) (2019)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information](https://mlsanity.com/paper/1805.04655/) (2018)
- [Benchmarking Machine Translation with Cultural Awareness](https://mlsanity.com/paper/2305.14328/) (2023)
- [Answer-based Adversarial Training for Generating Clarification Questions](https://mlsanity.com/paper/1904.02281/) (2019)
- [Quizbowl: The Case for Incremental Question Answering](https://mlsanity.com/paper/1904.04792/) (2019)
- [Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification](https://mlsanity.com/paper/2010.10035/) (2020)
- [Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank](https://mlsanity.com/paper/2010.03662/) (2020)
- [Elaborative Simplification as Implicit Questions Under Discussion](https://mlsanity.com/paper/2305.10387/) (2023)
- [Multilinguals and Wikipedia Editing](https://mlsanity.com/paper/1312.0976/) (2013)
- [Identifying Semantic Divergences in Parallel Text without Annotations](https://mlsanity.com/paper/1803.11112/) (2018)
- [The Tower of Babel Meets Web 2.0: User-Generated Content and its Applications in a Multilingual Context](https://mlsanity.com/paper/1904.01689/) (2019)
- [Audience-specific Explanations for Machine Translation](https://mlsanity.com/paper/2309.12998/) (2023)
- [Analysing Coreference in Transformer Outputs](https://mlsanity.com/paper/1911.01188/) (2019)

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

- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [Cultural Adaptation of Menus: A Fine-Grained Approach](https://mlsanity.com/paper/2408.13534/) (2024)
- [An Interdisciplinary Approach to Human-Centered Machine Translation](https://mlsanity.com/paper/2506.13468/) (2025)
- [Explanatory Summarization with Discourse-Driven Planning](https://mlsanity.com/paper/2504.19339/) (2025)
- [Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translation](https://mlsanity.com/paper/2509.23395/) (2025)
- [Toward Machine Interpreting: Lessons from Human Interpreting Studies](https://mlsanity.com/paper/2508.07964/) (2025)
- [PETra: A Multilingual Corpus of Pragmatic Explicitation in Translation](https://mlsanity.com/paper/2511.02721/) (2025)

## Abstract (arXiv)

Translations help people understand content written in another language. However, even correct literal translations do not fulfill that goal when people lack the necessary background to understand them. Professional translators incorporate explicitations to explain the missing context by considering cultural differences between source and target audiences. Despite its potential to help users, NLP research on explicitation is limited because of the dearth of adequate evaluation methods. This work introduces techniques for automatically generating explicitations, motivated by WikiExpl: a dataset that we collect from Wikipedia and annotate with human translators. The resulting explicitations are useful as they help answer questions more accurately in a multilingual question answering framework.