# DAHRS: Divergence-Aware Hallucination-Remediated SRL Projection

arXiv: https://arxiv.org/abs/2407.09283 · HTML: https://mlsanity.com/paper/2407.09283/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 12 Jul 2024.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [Achieving Human Parity on Automatic Chinese to English News Translation](https://mlsanity.com/paper/1803.05567/) (2018)
- [Towards Explainable NLP: A Generative Explanation Framework for Text Classification](https://mlsanity.com/paper/1811.00196/) (2018)
- [Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus](https://mlsanity.com/paper/2004.06295/) (2020)
- [X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset](https://mlsanity.com/paper/2010.01998/) (2020)
- [Towards Semi-Supervised Learning for Deep Semantic Role Labeling](https://mlsanity.com/paper/1808.09543/) (2018)
- [Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling](https://mlsanity.com/paper/1908.11326/) (2019)
- [Polyglot Semantic Role Labeling](https://mlsanity.com/paper/1805.11598/) (2018)
- [From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domains](https://mlsanity.com/paper/2203.10659/) (2022)

## Built on by (most cited first, 3 of 3)

- [Effective QA-driven Annotation of Predicate-Argument Relations Across Languages](https://mlsanity.com/paper/2602.22865/) (2026)
- [Revisiting Semantic Role Labeling: Efficient Structured Inference with Dependency-Informed Analysis](https://mlsanity.com/paper/2605.02505/) (2026)
- [REFLECT: Role-Aware Detection of Sentiment, Emotion, Politeness, and Formality](https://mlsanity.com/paper/2610.13797/) (2026)

## Abstract (arXiv)

Semantic role labeling (SRL) enriches many downstream applications, e.g., machine translation, question answering, summarization, and stance/belief detection. However, building multilingual SRL models is challenging due to the scarcity of semantically annotated corpora for multiple languages. Moreover, state-of-the-art SRL projection (XSRL) based on large language models (LLMs) yields output that is riddled with spurious role labels. Remediation of such hallucinations is not straightforward due to the lack of explainability of LLMs. We show that hallucinated role labels are related to naturally occurring divergence types that interfere with initial alignments. We implement Divergence-Aware Hallucination-Remediated SRL projection (DAHRS), leveraging linguistically-informed alignment remediation followed by greedy First-Come First-Assign (FCFA) SRL projection. DAHRS improves the accuracy of SRL projection without additional transformer-based machinery, beating XSRL in both human and automatic comparisons, and advancing beyond headwords to accommodate phrase-level SRL projection (e.g., EN-FR, EN-ES). Using CoNLL-2009 as our ground truth, we achieve a higher word-level F1 over XSRL: 87.6% vs. 77.3% (EN-FR) and 89.0% vs. 82.7% (EN-ES). Human phrase-level assessments yield 89.1% (EN-FR) and 91.0% (EN-ES). We also define a divergence metric to adapt our approach to other language pairs (e.g., English-Tagalog).