# How to best use Syntax in Semantic Role Labelling

arXiv: https://arxiv.org/abs/1906.00266 · HTML: https://mlsanity.com/paper/1906.00266/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2019.

## Built on by (most cited first, 11 of 11)

- [4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees](https://mlsanity.com/paper/2310.14319/) (2023)
- [Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing](https://mlsanity.com/paper/2108.07556/) (2021)
- [On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations](https://mlsanity.com/paper/2101.11492/) (2021)
- [A Syntax-Injected Approach for Faster and More Accurate Sentiment Analysis](https://mlsanity.com/paper/2406.15163/) (2024)
- [Dancing in the syntax forest: fast, accurate and explainable sentiment analysis with SALSA](https://mlsanity.com/paper/2406.16071/) (2024)
- [COMBO: a new module for EUD parsing](https://mlsanity.com/paper/2107.03809/) (2021)
- [Cited Text Spans for Citation Text Generation](https://mlsanity.com/paper/2309.06365/) (2023)
- [NLPre: a revised approach towards language-centric benchmarking of Natural Language Preprocessing systems](https://mlsanity.com/paper/2403.04507/) (2024)
- [Lexicalized Constituency Parsing for Middle Dutch: Low-resource Training and Cross-Domain Generalization](https://mlsanity.com/paper/2601.07008/) (2026)
- [FrameNet Semantic Role Classification by Analogy](https://mlsanity.com/paper/2603.19825/) (2026)
- [Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing](https://mlsanity.com/paper/2605.13373/) (2026)

## Abstract (arXiv)

There are many different ways in which external information might be used in an NLP task. This paper investigates how external syntactic information can be used most effectively in the Semantic Role Labeling (SRL) task. We evaluate three different ways of encoding syntactic parses and three different ways of injecting them into a state-of-the-art neural ELMo-based SRL sequence labelling model. We show that using a constituency representation as input features improves performance the most, achieving a new state-of-the-art for non-ensemble SRL models on the in-domain CoNLL'05 and CoNLL'12 benchmarks.