# Linguistically-Informed Self-Attention for Semantic Role Labeling

arXiv: https://arxiv.org/abs/1804.08199 · HTML: https://mlsanity.com/paper/1804.08199/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2018.

## Built on by (most cited first, 30 of 71)

- [Visual Semantic Role Labeling for Video Understanding](https://mlsanity.com/paper/2104.00990/) (2021)
- [Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees](https://mlsanity.com/paper/2103.04350/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale](https://mlsanity.com/paper/2203.00633/) (2022)
- [Local-Global Context Aware Transformer for Language-Guided Video Segmentation](https://mlsanity.com/paper/2203.09773/) (2022)
- [Link Prediction on N-ary Relational Facts: A Graph-based Approach](https://mlsanity.com/paper/2105.08476/) (2021)
- [Structural Guidance for Transformer Language Models](https://mlsanity.com/paper/2108.00104/) (2021)
- [Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing](https://mlsanity.com/paper/2110.15534/) (2021)
- [Semantic Representation for Dialogue Modeling](https://mlsanity.com/paper/2105.10188/) (2021)
- [End-to-end Semantic Role Labeling with Neural Transition-based Model](https://mlsanity.com/paper/2101.00394/) (2021)
- [Attention Can Reflect Syntactic Structure (If You Let It)](https://mlsanity.com/paper/2101.10927/) (2021)
- [Do Context-Aware Translation Models Pay the Right Attention?](https://mlsanity.com/paper/2105.06977/) (2021)
- [GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement](https://mlsanity.com/paper/2208.08965/) (2022)
- [Pushdown Layers: Encoding Recursive Structure in Transformer Language Models](https://mlsanity.com/paper/2310.19089/) (2023)
- [Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion](https://mlsanity.com/paper/2210.08471/) (2022)
- [Sentence-level Privacy for Document Embeddings](https://mlsanity.com/paper/2205.04605/) (2022)
- [Cloth Interactive Transformer for Virtual Try-On](https://mlsanity.com/paper/2104.05519/) (2021)
- [Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments](https://mlsanity.com/paper/2110.06865/) (2021)
- [Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph](https://mlsanity.com/paper/2210.03037/) (2022)
- [Video Question Answering with Phrases via Semantic Roles](https://mlsanity.com/paper/2104.03762/) (2021)
- [Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection](https://mlsanity.com/paper/2203.14380/) (2022)
- [Does injecting linguistic structure into language models lead to better alignment with brain recordings?](https://mlsanity.com/paper/2101.12608/) (2021)
- [Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation](https://mlsanity.com/paper/2306.06480/) (2023)
- [Syntax-augmented Multilingual BERT for Cross-lingual Transfer](https://mlsanity.com/paper/2106.02134/) (2021)
- [Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions](https://mlsanity.com/paper/2402.13551/) (2024)
- [The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?](https://mlsanity.com/paper/2601.07220/) (2026)
- [Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling](https://mlsanity.com/paper/2112.07874/) (2021)
- [SketchXAI: A First Look at Explainability for Human Sketches](https://mlsanity.com/paper/2304.11744/) (2023)
- [Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling](https://mlsanity.com/paper/2104.07704/) (2021)
- [Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Models](https://mlsanity.com/paper/2407.17406/) (2024)

## Abstract (arXiv)

Current state-of-the-art semantic role labeling (SRL) uses a deep neural network with no explicit linguistic features. However, prior work has shown that gold syntax trees can dramatically improve SRL decoding, suggesting the possibility of increased accuracy from explicit modeling of syntax. In this work, we present linguistically-informed self-attention (LISA): a neural network model that combines multi-head self-attention with multi-task learning across dependency parsing, part-of-speech tagging, predicate detection and SRL. Unlike previous models which require significant pre-processing to prepare linguistic features, LISA can incorporate syntax using merely raw tokens as input, encoding the sequence only once to simultaneously perform parsing, predicate detection and role labeling for all predicates. Syntax is incorporated by training one attention head to attend to syntactic parents for each token. Moreover, if a high-quality syntactic parse is already available, it can be beneficially injected at test time without re-training our SRL model. In experiments on CoNLL-2005 SRL, LISA achieves new state-of-the-art performance for a model using predicted predicates and standard word embeddings, attaining 2.5 F1 absolute higher than the previous state-of-the-art on newswire and more than 3.5 F1 on out-of-domain data, nearly 10% reduction in error. On ConLL-2012 English SRL we also show an improvement of more than 2.5 F1. LISA also out-performs the state-of-the-art with contextually-encoded (ELMo) word representations, by nearly 1.0 F1 on news and more than 2.0 F1 on out-of-domain text.