SRL

Syntax in End-to-End Natural Language Processing (2021.emnlp-tutorials)

Challenge:	Existing studies in cross-lingual semantic role labeling (SRL) lack a comprehensive analysis of their network selection.
Approach:	They compare the transferability of graph neural network-based models with universal dependency trees to English and 23 target languages.
Outcome:	The proposed models perform better in resource-poor languages than in resource rich ones.

Copied to clipboard

Hai Zhao, Rui Wang, Kehai Chen

CRAPES:Cross-modal Annotation Projection for Visual Semantic Role Labeling (2023.starsem-1)

Challenge:	tutorial focuses on syntactic parsing and syntax in end-to-end natural language processing (NLP) tasks.
Approach:	tutorial will introduce syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks.
Outcome:	This tutorial will introduce the background and the latest progress of syntactic parsing and SRL/NMT.

Copied to clipboard

Abhidip Bhattacharyya, Martha Palmer, Christoffer Heckman

Semantic-Aware Dynamic Retrospective-Prospective Reasoning for Event-Level Video Question Answering (2023.acl-srw)

Challenge:	Existing approaches to image comprehension limit the image to a single action, while text-based approaches label all actions in a sentence.
Approach:	They propose to expand GSR to follow more liberal text-based approach to action and participant identification.
Outcome:	The proposed approach improves image comprehension on a SWiG dataset by 28.6 points.

Copied to clipboard

Chenyang Lyu, Tianbo Ji, Yvette Graham, Jennifer Foster

InVeRo: Making Semantic Role Labeling Accessible with Intelligible Verbs and Roles (2020.emnlp-demos)

Challenge:	Event-Level Video Question Answering (EVQA) requires complex reasoning across video events to obtain the visual information needed to provide optimal answers.
Approach:	They propose a semantic-aware dynamic retrospective-prospective reasoning approach for video-based question answering that explicitly uses the Semantic Role Labeling (SRL) structure of the question in the dynamic reasoning process.
Outcome:	The proposed model outperforms existing models on a trafficQA benchmark dataset.

Copied to clipboard

Simone Conia, Fabrizio Brignone, Davide Zanfardino, Roberto Navigli

Bootstrapping Small & High Performance Language Models with Unmasking-Removal Training Policy (2023.emnlp-main)

Challenge:	Semantic Role Labeling (SRL) is dependent on complex linguistic resources and sophisticated neural models, which makes the task difficult to approach for non-experts.
Approach:	They propose a platform for semantic role labeling that provides verb sense and semantic role information with an easy to use Web interface and RESTful APIs.
Outcome:	The proposed system provides human-readable verb sense and semantic role information with an easy to use Web interface and RESTful APIs.

Copied to clipboard

Yahan Yang, Elior Sulem, Insup Lee, Dan Roth

Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources (2021.naacl-main)

Challenge:	Large-scale pre-trained language models (LMs) have shown promising ability on handling various downstream tasks including textual classification and question answering.
Approach:	They propose to use BabyBERTa to train child-directed speech without unmasking words while masking parameters to improve grammatical accuracy.
Outcome:	The proposed model achieves grammatical ability comparable to RoBERTa-base model, which is trained on 6,000 times more words and 15 times more parameters.

Copied to clipboard

Simone Conia, Andrea Bacciu, Roberto Navigli

Leveraging Active Learning to Minimise SRL Annotation Across Corpora (2023.starsem-1)

Challenge:	Using cross-lingual techniques to perform Semantic Role Labeling (SRL) has been limited by the fact that each language adopts its own linguistic formalism .
Approach:	They propose a unified model to perform cross-lingual SRL over heterogeneous linguistic resources.
Outcome:	The proposed model is able to annotate a sentence in a single forward pass with all the inventories it was trained with, providing a tool for the analysis and comparison of linguistic theories across different languages.

Copied to clipboard

Skatje Myers, Martha Palmer

Character-Level Models versus Morphology in Semantic Role Labeling (P18-1)

Challenge:	In this paper, we investigate the application of active learning to semantic role labeling (SRL) using Bayesian Active Learning by Disagreement (BALD).
Approach:	They propose a sentence-focused selection method that is based off of previous methods of using model dropout to approximate a Gaussian process for SRL.
Outcome:	The proposed selection method improves on three different domain corpora on three domains with a large and diverse corpus.

Copied to clipboard

Gözde Gül Şahin, Mark Steedman

Simple Temperature Cool-down in Contrastive Framework for Unsupervised Sentence Representation Learning (2024.findings-eacl)

Challenge:	Character-level models are used for high-level semantic analysis tasks such as semantic role labeling.
Approach:	They train character-level models that use word, character and morphology level information . they analyze how performance of characters compare to words and a variety of morphological typologies .
Outcome:	The results shed light on important characteristics of character-level models and their semantic capability.

Copied to clipboard

Yoo Hyun Jeong, Myeong Soo Han, Dong-Kyu Chae

A Novel Workflow for Accurately and Efficiently Crowdsourcing Predicate Senses and Argument Labels (2020.findings-emnlp)

Challenge:	Existing studies have focused on the effectiveness of contrastive learning in deep learning.
Approach:	They propose a method to improve sentence representation of unsupervised contrastive learning by examining the role of temperature in VRL and SRL.
Outcome:	The proposed method improves representation of unsupervised contrastive learning by cooling the temperature of the representation space.

Copied to clipboard

Youxuan Jiang, Huaiyu Zhu, Jonathan K. Kummerfeld, Yunyao Li, Walter Lasecki

Bootstrap Your Own PLM: Boosting Semantic Features of PLMs for Unsuperivsed Contrastive Learning (2024.findings-eacl)

Challenge:	Prior attempts to develop crowdsourcing methods have either had low accuracy or required substantial expert annotation.
Approach:	They propose a multi-stage crowd workflow that reduces expert involvement without sacrificing accuracy.
Outcome:	The proposed method reduces expert effort by 4x, from 56% to 14% of cases.

Copied to clipboard

Yoo Hyun Jeong, Myeong Soo Han, Dong-Kyu Chae

An Analysis under a Unified Formulation of Learning Algorithms with Output Constraints (2024.acl-srw)

Challenge:	Existing studies have shown that SimCSE significantly improves the performance of pretrained language models on the sentence representation benchmark.
Approach:	They propose a method called IFM which reduces the tendency of contrastive models for VRL to rely on feature-suppressing shortcut solutions.
Outcome:	The proposed method reduces the tendency of contrastive models for VRL to rely on feature-suppressing shortcut solutions.

Copied to clipboard

Mooho Song, Jay-Yoon Lee

Challenge:	Existing work on NN models with output constraints has not been able to categorize them in a unified manner.
Approach:	They propose new algorithms to integrate the information of main task and constraint injection . they use the H-score as a metric for considering main task metric and constrain infringement simultaneously .
Outcome:	The proposed algorithms integrate the information of main task and constraint injection, inspired by continual-learning algorithms.

Better Combine Them Together! Integrating Syntactic Constituency and Dependency Representations for Semantic Role Labeling (2021.findings-acl)

Copied to clipboard

Hao Fei, Shengqiong Wu, Yafeng Ren, Fei Li, Donghong Ji

SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling (N18-1)

Challenge:	Existing studies use only one singleton syntax for semantic role labeling (SRL).
Approach:	They propose a TreeLSTM-based integration that integrates phrasal boundaries and semantic relations from dependency into a labelaware GCN solution for simultaneously modeling syntactic edges and labels.
Outcome:	The proposed system achieves state-of-the-art performance on span-based and dependency-based SRL.

Copied to clipboard

Ana Marasović, Anette Frank

Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling (D19-1)

Challenge:	Recent neural approaches do not outperform the state-of-the-art feature-based models for Opinion Role Labeling (ORL).
Approach:	They propose to use multi-task learning to improve Opinion Role Labeling by using a related task which has substantially more data.
Outcome:	The proposed model outperforms the state-of-the-art model for Opinion Role Labeling (ORL) with more data.

Copied to clipboard

Angel Daza, Anette Frank

Syntax-Enhanced Self-Attention-Based Semantic Role Labeling (D19-1)

Challenge:	Unlike annotation projection techniques, our model does not need parallel data during inference time.
Approach:	They propose a cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with semantic role annotations in a resource-poor target language.
Outcome:	The proposed model can be applied in monolingual, multilingual and cross-lingual settings and produces dependency-based and span-based annotations.

Copied to clipboard

Yue Zhang, Rui Wang, Luo Si

Structured Mean-Field Variational Inference for Higher-Order Span-Based Semantic Role Labeling (2023.findings-acl)

Challenge:	Abstract: Syntax is the bridge to semantics, but recent studies have discussed the necessity of syntax in the context of SRL.
Approach:	They propose a syntax-enhanced self-attention model that incorporates syntactic knowledge into the SRL task effectively.
Outcome:	The proposed model achieves state-of-the-art for the Chinese SRL task on the CoNLL-2009 dataset.

Copied to clipboard

Wei Liu, Songlin Yang, Kewei Tu

Enhancing Opinion Role Labeling with Semantic-Aware Word Representations from Semantic Role Labeling (N19-1)

Challenge:	Span-based semantic role labeling is traditionally tackled by BIObased sequence labeling approaches.
Approach:	They propose to decompose the edge from predicate word to argument span into three different edges, enabling higher-order inference.
Outcome:	The proposed model outperforms vanilla MFVI on span-based semantic role labeling benchmarks.

Copied to clipboard

Meishan Zhang, Peili Liang, Guohong Fu

Syntax-aware Neural Semantic Role Labeling with Supertags (N19-1)

Challenge:	Existing work on opinion role labeling (ORL) is highly correlative with semantic role labeled (SRL) SRL is used to identify opinion holders and holder expressions for a given predicate.
Approach:	They propose a method to enhance opinion role labeling by presenting semantic-aware word representations which are learned from SRL.
Outcome:	The proposed method outperforms two other methods on a benchmark MPQA corpus and achieves higher F scores.

Copied to clipboard

Jungo Kasai, Dan Friedman, Robert Frank, Dragomir Radev, Owen Rambow

Semi-Supervised Semantic Role Labeling with Cross-View Training (D19-1)

Challenge:	a new syntax-aware model for dependency-based semantic role labeling outperforms syntax-based models for English and Spanish.
Approach:	They propose a syntax-aware model for dependency-based semantic role labeling that outperforms syntax-based models for English and Spanish.
Outcome:	The proposed model outperforms syntax-agnostic models for English and Spanish.

Copied to clipboard

Rui Cai, Mirella Lapata

Semantic Role Labeling with Iterative Structure Refinement (D19-1)

Challenge:	Recent approaches rely on expensive annotations and are unavailable in low resource scenarios (e.g., rare languages or domains).
Approach:	They propose an end-to-end SRL model which leverages unlabeled data and propose to reduce the annotation effort involved via semi-supervised learning.
Outcome:	The proposed model outperforms the state-of-the-art in English and consistently improves performance in other languages, including Chinese, German, and Spanish.

Copied to clipboard

Chunchuan Lyu, Shay B. Cohen, Ivan Titov

High-order Semantic Role Labeling (2020.findings-emnlp)

Challenge:	Modern state-of-the-art methods for semantic role labeling model only local interactions between individual labels .
Approach:	They propose to model local interactions between argument labeling decisions using a refinement network instead of arbitrary interactions between roles and words.
Outcome:	The proposed model outperforms baseline models on all 7 languages and achieves state-of-the-art results on 5 languages, including English.

Copied to clipboard

Zuchao Li, Hai Zhao, Rui Wang, Kevin Parnow

Zero-shot Label-Aware Event Trigger and Argument Classification (2021.findings-acl)

Challenge:	Experimental results show that high-order structural learning techniques are beneficial to SRL models . high-level features and structure learning are not common in deep neural networks .
Approach:	They propose a high-order graph structure for a neural semantic role labeling model . it explicitly considers the isolated predicate-argument pairs and interaction between them .
Outcome:	The proposed model can explicitly consider the isolated predicate-argument pairs and the interaction between the predicates-argoments pairs.

Copied to clipboard

Hongming Zhang, Haoyu Wang, Dan Roth

Information Extraction & Text Mining

Challenge:	Existing work on event extraction relies on labor-intensive annotation, ignoring semantic meaning of event types' labels.
Approach:	They propose a zero-shot event extraction approach that first identifies events with existing tools and then maps them to a given taxonomy of event types in a no-shot manner.
Outcome:	The proposed approach doubles the performance of previous approaches on a ACE-2005 dataset . it leverages label representations induced by pre-trained language models and maps events to the target types .

MuCPAD: A Multi-Domain Chinese Predicate-Argument Dataset (2022.naacl-main)

Copied to clipboard

Yahui Liu, Haoping Yang, Chen Gong, Qingrong Xia, Zhenghua Li, Min Zhang

Challenge:	Recent studies show that shallow semantic role labeling (SRL) performance drops under out-of-domain setting.
Approach:	They propose to annotate a multi-domain Chinese predicate-argument dataset using a frame-free annotation methodology and strict double annotation for improving data quality.
Outcome:	The proposed dataset is compared with a dataset from six different domains.

PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation (2023.findings-eacl)

Copied to clipboard

Ishan Jindal, Alexandre Rademaker, Khoi-Nguyen Tran, Huaiyu Zhu, Hiroshi Kanayama, Marina Danilevsky, Yunyao Li

Transfer Learning from Semantic Role Labeling to Event Argument Extraction with Template-based Slot Querying (2022.emnlp-main)

Challenge:	Existing evaluation scripts for semantic role labeling do not consider error propagation . existing evaluation script does not consider argument independent of predicate sense .
Approach:	They propose a more strict SRL evaluation metric PriMeSRL to address these issues . they propose to use a metric that measures the quality of the underlying SRL models .
Outcome:	The proposed metric reduces quality evaluation of all SoTA SRL models and penalizes failures.

Copied to clipboard

Zhisong Zhang, Emma Strubell, Eduard Hovy

Universal Proposition Bank 2.0 (2022.lrec-1)

Challenge:	Existing methods for event argument extraction are limited by the limited amount of annotations available.
Approach:	They propose to use SRL annotations for event argument extraction . they propose to specify natural language-like queries to tackle label mismatch problem .
Outcome:	The proposed model achieves impressive zero-shot results on English benchmarks . it also provides benefits in low-resource cases, where few annotations are available .

Copied to clipboard

Ishan Jindal, Alexandre Rademaker, Michał Ulewicz, Ha Linh, Huyen Nguyen, Khoi-Nguyen Tran, Huaiyu Zhu, Yunyao Li

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs (2022.findings-naacl)

Challenge:	Semantic role labeling (SRL) is a shallow semantic parsing task that identifies "who did what to whom when, where etc." SRL is useful in a wide range of downstream NLP tasks and real-world applications.
Approach:	They propose a method to generate shallow semantic parsing tasks using monolingual SRL and multilingual parallel data.
Outcome:	The proposed method improves the quality of the generated propbanks.

Copied to clipboard

Liang Chen, Peiyi Wang, Runxin Xu, Tianyu Liu, Zhifang Sui, Baobao Chang

An MRC Framework for Semantic Role Labeling (2022.coling-1)

Challenge:	Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations.
Approach:	They propose to use auxiliary tasks which are semantically or formally related to enhance AMR parsing.
Outcome:	The proposed method achieves state-of-the-art performance on benchmarks especially in topology-related scores.

Copied to clipboard

Nan Wang, Jiwei Li, Yuxian Meng, Xiaofei Sun, Han Qiu, Ziyao Wang, Guoyin Wang, Jun He

Semantic Parsing

Challenge:	Existing work on semantic role labels ignores the semantic connection between the two tasks . et al. (2010) defined two types of semantic roles: core roles and non-core roles.
Approach:	They propose to use machine reading comprehension to bridge the gap between these two tasks . they formalize predicate disambiguation as multiple-choice machine reading understanding .
Outcome:	The proposed framework achieves state-of-the-art or comparable results to previous work . it uses the descriptions of candidate senses of a given predicate as options to select the correct sense .

A Span Selection Model for Semantic Role Labeling (D18-1)

Copied to clipboard

Hiroki Ouchi, Hiroyuki Shindo, Yuji Matsumoto

Nicholas FitzGerald, Julian Michael, Luheng He, Luke Zettlemoyer

Challenge:	Existing models for semantic role labeling use BIO tags to predict argument spans . but performance of these approaches is weak .
Approach:	They propose a span-based model that takes into account all possible argument spans and scores them for each label.
Outcome:	The proposed model achieves state-of-the-art results on the CoNLL-2005 and 2012 datasets.

Large-Scale QA-SRL Parsing (P18-1)

Copied to clipboard

Natural Language Interfaces

Challenge:	a crowd-sourced approach to learning semantic parsers to predict predicateargument structures is open to many researchers.
Approach:	They propose a large-scale corpus of Question-Answer driven Semantic Role Labeling annotations . they also propose QA-SRL Bank 2.0, a crowd-sourcing scheme that can be used to train high quality parsers .
Outcome:	The proposed QA-SRL parser can generate high-quality questions at low cost and is intuitive to non-experts.

Syntax for Semantic Role Labeling, To Be, Or Not To Be (P18-1)

Copied to clipboard

Shexia He, Zuchao Li, Hai Zhao, Hongxiao Bai

UniteD-SRL: A Unified Dataset for Span- and Dependency-Based Multilingual and Cross-Lingual Semantic Role Labeling (2021.findings-emnlp)

Challenge:	Existing neural SRL models lack syntactic backbone for performance, limiting its use in deep learning.
Approach:	They propose an enhanced argument labeling model with extended korder argument pruning algorithm for effectively exploiting syntactic information.
Outcome:	The proposed model achieves state-of-the-art on the CoNLL-2008 and 2009 benchmarks in English and Chinese.

Copied to clipboard

Rocco Tripodi, Simone Conia, Roberto Navigli

GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles (2023.acl-long)

Challenge:	Multilingual and cross-lingual Semantic Role Labeling (SRL) has attracted increasing attention as multilingual text representation techniques have become more effective and widely available.
Approach:	They propose a benchmark for multilingual and cross-lingual, span- and dependency-based SRL that provides expert-curated parallel annotations using a common predicate-argument structure inventory.
Outcome:	The proposed benchmark provides expert-curated parallel annotations using a common predicate-argument structure inventory, allowing direct comparisons across languages and encouraging studies on cross-lingual transfer in SRL.

Copied to clipboard

Tanmay Parekh, I-Hung Hsu, Kuan-Hao Huang, Kai-Wei Chang, Nanyun Peng

Do Syntax Trees Help Pre-trained Transformers Extract Information? (2021.eacl-main)

Challenge:	Existing benchmarking datasets for Event Argument Extraction (EAE) cover less than 40 event types and 25 entity-centric argument roles.
Approach:	They propose to use a large and diverse EAE ontology to create a semantic role labeling dataset for EAE that incorporates 115 events and 220 argument roles.
Outcome:	The proposed ontology concludes with 115 events and 220 argument roles, with a significant portion of roles not being entities.

Copied to clipboard

Devendra Sachan, Yuhao Zhang, Peng Qi, William L. Hamilton

The New Propbank: Aligning Propbank with AMR through POS Unification (L18-1)

Challenge:	Recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models.
Approach:	They propose to incorporate dependency tree information into pre-trained transformers for three tasks . they propose a late fusion approach and a joint fusion technique to infuses syntax structure into attention layers.
Outcome:	The proposed models obtain state-of-the-art results on SRL and relation extraction tasks.

Copied to clipboard

Tim O’Gorman, Sameer Pradhan, Martha Palmer, Julia Bonn, Katie Conger, James Gung

A Full End-to-End Semantic Role Labeler, Syntactic-agnostic Over Syntactic-aware? (C18-1)

Challenge:	Existing Propbank corpus converts sense labels to a format which is more compatible with AMR and more robust to sparsity.
Approach:	They propose a corpus which converts existing Propbank sense labels to a new unified format which is more compatible with AMR and more robust to sparsity.
Outcome:	The proposed format is more compatible with AMR and robust to sparsity.

Copied to clipboard

Jiaxun Cai, Shexia He, Zuchao Li, Hai Zhao

Gold Standard Annotations for Preposition and Verb Sense with Semantic Role Labels in Adult-Child Interactions (C18-1)

Challenge:	Existing models for semantic role labeling are syntax-agnostic, but outperform them on benchmarks.
Approach:	They propose an end-to-end neural model which tackles the SRL problem in one shot . they augment the encoder with a non-linear transformation to distinguish the predicate and the argument .
Outcome:	The proposed model outperforms state-of-the-art syntax-aware SRL systems on CoNLL-2008 and 2009 benchmarks for English and Chinese.

Copied to clipboard

Lori Moon, Christos Christodoulopoulos, Cynthia Fisher, Sandra Franco, Dan Roth

CANarEx: Contextually Aware Narrative Extraction for Semantically Rich Text-as-data Applications (2022.findings-emnlp)

Challenge:	Existing corpus of child-directed speech augments existing corpus for semantic role labels . sense and number of arguments were open to multiple interpretations due to rapidly changing discourse .
Approach:	They propose to augment an existing corpus of child-directed speech to provide supervised learning of semantic role labels.
Outcome:	The resulting corpus is a gold standard for supervised learning of semantic role labels in child-directed speech.

Copied to clipboard

Nandini Anantharama, Simon Angus, Lachlan O’Neill

A Unified Syntax-aware Framework for Semantic Role Labeling (D18-1)

Challenge:	Narrative modelling is a field of active research that conceptualizes narratives as connected entity chains.
Approach:	They propose an alternative narrative extraction approach using semantic role labeling to extract tuples from text, then dimensionality reduction to reduce the space of entities and connections separately.
Outcome:	The proposed approach improves on a text-as-data task and improves accuracy and recall.

Copied to clipboard

Zuchao Li, Shexia He, Jiaxun Cai, Zhuosheng Zhang, Hai Zhao, Gongshen Liu, Linlin Li, Luo Si

Semantic Role Labeling with Heterogeneous Syntactic Knowledge (2020.coling-main)

Challenge:	Syntactic information has been paid a great attention over the role of enhancing SRL . but the gap between syntax-aware and syntax-gnostic SRL is smaller . a new framework proposes syntax-based SRL for a wide range of NLP tasks .
Approach:	They propose to extend existing models to investigate more effective ways of incorporating syntax into sequential neural networks.
Outcome:	The proposed framework outperforms existing models on CoNLL-2009 benchmarks in English and Chinese.

Copied to clipboard

Qingrong Xia, Rui Wang, Zhenghua Li, Yue Zhang, Min Zhang

CLAR: A Cross-Lingual Argument Regularizer for Semantic Role Labeling (2020.findings-emnlp)

Challenge:	Recent work on incorporating syntactic knowledge into neural semantic role labeling has gained much attention . incorporating heterogeneous syntaktic knowledge brings significant improvements over strong baselines .
Approach:	They propose to encode heterogeneous syntactic knowledge for SRL from explicit and implicit representations from heterogenous treebanks.
Outcome:	The proposed approaches improve on two widely-used benchmark datasets.

Copied to clipboard

Ishan Jindal, Yunyao Li, Siddhartha Brahma, Huaiyu Zhu

Semantic Parsing

Challenge:	Existing methods for training one model on multiple languages outperform monolingual baselines for low resource languages.
Approach:	They propose a method to combine training data from multiple languages to create a shared representation space for the model.
Outcome:	The proposed method outperforms monolingual and polyglot training on low resource languages.

Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures (2022.findings-emnlp)

Copied to clipboard

Simone Conia, Edoardo Barba, Alessandro Scirè, Roberto Navigli

Probing for Predicate Argument Structures in Pretrained Language Models (2022.acl-long)

Challenge:	Existing approaches to Semantic Role Labeling rely on discrete labels to classify predicate senses and their arguments.
Approach:	They propose a generalized formulation of Semantic Role Labeling that leverages Definition Modeling to describe predicate-argument structures using natural language definitions instead of discrete labels.
Outcome:	The proposed model can describe predicate-argument structures using natural language definitions instead of discrete labels.

Copied to clipboard

Simone Conia, Roberto Navigli

Language Models

Challenge:	Recent proposed approaches have achieved impressive results in dependency- and span-based, multilingual and cross-lingual Semantic Role Labeling (SRL)
Approach:	They propose to probe for predicate argument structures in pretrained language models . they show that PLMs encode semantic structures directly into contextualized representations .
Outcome:	The proposed models have achieved impressive results in dependency- and span-based, multilingual and cross-lingual Semantic Role Labeling (SRL)

A Simple Angle-based Approach for Contrastive Learning of Unsupervised Sentence Representation (2024.findings-emnlp)

Copied to clipboard

Yoo Hyun Jeong, Myeongsoo Han, Dong-Kyu Chae

Alignment-free Cross-lingual Semantic Role Labeling (2020.emnlp-main)

Challenge:	a promising baseline SimCSE has made notable breakthroughs in unsupervised SRL . however, there is still room for designing a novel contrastive framework specifically targeted for SRL.
Approach:	They propose an angle-based similarity function for a contrastive objective and propose a new approach for SRL.
Outcome:	The proposed approach shows better training dynamics on SRL than the standard cosine similarity function.

Copied to clipboard

Rui Cai, Mirella Lapata

X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset (2020.emnlp-main)

Challenge:	Existing approaches to semantic role labeling rely on word alignments, translation engines or preprocessing tools.
Approach:	They propose a cross-lingual semantic role labeling model which only requires annotations in a source language and access to raw text in .
Outcome:	The proposed model minimizes the effort required to construct annotations or models for a new target language.

Copied to clipboard

Angel Daza, Anette Frank

Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling (2020.emnlp-main)

Challenge:	Existing multilingual SRL datasets contain disparate annotation styles or come from different domains, hampering generalization in multilingual learning.
Approach:	They propose to automatically construct an SRL corpus that is parallel in four languages with unified predicate and role annotations that are fully comparable across languages.
Outcome:	The proposed method improves performance for English SRL in weaker languages.

Copied to clipboard

Diego Marcheggiani, Ivan Titov

Using Semantic Role Labeling to Improve Neural Machine Translation (2022.lrec-1)

Challenge:	Semantic role labeling (SRL) is the task of identifying predicates and labeling argument spans with semantic roles.
Approach:	They propose to use graph convolutional networks to encode constituents and inform an SRL system by combining word representations of the first and last words in a constituent tree.
Outcome:	The proposed model is compared with other models and shows that it is more efficient than dependency trees.

Copied to clipboard

Reinhard Rapp

Semantic Role Labeling with Associated Memory Network (N19-1)

Challenge:	despite progress in machine translation, some form of language understanding may be desirable . current systems rely on pattern recognition, but some form may be useful .
Approach:	They use semantic role labeling to annotate a standard parallel corpus with semantic roles . they then train a neural machine translation system using the annotated corpus and original unannotated text .
Outcome:	The proposed system improves BLEU scores for English, French, German, Greek and Spanish.

Copied to clipboard

Chaoyu Guan, Yuhao Cheng, Hai Zhao

Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing (2022.coling-1)

Challenge:	Existing work on semantic role labeling has been focused on using deep learning methods to solve the task.
Approach:	They propose a syntax-agnostic SRL model enhanced by the proposed associated memory network which makes use of inter-sentence attention of label-known associated sentences as a kind of memory to further enhance dependency-based SRL.
Outcome:	The proposed model achieves state-of-the-art on CoNLL-2009 benchmark datasets showing that it is not dependent on external resources.

Copied to clipboard

Shilin Zhou, Qingrong Xia, Zhenghua Li, Yu Zhang, Yu Hong, Min Zhang

Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures inside Arguments (2022.coling-1)

Challenge:	Using end-to-end span-based SRL, we propose a word-based graph parsing task for word-level representation of spans . compared with word-driven SRL, span-Based SRL is more complex due to difficulties in determining argument boundaries.
Approach:	They propose to cast end-to-end span-based SRL as a word-based graph parsing task . they propose a constrained Viterbi procedure to ensure the legality of the output graph .
Outcome:	The proposed model can parse 669/252 sentences per second without and with pre-trained models.

Copied to clipboard

Yu Zhang, Qingrong Xia, Shilin Zhou, Yong Jiang, Guohong Fu, Min Zhang

LIMIT-BERT : Linguistics Informed Multi-Task BERT (2020.findings-emnlp)

Challenge:	Recent works of SRL mainly fall into two lines: 1) BIO-based; 2) span-based.
Approach:	They propose to regard flat argument spans as latent subtrees, thus reducing SRL to a tree parsing task.
Outcome:	The proposed model performs better than previous syntax-agnostic models on CoNLL05 and CoNll12 benchmarks.

Copied to clipboard

Junru Zhou, Zhuosheng Zhang, Hai Zhao, Shuailiang Zhang

Semantic Role Labeling for Learner Chinese: the Importance of Syntactic Parsing and L2-L1 Parallel Data (D18-1)

Challenge:	Existing language models are usually trained on large amounts of unlabeled text data.
Approach:	They propose a multi-task language representations learning framework for multi-linguistics tasks by Multi-Task Learning.
Outcome:	The proposed model outperforms the baseline Whole Word Masking BERT on both dependency and constituent syntactic/semantic parsing, GLUE benchmark, and SNLI task.

Copied to clipboard

Zi Lin, Yuguang Duan, Yuanyuan Zhao, Weiwei Sun, Xiaojun Wan

The Robotic Surgery Procedural Framebank (2022.lrec-1)

Challenge:	a learner language (interlanguage) is an idiolect developed by a learning of a second or foreign language.
Approach:	They propose to use semantic role labeling as a case task to parse interlanguages . they then evaluate three off-the-shelf SRL systems to gauge how successful they are .
Outcome:	The proposed model achieves an F-score of 72.06, a 2.02 point improvement over the baseline.

Copied to clipboard

Marco Bombieri, Marco Rospocher, Simone Paolo Ponzetto, Paolo Fiorini

Semantic Parsing

Challenge:	Surgical practice has steadily improved thanks to the support of the approaches made available by observational science.
Approach:	They propose to extract from robot-surgical texts verbs and nouns that describe surgical actions and extend PropBank frames by adding any of new lemmas, frames or role sets required to cover missing lemae.
Outcome:	The proposed resource can be used to train and evaluate Semantic Role Labeling (SRL) systems in a fine-grained domain setting.

The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders (2021.emnlp-main)

Copied to clipboard

Han He, Jinho D. Choi

Language Models

Challenge:	Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency.
Approach:	They propose a multi-task learning technique that uses transformer encoders to improve performance on closely-related tasks.
Outcome:	The proposed method performs better on five NLP tasks than single-task learning on similar tasks.

Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings (2024.acl-long)

Copied to clipboard

Yichen Jiang, Xiang Zhou, Mohit Bansal

Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling (2022.coling-1)

Challenge:	Empirically, we show SQ-Transformer achieves stronger compositional generalization than the vanilla Transformer on low-complexity datasets.
Approach:	They propose a Transformer that explicitly encourages systematicity in the embeddings and attention layers even with low-complexity data.
Outcome:	Empirically, the proposed model achieves stronger compositional generalization than the vanilla Transformer on low-complexity datasets.

Copied to clipboard

Shuhei Kurita, Hiroki Ouchi, Kentaro Inui, Satoshi Sekine

On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling (2021.emnlp-main)

Challenge:	Semantic role labeling is the task of labeling semantic arguments for marked semantic predicates.
Approach:	They propose a model which combines global decoding and iterative identification for the semantic arguments to consider their roles and relations in the labeling order.
Outcome:	The proposed model outperforms existing models in the benchmark datasets of span-based SRL: CoNLL-2005 and CoNll-2012.

Copied to clipboard

Zhisong Zhang, Emma Strubell, Eduard Hovy

Semantic Role Labeling from Chinese Speech via End-to-End Learning (2024.findings-acl)

Challenge:	Recent advances in neural architectures and pre-trained representations have greatly improved the performance of fully-supervised semantic role labeling (SRL) but there are limitations in the availability of supervised training data.
Approach:	They propose to leverage syntactic dependencies to facilitate cross-lingual transfer by annotating predicate-argument structures in text.
Outcome:	The proposed model can be extended to other languages with limited training data.

Copied to clipboard

Huiyao Chen, Xinxin Li, Meishan Zhang, Min Zhang

How to Best Use Syntax in Semantic Role Labelling (P19-1)

Challenge:	Semantic role labeling (SRL) has traditionally focused on text input.
Approach:	They propose an end-to-end approach for SRL from speech integrating ASR and SRL in a joint-learning framework, focusing on the Chinese language.
Outcome:	The proposed model improves on the Chinese Proposition Bank 1.0 dataset and the existing model with improved performance.

Copied to clipboard

Yufei Wang, Mark Johnson, Stephen Wan, Yifang Sun, Wei Wang

Finding a Balanced Degree of Automation for Summary Evaluation (2021.emnlp-main)

Challenge:	Existing studies on integrating external information into NLP tasks focus on word-level shallow features such as POS or chunk tags.
Approach:	They propose to integrate syntactic information into a neural ELMo-based SRL sequence labelling model by using a constituency representation as input features.
Outcome:	The proposed approach improves performance on the in-domain CoNLL’05 and CoNll’12 benchmarks.

Copied to clipboard

Shiyue Zhang, Mohit Bansal

Semantic Role Labeling Guided Multi-turn Dialogue ReWriter (2020.emnlp-main)

Challenge:	Automated summarization metrics are reliable but often poorly correlated with human judgment.
Approach:	They propose a semi-automatic to automatic summary evaluation metrics, following the Pyramid human evaluation method.
Outcome:	The proposed metrics are semi-automatic to automatic summary evaluation metrics, following the Pyramid human evaluation method.

Copied to clipboard

Kun Xu, Haochen Tan, Linfeng Song, Han Wu, Haisong Zhang, Linqi Song, Dong Yu

Paraphrasing

Challenge:	Existing attentive models attend to all words without prior focus, which results in inaccurate concentration on some dispensable words.
Approach:	They propose to use semantic role labeling to provide additional guidance for multi-turn dialogue rewriting models.
Outcome:	The proposed model outperforms existing models on multi-turn dialogue rewriting tasks.

Syntax-aware Multilingual Semantic Role Labeling (D19-1)

Copied to clipboard

Shexia He, Zuchao Li, Hai Zhao

Towards Semi-Supervised Learning for Deep Semantic Role Labeling (D18-1)

Challenge:	Existing work on semantic role labeling (SRL) on English has focused on syntactic integration and enhanced word representation.
Approach:	They propose a method guided by syntactic rule to prune arguments to integrate syntax into multilingual SRL model simply and effectively.
Outcome:	The proposed model achieves state-of-the-art results on the CoNLL-2009 benchmarks of all seven languages.

Copied to clipboard

Sanket Vaibhav Mehta, Jay Yoon Lee, Jaime Carbonell

A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling (D19-1)

Challenge:	Existing methods for semantic role labeling require an immense amount of semantic-role corpora and are therefore not suitable for low-resource languages or domains.
Approach:	They propose a semi-supervised method that outperforms the state-of-the-art on SRL . method explicitly enforcs syntactic constraints by augmenting the training objective with a syntastic-inconsistency loss component.
Outcome:	The proposed method outperforms the state-of-the-art on limited SRL training corpora on CoNLL-2012 English section.

Copied to clipboard

Qingrong Xia, Zhenghua Li, Min Zhang

Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks (D19-1)

Challenge:	Semantic role labeling (SRL) aims to identify the predicate-argument structure of a sentence.
Approach:	They propose to use a unified span-based model for Chinese SRL as a strong baseline.
Outcome:	The proposed framework achieves state-of-the-art 87.54 and 88.5 F1 scores on the Chinese Proposition Bank and CoNLL-2009 datasets.

Copied to clipboard

Xinchi Chen, Chunchuan Lyu, Ivan Titov

Modeling Syntactic-Semantic Dependency Correlations in Semantic Role Labeling Using Mixture Models (2022.acl-long)

Challenge:	State-of-the-art SRL models do not model non-local interaction between arguments . e.g., LSTMs do not allow for efficient inference .
Approach:	They propose a new approach to model interactions between arguments using capsule networks . they analyze errors in the refinement procedure by capturing intuition in a flexible way .
Outcome:	The proposed model outperforms the baseline model on all 7 languages and achieves state-of-the-art results on 5 languages including English.

Copied to clipboard

Junjie Chen, Xiangheng He, Yusuke Miyao

Linguistically-Informed Self-Attention for Semantic Role Labeling (D18-1)

Challenge:	Existing methods for SRL identify semantic dependencies that specify the semantic role of arguments in relation to predicates.
Approach:	They propose a mixture model-based end-to-end method to model syntactic-semantic dependency correlation in Semantic Role Labeling.
Outcome:	The proposed method improves performance in English, German, and Spanish . it achieves small but statistically significant improvement over baseline methods .

Copied to clipboard

Emma Strubell, Patrick Verga, Daniel Andor, David Weiss, Andrew McCallum

Span-based Semantic Role Labeling as Lexicalized Constituency Tree Parsing (2025.findings-acl)

Challenge:	Existing models of semantic role labeling use no explicit linguistic features. prior work has shown that syntax trees can dramatically improve SRL decoding.
Approach:	They propose a neural network model that incorporates syntax using only raw tokens . they show that LISA out-performs the state-of-the-art with contextually-encoded word representations a 1.0 F1 on newswire and 2.0 F1 in out-of domain text .
Outcome:	The proposed model outperforms the state-of-the-art model with word embeddings and predicted predicates.

Copied to clipboard

Yang Hou, Zhenghua Li

Semantic Role Labeling as Syntactic Dependency Parsing (2020.emnlp-main)

Challenge:	Existing models for semantic role labeling fail to capture the relationship between syntax and semantics.
Approach:	They propose a lexicalized tree representation for span-based SRL that integrates constituency and dependency parsing to explicitly model predicate-argument structures.
Outcome:	The proposed model achieves competitive performance on standard English benchmarks.

Copied to clipboard

Tianze Shi, Igor Malioutov, Ozan Irsoy

On the Role of Semantic Proto-roles in Semantic Analysis: What do LLMs know about agency? (2025.findings-acl)

Challenge:	Using propBank-style semantic role labeling, we reduce the task to syntactic dependency parsing.
Approach:	They propose to convert SRL annotations into dependency tree representations through joint labels that permit highly accurate recovery back to the original format.
Outcome:	The proposed scheme reduces the task of (span-based) PropBank-style semantic role labeling to syntactic dependency parsing.

Copied to clipboard

Elizabeth Spaulding, Shafiuddin Rehan Ahmed, James Martin

Controlled Crowdsourcing for High-Quality QA-SRL Annotation (2020.acl-main)

Challenge:	Existing studies on large language models (LLMs) have not explored their capacity to reason over event structure . et al., 2015, 142: e007-e0027; eugene, 1985; Weiner, 1995; saab, 1985) focus on the role of large language model in decision-making .
Approach:	They propose to characterize agents via properties such as "instigation" and "volition" they also examine whether incorporating semantic proto-role labeling context improves SRL performance .
Outcome:	The proposed model improves in a zero-shot setting by incorporating proto-role labeling context . the results support previous work showing that LLMs underperform human annotators in complex semantic analysis.

Copied to clipboard

Paul Roit, Ayal Klein, Daniela Stepanov, Jonathan Mamou, Julian Michael, Gabriel Stanovsky, Luke Zettlemoyer, Ido Dagan

Natural Language Interfaces

Challenge:	Question-answer driven Semantic Role Labeling (QA-SRL) is an open and natural flavour of SRL, potentially attainable from laymen.
Approach:	They propose a question-answer driven semantic role labeling approach that uses question-announced questions to label predicate-argument relationships.
Outcome:	The proposed method yields high-quality annotation with dramatically higher coverage, enabling future replicable research of natural semantic annotations.

Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus (2020.acl-main)

Copied to clipboard

Hao Fei, Meishan Zhang, Donghong Ji

BERTie Bott’s Every Flavor Labels: A Tasty Introduction to Semantic Role Labeling for Galician (2023.emnlp-main)

Challenge:	Existing approaches to semantic role labeling (SRL) are focusing on the English language.
Approach:	They propose a method for semantic role labeling that uses corpus translation to build training datasets from SRL annotations.
Outcome:	The proposed method is highly effective and can improve the target-language performance significantly.

Copied to clipboard

Micaella Bruton, Meriem Beloucif

SRLGRN: Semantic Role Labeling Graph Reasoning Network (2020.emnlp-main)

Challenge:	Existing corpora, WordNet, and dependency parsing are used to build a semantic role labeling system.
Approach:	They use existing corpora, WordNet, and dependency parsing to build a Galician dataset for training semantic role labeling systems.
Outcome:	The proposed model outperforms the 2009 CoNLL Shared Task by 0.83 on Spanish datasets.

Copied to clipboard

Chen Zheng, Parisa Kordjamshidi

Structured Data in NLP

Challenge:	Existing models that use context and type-matching heuristics do not provide realistic evaluation of reasoning capabilities.
Approach:	They propose a graph reasoning network based on the semantic structure of the sentences to learn cross paragraph reasoning paths and find supporting facts and the answer jointly.
Outcome:	The proposed network shows competitive performance on the HotpotQA distractor setting benchmark compared to the state-of-the-art models.

The Russian PropBank (2020.lrec-1)

Copied to clipboard

Sarah Moeller, Irina Wagner, Martha Palmer, Kathryn Conger, Skatje Myers

Structured Tuning for Semantic Role Labeling (2020.acl-main)

Challenge:	Using proposition bank for Russian, we can automatically project semantic role labels from English to Russian.
Approach:	They propose a proposition bank for Russian that automatically projects semantic role labels from English to Russian.
Outcome:	The proposed resource automatically projectes semantic role labels from English to Russian.

Copied to clipboard

Tao Li, Parth Anand Jawale, Martha Palmer, Vivek Srikumar

Syntax-driven Approach for Semantic Role Labeling (2022.lrec-1)

Challenge:	Recent neural network-driven semantic role labeling systems have shown impressive improvements in F1 scores.
Approach:	They propose a framework to tune models using softened constraints only at training time.
Outcome:	The proposed framework outperforms the baseline model with minimal training time and consistent improvements under low-resource scenarios.

Copied to clipboard

Yuanhe Tian, Han Qin, Fei Xia, Yan Song

On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation Learning (2023.findings-acl)

Challenge:	Existing studies focus on auto-generated syntactic knowledge to enhance semantic role labeling . experimental results show that map memories can enhance SRL .
Approach:	They propose to map memories to enhance semantic role labeling by encoding auto-generated syntactic knowledge from off-the-shelf toolkits.
Outcome:	The proposed model outperforms baselines and achieves state-of-the-art results on two English benchmark datasets.

Copied to clipboard

Chenghao Xiao, Yang Long, Noura Al Moubayed

Exploring Non-Verbal Predicates in Semantic Role Labeling: Challenges and Opportunities (2023.findings-acl)

Challenge:	Incorporating contrastive learning objectives in sentence representation learning has yielded significant improvements on many sentence-level NLP tasks.
Approach:	They aim to examine why contrastive learning works for learning sentence-level semantics . they interpret successes through the geometry of the representation shifts based on isotropy .
Outcome:	The proposed model improves on many sentence-level NLP tasks, but it is not well understood why it works.

Copied to clipboard

Riccardo Orlando, Simone Conia, Roberto Navigli

DATA-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning (2024.findings-acl)

Challenge:	Existing systems for SRL are incapable of transferring knowledge across different predicate types.
Approach:	They propose a new PropBank dataset which boasts wide coverage of multiple predicate types and a manually-annotated challenge set which gives equal importance to verbal, nominal, and adjectival predicates.
Outcome:	The proposed dataset shows that standard benchmarks do not provide an accurate picture of the current situation in SRL and that state-of-the-art systems are still incapable of transferring knowledge across different predicate types.

Copied to clipboard

Yingqian Min, Kun Zhou, Dawei Gao, Xin Zhao, He Hu, Yaliang Li

Learning Semantic Role Labeling from Compatible Label Sequences (2023.findings-emnlp)

Challenge:	Existing methods to improve sentence representation learning (SRL) ignore the potential interference problems across tasks and instances.
Approach:	They propose a multi-task instruction tuning method that arranges the order of multi- task data for training to minimize interference risks.
Outcome:	The proposed method can boost the performance of state-of-the-art methods.

Copied to clipboard

Tao Li, Ghazaleh Kazeminejad, Susan Brown, Vivek Srikumar, Martha Palmer

LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models (2025.findings-acl)

Challenge:	Prior work has shown that cross-task interaction helps, but only explored multitask learning so far.
Approach:	They propose a framework that jointly models VerbNet and PropBank labels as one sequence and enforcing Semlink constraints during decoding improves the overall F1 .
Outcome:	The proposed model outperforms the prior best in-domain model by 3.5 (VerbNet) and 0.8 (PropBank).

Copied to clipboard

Xinxin Li, Huiyao Chen, Chengjun Liu, Jing Li, Meishan Zhang, Jun Yu, Min Zhang

Semantic Role Labeling Guided Out-of-distribution Detection (2024.lrec-main)

Challenge:	Semantic role labeling (SRL) is a crucial task of natural language processing (NLP).
Approach:	They propose to equip LLMs with retrieval-augmented generation and self-correction mechanisms to enable SRL to perform better in Chinese and English.
Outcome:	The proposed method achieves state-of-the-art in Chinese and English on three widely-used benchmarks.

Copied to clipboard

Jinan Zou, Maihao Guo, Yu Tian, Yuhao Lin, Haiyao Cao, Lingqiao Liu, Ehsan Abbasnejad, Javen Qinfeng Shi

Transformer-based Swedish Semantic Role Labeling through Transfer Learning (2024.lrec-main)

Challenge:	Existing methods for identifying domain-shifted instances are prone to OOD and adversarial inputs.
Approach:	They propose an unsupervised method that separates, extracts, and learns the semantic role labeling guided out-of-distribution Detection (SRLOOD) they propose a self-supervised approach to enhance global-local feature learning by predicting SRL extracted role.
Outcome:	The proposed method achieves SOTA performance on four OOD benchmarks.

Copied to clipboard

Dana Dannélls, Richard Johansson, Lucy Yang Buhr

Predicting Implicit Arguments in Procedural Video Instructions (2025.acl-long)

Challenge:	Semantic Role Labeling (SRL) is a task in natural language understanding where the goal is to extract semantic roles for a given sentence.
Approach:	They propose to build a Transformer-based SRL system for Swedish by exploring multilingual and cross-lingual transfer learning methods and leveraging the Swedish FrameNet resource.
Outcome:	The proposed model outperforms two different cross-lingual transfer models and shows that the multilingual learning outperformed the other models.

Copied to clipboard

Anil Batra, Laura Sevilla-Lara, Marcus Rohrbach, Frank Keller

3R: Enhancing Sentence Representation Learning via Redundant Representation Reduction (2025.emnlp-main)

Challenge:	Prior SRL benchmarks often miss implicit arguments, leading to incomplete understanding.
Approach:	They propose a dataset that necessitates inferring implicit and explicit arguments from contextual information in multimodal cooking procedures.
Outcome:	The proposed dataset achieves a 17% relative improvement in F1-score for what-implicit and a 14.7% improvement for where/with-implicative semantic roles over GPT-4o.

Copied to clipboard

Longxuan Ma, Xiao Wu, Yuxin Huang, Shengxiang Gao, Zhengtao Yu