Comparing Span Extraction Methods for Semantic Role Labeling
In this work, we empirically compare span extraction methods for the task of semantic role labeling (SRL). While recent progress incorporating pre-trained contextualized representations into neural encoders has greatly improved SRL F1 performance on popular benchmarks, the potential costs and benefits of structured decoding in these models have become less clear. With extensive experiments on PropBank SRL datasets, we find that more structured decoding methods outperform BIO-tagging when using static (word type) embeddings across all experimental settings. However, when used in conjunction with pre-trained contextualized word representations, the benefits are diminished. We also experiment in cross-genre and cross-lingual settings and find similar trends. We further perform speed comparisons and provide analysis on the accuracy-efficiency trade-offs among different decoding methods.
Code (1)
Tasks
Semantic Role LabelingSimilar Papers 제목 키워드 기반
From Semantic Roles to Opinion Roles: SRL Data Extraction for Multi-Task and Transfer Learning in Low-Resource ORL
This report presents a detailed methodology for constructing a high-quality Semantic Role Labeling (SRL) dataset from the Wall Street Journal (WSJ) portion of the OntoNotes 5.0 corpus and adapting it for Opinion Role Lab…
Semantic Role LabelingTransfer LearningOpinion MiningOSLAT: Open Set Label Attention Transformer for Medical Entity Retrieval and Span Extraction
Medical entity span extraction and linking are critical steps for many healthcare NLP tasks. Most existing entity extraction methods either have a fixed vocabulary of medical entities or require span annotations. In this…
Entity LinkingEntity RetrievalRetrievalEnhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance
Document-level event argument extraction poses new challenges of long input and cross-sentence inference compared to its sentence-level counterpart. However, most prior works focus on capturing the relations between cand…
Event Argument ExtractionEvent ExtractionSentenceSpan-based Joint Entity and Relation Extraction with Attention-based Span-specific and Contextual Semantic Representations
Span-based joint extraction models have shown their efficiency on entity recognition and relation extraction. These models regard text spans as candidate entities and span tuples as candidate relation tuples. Span semant…
Joint Entity and Relation ExtractionRelationRelation ExtractionEntity, Relation, and Event Extraction with Contextualized Span Representations
We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all …
Event ExtractionJoint Entity and Relation Extractionnamed-entity-recognitionNamed Entity Recognition+4