A Joint Sequential and Relational Model for Frame-Semantic Parsing

@inproceedings{Yang2017AJS,
  title={A Joint Sequential and Relational Model for Frame-Semantic Parsing},
  author={Bishan Yang and Tom Michael Mitchell},
  booktitle={Conference on Empirical Methods in Natural Language Processing},
  year={2017}
}
We introduce a new method for framesemantic parsing that significantly improves the prior state of the art. [] Key Method The two networks are integrated into a single model via knowledge distillation, and a unified graphical model is employed to jointly decode frames and semantic roles during inference. Experiments on the standard FrameNet data show that our model significantly outperforms existing neural and non-neural approaches, achieving a 5.7 F1 gain over the current state of the art, for full frame…

Figures and Tables from this paper

A Graph-Based Neural Model for End-to-End Frame Semantic Parsing

This work exploits a graph-based method, regarding frame semantic parsing as a graph construction problem, and proposes an end-to-end neural model to tackle the task jointly, resulting in better performance than pipeline models.

Joint Multi-Decoder Framework with Hierarchical Pointer Network for Frame Semantic Parsing

A novel architecture based on multi-decoder strategy to handle three subtasks, namely frame identification, argument identification and role classification is introduced and a hierarchical pointer network for argument identification is designed which reduces the computational complexity.

Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling

This work proposes an end-to-end approach for jointly predicting all predicates, arguments spans, and the relations between them, and makes independent decisions about what relationship, if any, holds between every possible word-span pair.

A Double-Graph Based Framework for Frame Semantic Parsing

This paper proposes a Knowledge-guided Incremental semantic parser with Double-graph (KID), a heterogeneous graph containing both frames and FEs (Frame Elements) built on the frame knowledge so that it can derive knowledge-enhanced representations for frames andFEs.

A Span-based Target-aware Relation Model for Frame-Semantic Parsing

  • Xuefeng SuRui Li Zhichao Yan
  • Computer Science
    ACM Transactions on Asian and Low-Resource Language Information Processing
  • 2022
This work reformulates the FSRL task into a target-aware relation classification task, and proposes a novel and lightweight jointly learning framework that simultaneously processes three subtasks of FSP, including frame identification, argument identification and role classification.

Positional Attention-based Frame Identification with BERT: A Deep Learning Approach to Target Disambiguation and Semantic Frame Selection

A deep neural network architecture known as Positional Attention-based Frame Identification with BERT (PAFIBERT) is presented as a solution to the frame identification subtask in frame-semantic parsing.

Sources of Complexity in Semantic Frame Parsing for Information Extraction

The purpose of this study is to analyze the task complexity, to highlight the factors that make Semantic Frame parsing a difficult task and to provide detailed evaluations of the performance on different types of frames and sentences.

Debugging Frame Semantic Role Labeling

It is proved that syntactic pre-processing plays a major role in the performances of statistical classifiers to argument identification, and the core reasons of syntactic mismatch between dependency parsers output and FrameNet syntactic formalism are discussed.

Query Your Model with Definitions in FrameNet: An Effective Method for Frame Semantic Role Labeling

A query-based framework named ArGument Extractor with Definitions in FrameNet (A GED) to mitigate problems of frame semantic roles and the generalization power of A GED in zero-shot and few-shot scenarios is proposed.

Syntax Role for Neural Semantic Role Labeling

This paper quantifies the importance of syntactic information for neural SRL in the deep learning framework and shows the quantitative significance of syntax to Neural SRL models together with a thorough empirical survey using existing models.
...

References

SHOWING 1-10 OF 39 REFERENCES

Deep Semantic Role Labeling: What Works and What’s Next

We introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations. We use

Semantic Role Labeling with Neural Network Factors

A new method for semantic role labeling in which arguments and semantic roles are jointly embedded in a shared vector space for a given predicate, which is based on a neural network designed for the SRL task.

The Importance of Syntactic Parsing and Inference in Semantic Role Labeling

It is shown that full syntactic parsing information is, by far, most relevant in identifying the argument, especially in the very first stagethe pruning stage, and an effective and simple approach of combining different semantic role labeling systems through joint inference is proposed, which significantly improves its performance.

A Global Joint Model for Semantic Role Labeling

We present a model for semantic role labeling that effectively captures the linguistic intuition that a semantic argument frame is a joint structure, with strong dependencies among the arguments. We

Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs

This work presents a transition-based parser that jointly produces syntactic and semantic dependencies and obtains the best published parsing performance among models that jointly learn syntax and semantics.

Semantic Frame Identification with Distributed Word Representations

A novel technique for semantic frame identification using distributed representations of predicates and their syntactic context using automatic syntactic parses and a generic set of word embeddings is presented.

Semantic Role Features for Machine Translation

We propose semantic role features for a Tree-to-String transducer to model the reordering/deletion of source-side semantic roles. These semantic features, as well as the Tree-to-String templates, are

Probabilistic Frame-Semantic Parsing

An implemented parser that transforms an English sentence into a frame-semantic representation and uses two feature-based, discriminative probabilistic models to permit disambiguation of new predicate words is described.

Efficient Inference and Structured Learning for Semantic Role Labeling

A dynamic programming algorithm for efficient constrained inference in semantic role labeling that tractably captures a majority of the structural constraints examined by prior work in this area, and allows training a globally-normalized log-linear model with respect to constrained conditional likelihood.

End-to-end learning of semantic role labeling using recurrent neural networks

This work proposes to use deep bi-directional recurrent network as an end-to-end system for SRL, which takes only original text information as input feature, without using any syntactic knowledge.