Corpus ID: 9406422

A Bayesian Approach to Unsupervised Semantic Role Induction

@inproceedings{Titov2012ABA,
  title={A Bayesian Approach to Unsupervised Semantic Role Induction},
  author={Ivan Titov and A. Klementiev},
  booktitle={EACL},
  year={2012}
}
We introduce two Bayesian models for unsupervised semantic role labeling (SRL) task. The models treat SRL as clustering of syntactic signatures of arguments with clusters corresponding to semantic roles. The first model induces these clusterings independently for each predicate, exploiting the Chinese Restaurant Process (CRP) as a prior. In a more refined hierarchical model, we inject the intuition that the clusterings are similar across different predicates, even though they are not… Expand
Similarity-Driven Semantic Role Induction via Graph Partitioning
TLDR
The working hypothesis of this article is that semantic roles can be induced without human supervision from a corpus of syntactically parsed sentences based on three linguistic principles, and a method is presented that implements these principles and formalizes the task as a graph partitioning problem. Expand
Semantic role induction in Persian: An unsupervised approach by using probabilistic models
TLDR
A Bayesian model for learning argument structure from un-annotated text and estimate the model parameters using expectation maximization method is presented and the system in both small and large training datasets works better than a strong baseline proposed by Lang and Lapata 2010. Expand
A Bayesian Model of Multilingual Unsupervised Semantic Role Induction
TLDR
It is found that the biggest impact of adding a parallel corpus to training is actually the increase in mono-lingual data, with the alignments to another language resulting in small improvements, even with labeled data for the other language. Expand
Inducing Semantic Roles Without Syntax
TLDR
It is shown it is possible to automatically induce semantic roles from QA-SRL, a scalable and ontology-free semantic annotation scheme that uses question-answer pairs to represent predicate-argument structure, and this method outperforms all previous models as well as a new state-of-the-art baseline over gold syntax. Expand
Learning Generalized Features for Semantic Role Labeling
TLDR
This article embeds the information of lexicalization and syntax into a feature vector for each argument and uses K-means to make clustering for all feature vectors of training set. Expand
Crosslingual Induction of Semantic Roles
TLDR
This work considers unsupervised induction of semantic roles from sentences annotated with automatically-predicted syntactic dependency representations and uses a state-of-the-art generative Bayesian non-parametric model to do so. Expand
Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations
TLDR
A new method to integrate two recent lines of work: unsupervised induction of shallow semantics and factorization of relations in text and knowledge bases, which performs on par with most accurate role induction methods on English, even though it does not incorporate any prior linguistic knowledge about the language. Expand
Distributed Representations for Unsupervised Semantic Role Labeling
TLDR
This work induces embeddings to represent a predicate, its arguments and their complex interdependence through distributed representations that are clustered into roles using a linear programming formulation of hierarchical clustering. Expand
Multiplicative Representations for Unsupervised Semantic Role Induction
TLDR
This work proposes a neural model to learn argument embeddings from the context by explicitly incorporating dependency relations as multiplicative factors, which bias argumentembeddings according to their dependency roles. Expand
Bootstrapping Semantic Role Labelers from Parallel Data
TLDR
This work uses the similarity in semantic structure of bilingual parallel sentences to bootstrap a pair of semantic role labeling (SRL) models which can facilitate the construction of SRL models for resource-poor languages, while preserving the annotation schemes designed for the target language and making use of the limited resources available for it. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 50 REFERENCES
Unsupervised Induction of Semantic Roles
TLDR
A method for inducing the semantic roles of verbal arguments directly from unannotated text by detecting alternations and finding a canonical syntactic form for them in a novel probabilistic model, a latent-variable variant of the logistic classifier. Expand
A Bayesian Model for Unsupervised Semantic Parsing
TLDR
A non-parametric Bayesian model for unsupervised semantic parsing that uses hierarchical Pitman-Yor processes to model statistical dependencies between meaning representations of predicates and those of their arguments, as well as the clusters of their syntactic realizations. Expand
Unsupervised Semantic Role Induction via Split-Merge Clustering
TLDR
An unsupervised method for semantic role induction which holds promise for relieving the data acquisition bottleneck associated with supervised role labelers and an algorithm that iteratively splits and merges clusters representing semantic roles, thereby leading from an initial clustering to a final clustering of better quality. Expand
Unsupervised Semantic Role Labellin
TLDR
An unsupervised method for labelling the arguments of verbs with their semantic roles that achieves 50–65% reduction in the error rate over an informed baseline, indicating the potential of this approach for a task that has heretofore relied on large amounts of manually generated training data. Expand
Unsupervised Argument Identification for Semantic Role Labeling
TLDR
This paper presents an unsupervised algorithm for identifying verb arguments, where the only type of annotation required is POS tagging, and makes use of a fullyunsupervised syntactic parser in order to detect clauses and gather candidate argument collocation statistics. Expand
Unsupervised Discovery of a Statistical Verb Lexicon
TLDR
A method for learning models of verb argument patterns directly from unannotated text that is based on a structured probabilistic model of the domain, and unsupervised learning is performed with the EM algorithm. Expand
Cross-lingual Annotation Projection for Semantic Roles
TLDR
An experimental evaluation on an English-German parallel corpus is provided which demonstrates the feasibility of inducing high-precision German semantic role annotation both for manually and automatically annotated English data. Expand
Semi-supervised Semantic Role Labeling Using the Latent Words Language Model
TLDR
The Latent Words Language Model is presented, which is a language model that learns word similarities from unlabeled texts that uses these similarities for different semi-supervised SRL methods as additional features or to automatically expand a small training set. Expand
Unsupervised Semantic Role Induction with Graph Partitioning
TLDR
The method is algorithmically and conceptually simple, especially with respect to how problem-specific knowledge is incorporated into the model, and competitive with other unsupervised approaches in terms of F1 whilst attaining significantly higher cluster purity. Expand
Automatic Labeling of Semantic Roles
TLDR
A system for identifying the semantic relationships, or semantic roles, filled by constituents of a sentence within a semantic frame, based on statistical classifiers trained on roughly 50,000 sentences that were hand-annotated with semantic roles by the FrameNet semantic labeling project. Expand
...
1
2
3
4
5
...