Unsupervised Transfer of Semantic Role Models from Verbal to Nominal Domain

• URL: http://arxiv.org/abs/2005.00278v2
• Date: Sat, 26 Sep 2020 12:56:08 GMT
• Title: Unsupervised Transfer of Semantic Role Models from Verbal to Nominal Domain
• Authors: Yanpeng Zhao and Ivan Titov
• Abstract summary: We investigate a transfer scenario where we assume role-annotated data for the source verbal domain but only unlabeled data for the target nominal domain. Our key assumption, enabling the transfer between the two domains, is that selectional preferences of a role do not strongly depend on whether the relation is triggered by a verb or a noun. The method substantially outperforms baselines, such as unsupervised and direct transfer' methods, on the English CoNLL-2009 dataset.
• Score: 65.04669567781634
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Semantic role labeling (SRL) is an NLP task involving the assignment of predicate arguments to types, called semantic roles. Though research on SRL has primarily focused on verbal predicates and many resources available for SRL provide annotations only for verbs, semantic relations are often triggered by other linguistic constructions, e.g., nominalizations. In this work, we investigate a transfer scenario where we assume role-annotated data for the source verbal domain but only unlabeled data for the target nominal domain. Our key assumption, enabling the transfer between the two domains, is that selectional preferences of a role (i.e., preferences or constraints on the admissible arguments) do not strongly depend on whether the relation is triggered by a verb or a noun. For example, the same set of arguments can fill the Acquirer role for the verbal predicate `acquire' and its nominal form `acquisition'. We approach the transfer task from the variational autoencoding perspective. The labeler serves as an encoder (predicting role labels given a sentence), whereas selectional preferences are captured in the decoder component (generating arguments for the predicting roles). Nominal roles are not labeled in the training data, and the learning objective instead pushes the labeler to assign roles predictive of the arguments. Sharing the decoder parameters across the domains encourages consistency between labels predicted for both domains and facilitates the transfer. The method substantially outperforms baselines, such as unsupervised and `direct transfer' methods, on the English CoNLL-2009 dataset.

Related papers

• Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures [104.32063681736349]
  We present an approach to describe predicate-argument structures using natural language definitions instead of discrete labels. Our experiments and analyses on PropBank-style and FrameNet-style, dependency-based and span-based SRL also demonstrate that a flexible model with an interpretable output does not necessarily come at the expense of performance.
  arXiv  Detail & Related papers  (2022-12-02T11:19:16Z)
• Open-Vocabulary Argument Role Prediction for Event Extraction [70.93524366880521]
  In this paper, we define this essential but under-explored task: open-vocabulary argument role prediction. The goal of this task is to infer a set of argument roles for a given event type. We propose a novel unsupervised framework, RolePred for this task.
  arXiv  Detail & Related papers  (2022-11-03T04:13:37Z)
• Rethinking the Two-Stage Framework for Grounded Situation Recognition [61.93345308377144]
  Grounded Situation Recognition is an essential step towards "human-like" event understanding. Existing GSR methods resort to a two-stage framework: predicting the verb in the first stage and detecting the semantic roles in the second stage. We propose a novel SituFormer for GSR which consists of a Coarse-to-Fine Verb Model (CFVM) and a Transformer-based Noun Model (TNM)
  arXiv  Detail & Related papers  (2021-12-10T08:10:56Z)
• An MRC Framework for Semantic Role Labeling [21.140775452024894]
  We propose to use the machine reading comprehension framework to bridge the gap between predicate disambiguation and argument labeling. We leverage both the predicate semantics and the semantic role semantics for argument labeling. Experiments show that the proposed framework achieves state-of-the-art results on both span and dependency benchmarks.
  arXiv  Detail & Related papers  (2021-09-14T13:04:08Z)
• Learning Transferable Parameters for Unsupervised Domain Adaptation [29.962241958947306]
  Untrivial domain adaptation (UDA) enables a learning machine to adapt from a labeled source domain to an unlabeled domain under the distribution shift. We propose Transferable Learning (TransPar) to reduce the side effect brought by domain-specific information in the learning process.
  arXiv  Detail & Related papers  (2021-08-13T09:09:15Z)
• Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder [7.60457018063735]
  We formalize event argument extraction (EAE) as a Seq2Seq-like learning problem for the first time. A neural architecture with a novel Bi-directional Entity-level Recurrent Decoder (BERD) is proposed to generate argument roles.
  arXiv  Detail & Related papers  (2021-07-01T02:55:12Z)
• Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models [9.359514457957799]
  We explore how much transfer occurs when models are denied any information about word identity via random scrambling. We find that only BERT shows high rates of transfer into our scrambled domains, and for classification but not sequence labeling tasks. Our analyses seek to explain why transfer succeeds for some tasks but not others, to isolate the separate contributions of pretraining versus fine-tuning, and to quantify the role of word frequency.
  arXiv  Detail & Related papers  (2021-04-17T00:14:39Z)
• R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching [58.72111690643359]
  We propose a Relation of Relation Learning Network (R2-Net) for sentence semantic matching. We first employ BERT to encode the input sentences from a global perspective. Then a CNN-based encoder is designed to capture keywords and phrase information from a local perspective. To fully leverage labels for better relation information extraction, we introduce a self-supervised relation of relation classification task.
  arXiv  Detail & Related papers  (2020-12-16T13:11:30Z)
• Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network [61.94394163309688]
  We propose a Label-enhanced Task-Adaptive Projection Network (L-TapNet) based on the state-of-the-art few-shot classification model -- TapNet. Experimental results show that our model significantly outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.
  arXiv  Detail & Related papers  (2020-06-10T07:50:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.