paper-with-me

홈 › Papers

Towards Semi-Supervised Learning for Deep Semantic Role Labeling

2018-08-28 · EMNLP 2018 10 · Sanket Vaibhav Mehta, Jay Yoon Lee, Jaime Carbonell

Neural models have shown several state-of-the-art performances on Semantic Role Labeling (SRL). However, the neural models require an immense amount of semantic-role corpora and are thus not well suited for low-resource languages or domains. The paper proposes a semi-supervised semantic role labeling method that outperforms the state-of-the-art in limited SRL training corpora. The method is based on explicitly enforcing syntactic constraints by augmenting the training objective with a syntactic-inconsistency loss component and uses SRL-unlabeled instances to train a joint-objective LSTM. On CoNLL-2012 English section, the proposed semi-supervised training with 1%, 10% SRL-labeled data and varying amounts of SRL-unlabeled data achieves +1.58, +0.78 F1, respectively, over the pre-trained models that were trained on SOTA architecture with ELMo on the same SRL-labeled data. Additionally, by using the syntactic-inconsistency loss on inference time, the proposed model achieves +3.67, +2.1 F1 over pre-trained model on 1%, 10% SRL-labeled data, respectively.

📄 PDF Abstract BibTeX arXiv:1808.09543

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Role Labeling

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
ELMo Embeddings from Language Models, or ELMo, is a type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and…

Similar Papers 제목 키워드 기반

Semi-Supervised Semantic Role Labeling: Approaching from an Unsupervised Perspective

2012-12-01 · COLING 2012 12 · Ivan Titov, Alex Klementiev, re
Semantic Role Labeling

Semi-Supervised Semantic Role Labeling via Structural Alignment

2012-01-01 · CL 2012 1 · Hagen F{\"u}rstenau, Mirella Lapata
Semantic Role Labeling

Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training

2016-12-01 · COLING 2016 12 · Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens

We present a successful collaboration of word embeddings and co-training to tackle in the most difficult test case of semantic role labeling: predicting out-of-domain and unseen semantic frames. Despite the fact that co-…

Semantic Role LabelingWord Embeddings

Semi-Supervised Semantic Role Labeling with Cross-View Training

2019-11-01 · IJCNLP 2019 11 · Rui Cai, Mirella Lapata

The successful application of neural networks to a variety of NLP tasks has provided strong impetus to develop end-to-end models for semantic role labeling which forego the need for extensive feature engineering. Recent …

Dependency ParsingFeature EngineeringPOSPOS Tagging+2

Structured Consistency Loss for semi-supervised semantic segmentation

2020-01-14 · Jongmok Kim, Jooyoung Jang, Hyunwoo Park, Seongah Jeong

The consistency loss has played a key role in solving problems in recent studies on semi-supervised learning. Yet extant studies with the consistency loss are limited to its application to classification tasks; extant st…

General ClassificationSegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation