Syntax-aware Multilingual Semantic Role Labeling

He, Shexia; Li, Zuchao; Zhao, Hai

doi:10.18653/v1/d19-1538

Cited by 31 publications

(30 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our baseline and full model with previous multilingual works. The performance of our baseline is similar to the model of He et al (2019), which integrated syntactic information and achieved the best results. This shows that our baseline is a very strong SRL model, and owes its success to directly modeling on the full semantic graph rather than separately based on predicates.…”

Section: Multilingual Resultsmentioning

confidence: 73%

High-order Semantic Role Labeling

Zhao

Wang

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships. Due to the limitations of modeling methods and the conditions of pre-identified predicates, previous work has focused on the relationships between predicates and arguments and the correlations between arguments at most, while the correlations between predicates have been neglected for a long time. High-order features and structure learning were very common in modeling such correlations before the neural network era. In this paper, we introduce a highorder graph structure for the neural semantic role labeling model, which enables the model to explicitly consider not only the isolated predicate-argument pairs but also the interaction between the predicate-argument pairs. Experimental results on 7 languages of the CoNLL-2009 benchmark show that the highorder structural learning techniques are beneficial to the strong performing SRL models and further boost our baseline to achieve new stateof-the-art results.

show abstract

Section: Multilingual Resultsmentioning

confidence: 73%

High-order Semantic Role Labeling

Zhao

Wang

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Biaffine attention scorer is used to label the gap (Dozat and Manning, 2017;Cai et al, 2018;Zhou and Zhao, 2019;He et al, 2019). The distribution of labels in a labeling task is often uneven.…”

Section: Biaffine Attention Scorermentioning

confidence: 99%

Attention Is All You Need for Chinese Word Segmentation

Duan¹,

Zhao²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

Taking greedy decoding algorithm as it should be, this work focuses on further strengthening the model itself for Chinese word segmentation (CWS), which results in an even more fast and more accurate CWS model. Our model consists of an attention only stacked encoder and a light enough decoder for the greedy segmentation plus two highway connections for smoother training, in which the encoder is composed of a newly proposed Transformer variant, Gaussian-masked Directional (GD) Transformer, and a biaffine attention scorer. With the effective encoder design, our model only needs to take unigram features for scoring. Our model is evaluated on SIGHAN Bakeoff benchmark datasets. The experimental results show that with the highest segmentation speed, the proposed model achieves new state-of-the-art or comparable performance against strong baselines in terms of strict closed test setting.

show abstract

“…Predicate embeddings are randomly initialized and updated constantly during model training. Unlike previous supervised SRL approaches (Roth and Lapata, 2016;Cai and Lapata, 2019;He et al, 2019), our model does not make use of any syntactic information (e.g., POS-tags, dependency relations) since we cannot assume it will be available for low-resource languages.…”

Section: Semantic Role Labelermentioning

confidence: 99%

Alignment-free Cross-lingual Semantic Role Labeling

Cai

Lapata

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Cross-lingual semantic role labeling (SRL) aims at leveraging resources in a source language to minimize the effort required to construct annotations or models for a new target language. Recent approaches rely on word alignments, machine translation engines, or preprocessing tools such as parsers or taggers. We propose a cross-lingual SRL model which only requires annotations in a source language and access to raw text in the form of a parallel corpus. The backbone of our model is an LSTM-based semantic role labeler jointly trained with a semantic role compressor and multilingual word embeddings. The compressor collects useful information from the output of the semantic role labeler, filtering noisy and conflicting evidence. It lives in a multilingual embedding space and provides direct supervision for predicting semantic roles in the target language. Results on the Universal Proposition Bank and manually annotated datasets show that our method is highly effective, even against systems utilizing supervised features. 1

show abstract

Syntax-aware Multilingual Semantic Role Labeling

Cited by 31 publications

References 28 publications

High-order Semantic Role Labeling

High-order Semantic Role Labeling

Attention Is All You Need for Chinese Word Segmentation

Alignment-free Cross-lingual Semantic Role Labeling

Contact Info

Product

Resources

About