Semantic Role Labeling as Syntactic Dependency Parsing

Shi, Tingna; Malioutov, Igor; İrsoy, Ozan

doi:10.18653/v1/2020.emnlp-main.610

Cited by 10 publications

(8 citation statements)

References 112 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work may address multilingual approaches such as the training setup used by UDify or the recently proposed UDapter (Üstün et al, 2020), which aims at boosting performance of low-resource languages while keeping performance of high-resource languages high. Furthermore, it would be interesting to see if our results about biaffine achitectures also hold for non-syntactic tasks that have recently been framed as dependency parsing tasks, such as Named Entity Recognition (Yu et al, 2020), negation scope detection (Kurtz et al, 2020) or Semantic Role Labeling (Shi et al, 2020).…”

Section: Discussionmentioning

confidence: 91%

Applying Occam’s Razor to Transformer-Based Dependency Parsing: What Works, What Doesn’t, and What is Really Necessary

Grünewald¹,

Friedrich²,

Kuhn³

2021

Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing Into Enhanced

View full text Add to dashboard Cite

The introduction of pre-trained transformerbased contextualized word embeddings has led to considerable improvements in the accuracy of graph-based parsers for frameworks such as Universal Dependencies (UD). However, previous works differ in various dimensions, including their choice of pre-trained language models and whether they use LSTM layers. With the aims of disentangling the effects of these choices and identifying a simple yet widely applicable architecture, we introduce STEPS, a new modular graph-based dependency parser. Using STEPS, we perform a series of analyses on the UD corpora of a diverse set of languages. We find that the choice of pre-trained embeddings has by far the greatest impact on parser performance and identify XLM-R as a robust choice across the languages in our study. Adding LSTM layers provides no benefits when using transformerbased embeddings. A multi-task training setup outputting additional UD features may contort results. Taking these insights together, we propose a simple but widely applicable parser architecture and configuration, achieving new state-of-the-art results (in terms of LAS) for 10 out of 12 diverse languages. 1

show abstract

Section: Discussionmentioning

confidence: 91%

Applying Occam’s Razor to Transformer-Based Dependency Parsing: What Works, What Doesn’t, and What is Really Necessary

Grünewald¹,

Friedrich²,

Kuhn³

2021

Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing Into Enhanced

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 91%

Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)

2021

View full text Add to dashboard Cite

When learned without exploration, local models for structured prediction tasks are subject to exposure bias and cannot be trained without detailed guidance. Active Imitation Learning (AIL), also known in NLP as Dynamic Oracle Learning, is a general technique for working around these issues by allowing the exploration of different outputs at training time.AIL requires oracle feedback: an oracle is any algorithm which can, given a partial candidate solution and gold annotation, find the correct (minimum loss) next output to produce. This paper describes a general finite state technique for deriving oracles. The technique described is also efficient and will greatly expand the tasks for which AIL can be used.

show abstract

“…Even with recent developments in neural network modeling, with which syntax-agnostic models have been shown to match linguistically-informed counterparts Cai et al, 2018), syntax has also been found helpful for SRL Strubell et al, 2018;Cai and Lapata, 2019;Shi et al, 2020;Fei et al, 2021). In this work, we further explore the helpfulness of syntax for cross-lingual SRL.…”

Section: Syntax and Srlmentioning

confidence: 87%

On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling

Zhang¹,

Strubell²,

Hovy³

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Although recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challenging for languages where supervised SRL training data are not abundant. Cross-lingual learning can improve performance in this setting by transferring knowledge from high-resource languages to low-resource ones. Moreover, we hypothesize that annotations of syntactic dependencies can be leveraged to further facilitate cross-lingual transfer. In this work, we perform an empirical exploration of the helpfulness of syntactic supervision for crosslingual SRL within a simple multitask learning scheme. With comprehensive evaluations across ten languages (in addition to English) and three SRL benchmark datasets, including both dependency-and span-based SRL, we show the effectiveness of syntactic supervision in low-resource scenarios.

show abstract

Semantic Role Labeling as Syntactic Dependency Parsing

Cited by 10 publications

References 112 publications

Applying Occam’s Razor to Transformer-Based Dependency Parsing: What Works, What Doesn’t, and What is Really Necessary

Applying Occam’s Razor to Transformer-Based Dependency Parsing: What Works, What Doesn’t, and What is Really Necessary

Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)

On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling

Contact Info

Product

Resources

About