Alignment-free Cross-lingual Semantic Role Labeling

Cai, Rui; Lapata, Mirella

doi:10.18653/v1/2020.emnlp-main.319

Cited by 6 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of dealing with heterogeneous linguistic theories, another line of research consists in actively studying the effect of using a single formalism across multiple languages through annotation projection or other transfer techniques (Akbik et al, 2015(Akbik et al, , 2016Daza and Frank, 2019;Cai and Lapata, 2020;Daza and Frank, 2020). However, such approaches often rely on word aligners and/or automatic translation tools which may introduce a considerable amount of noise, especially in lowresource languages.…”

Section: Introductionmentioning

confidence: 99%

Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources

Conia¹,

Bacciu²,

Navigli³

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

While cross-lingual techniques are finding increasing success in a wide range of Natural Language Processing tasks, their application to Semantic Role Labeling (SRL) has been strongly limited by the fact that each language adopts its own linguistic formalism, from Prop-Bank for English to AnCora for Spanish and PDT-Vallex for Czech, inter alia. In this work, we address this issue and present a unified model to perform cross-lingual SRL over heterogeneous linguistic resources. Our model implicitly learns a high-quality mapping for different formalisms across diverse languages without resorting to word alignment and/or translation techniques. We find that, not only is our cross-lingual system competitive with the current state of the art but that it is also robust to low-data scenarios. Most interestingly, our unified model is able to annotate a sentence in a single forward pass with all the inventories it was trained with, providing a tool for the analysis and comparison of linguistic theories across different languages. We release our code and model at https://github.com/ SapienzaNLP/unify-srl.

show abstract

Section: Introductionmentioning

confidence: 99%

Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources

Conia¹,

Bacciu²,

Navigli³

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…The second type of zero-shot CLT is to expose certain target languages directly in the training process, and many techniques have been proposed within this line of work. In the task of MRC, Hsu, Liu, and Lee (2019); Lee et al (2019); Cui et al (2019) obtain training corpus for target languages by utilizing translation and projecting silver labels; similar techniques are also used in other cross-lingual tasks such as SRL (Cai and Lapata 2020), POS tagging (Eskander, Muresan, and Collins 2020) and Abstract Meaning Representation (AMR) parsing (Blloshmi, Tripodi, and Navigli 2020). Other techniques such as self-learning (Xu et al 2021) and meta-learning (Li et al 2020;Nooralahzadeh et al 2020) are also proposed for CLT.…”

Section: Related Workmentioning

confidence: 99%

Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph

Zhang

Zong

et al. 2022

AAAI

View full text Add to dashboard Cite

We target the task of cross-lingual Machine Reading Comprehension (MRC) in the direct zero-shot setting, by incorporating syntactic features from Universal Dependencies (UD), and the key features we use are the syntactic relations within each sentence. While previous work has demonstrated effective syntax-guided MRC models, we propose to adopt the inter-sentence syntactic relations, in addition to the rudimentary intra-sentence relations, to further utilize the syntactic dependencies in the multi-sentence input of the MRC task. In our approach, we build the Inter-Sentence Dependency Graph (ISDG) connecting dependency trees to form global syntactic relations across sentences. We then propose the ISDG encoder that encodes the global dependency graph, addressing the inter-sentence relations via both one-hop and multi-hop dependency paths explicitly. Experiments on three multilingual MRC datasets (XQuAD, MLQA, TyDiQA-GoldP) show that our encoder that is only trained on English is able to improve the zero-shot performance on all 14 test sets covering 8 languages, with up to 3.8 F1 / 5.2 EM improvement on-average, and 5.2 F1 / 11.2 EM on certain languages. Further analysis shows the improvement can be attributed to the attention on the cross-linguistically consistent syntactic path. Our code is available at https://github.com/lxucs/multilingual-mrc-isdg.

show abstract

“…One method requires parallel corpora to extract alignments between source and target languages using machine translation (Padó and Lapata, 2005;Damonte and Cohen, 2017;Zhang et al, 2018;, often followed by projection of semantic representations (Reddy et al, 2017). The other method is to use parameter-shared models based on cross-lingual representations such as cross-lingual word embeddings (Duong et al, 2017;Susanto and Lu, 2017;Mulcaire et al, 2018;Hershcovich et al, 2019;Cai and Lapata, 2020), pretrained multilingual models (Zhu et al, 2020;Oepen et al, 2020), and universal POS tags (Blloshmi et al, 2020). Recently, Ozaki et al (2020); Samuel and Straka (2020); Dou et al (2020) conducted supervised German DRS parsing with pretrained multilingual models, but they did not explore zero-shot cross-lingual semantic parsing.…”

Section: Related Workmentioning

confidence: 99%

Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing

Yang

Fancellu

Webber

et al. 2021

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

View full text Add to dashboard Cite

The availability of corpora has led to significant advances in training semantic parsers in English. Unfortunately, for languages other than English, annotated data is limited and so is the performance of the developed parsers. Recently, pretrained multilingual models have been proven useful for zero-shot cross-lingual transfer in many NLP tasks. What else does it require to apply a parser trained in English to other languages for zero-shot cross-lingual semantic parsing? Will simple language-independent features help? To this end, we experiment with six Discourse Representation Structure (DRS) semantic parsers in English, and generalize them to Italian, German and Dutch, where there are only a small number of manually annotated parses available. Extensive experiments show that despite its simplicity, adding Universal Dependency (UD) relations and Universal POS tags (UPOS) as model-agnostic features achieves surprisingly strong improvement on all parsers. We have publicly released our code at https://github.com/GT-SALT/ Multilingual-DRS-Semantic-Parsing .

show abstract

Alignment-free Cross-lingual Semantic Role Labeling

Cited by 6 publications

References 30 publications

Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources

Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources

Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph

Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing

Contact Info

Product

Resources

About