Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling

Daza, Angel; Frank, Anette

doi:10.18653/v1/d19-1056

Cited by 15 publications

(18 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…He et al (2019) propose a biaffine scorer with syntax rules to prune of candidates, achieving SOTA independently in all languages from CoNLL-09. Mulcaire et al (2018) and Daza and Frank (2019) train a single model using input data from different languages and obtain modest improvements, especially for languages where less monolingual training data is available. In this sense, our X-SRL corpus contributes with more compatible training data across languages, and aims to improve the performance of jointly trained multilingual models.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset

Daza

Frank

2020

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

Self Cite

View full text Add to dashboard Cite

Even though SRL is researched for many languages, major improvements have mostly been obtained for English, for which more resources are available. In fact, existing multilingual SRL datasets contain disparate annotation styles or come from different domains, hampering generalization in multilingual learning.In this work we propose a method to automatically construct an SRL corpus that is parallel in four languages: English, French, German, Spanish, with unified predicate and role annotations that are fully comparable across languages. We apply high-quality machine translation to the English CoNLL-09 dataset and use multilingual BERT to project its highquality annotations to the target languages. We include human-validated test sets that we use to measure the projection quality, and show that projection is denser and more precise than a strong baseline. Finally, we train different SOTA models on our novel corpus for monoand multilingual SRL, showing that the multilingual annotations improve performance especially for the weaker languages.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Table 7 summarizes the results. The model of Daza and Frank (2019) is an Encoder-Decoder model that was designed for multilingual SRL. It performs poorly when trained on monolingual data but improves significantly when trained with more data (multilingual setting).…”

Section: Training Srl Systems On X-srlmentioning

confidence: 99%

X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset

Daza

Frank

2020

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…Translation-based approaches have been gaining popularity in cross-lingual dependency parsing (Rasooli and Collins, 2015;Tiedemann, 2015; and have recently been applied to SRL (Fei et al, 2020). Daza and Frank (2019b) propose a cross-lingual encoder-decoder model that simultaneously translates and generates sentences with semantic role annotations in a resource-poor target language. Rather than creating annotations or models for a target language, other work aims to exploit the similarities between languages.…”

Section: Related Workmentioning

confidence: 99%

“…Translation-based approaches (Täckström et al, 2012;Fei et al, 2020;Rasooli and Collins, 2015) aim to alleviate the noise brought by the the source-side labeler by directly translating the gold-standard data into the target language. A third alternative is model transfer where a source-language model is modified in a way that it can be directly applied to a new language, e.g., by employing cross-lingual word representations (Täckström et al, 2012;Swayamdipta et al, 2016;Daza and Frank, 2019a) and universal POS tags (McDonald et al, 2013).…”

Section: Introductionmentioning

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

“…Both the input and output sequence are variable-length, and can be effectively represented in this model. The encoder-decoder model can be applied to NLP task and achieve promising performance [30]- [32].…”

Section: B Encoder-decoder Modelmentioning

confidence: 99%

Keyphrase Generation With CopyNet and Semantic Web

Zhu

Lyu

2020

IEEE Access

View full text Add to dashboard Cite

Keyphrases provide core information for users to understand the document. Most previous works utilize machine learning based methods for keyphrases extraction and achieve promising performance. However, these methods focus on identify keyphrases from the input text, and can not extract keyphrases that do not appear in the text. In this paper, we present an encoder-decoder framework, which incorporating copying mechanism, to generate keyphrases for the given text. This framework (CopyNet) integrates the generation part and copying part. The generation part generates the keyphrase from the predefined vocabulary, and the copy part gets the keyphrases from the source text. Furthermore, we improve the CopyNet by using different probability of the two parts. To incorporate more related information for keyphrase generation, the automatically built keyphrase semantic web is merged into the dataset to participate in the training process of the neural network. Semantic similarity based and word co-occurrence based methods are used for keyphrase semantic web construction. We build a large-scale biomedical keyphrase dataset to evaluate the system performance. Experiments show that our improved CopyNet can achieve better performance with different portions of the generation and copying part, and the incorporation of the semantic web also effectively improves the keyphrase generation. INDEX TERMS Keyphrase generation, encoder-decoder model, copying mechanism, semantic web.

show abstract

Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling

Cited by 15 publications

References 48 publications

X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset

X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset

Alignment-free Cross-lingual Semantic Role Labeling

Keyphrase Generation With CopyNet and Semantic Web

Contact Info

Product

Resources

About