Untitled

Kanerva, Jenna; Ginter, Filip; Miekka, Niko; Leino, Aila; Salakoski, Tapio

doi:10.18653/v1/k18-2013

Cited by 28 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Omorfi uses finite state transducers and can be used further for enhancing lemmatization (Silfverberg et al, 2016). The current state-of-the-art is represented by Turku neural parser pipeline (Kanerva et al, 2018), (Kanerva et al, 2019) that treats lemmatization as a sequence-to-sequence problem using the OpenNMT neural machine translation toolkit (Klein et al, 2017) and yields 95%-97% accuracy.…”

Section: Related Workmentioning

confidence: 99%

Dr. Livingstone, I presume? Polishing of foreign character identification in literary texts

Konovalova¹,

Toral²,

Taivalkoski-Shilov³

2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Character identification is a key element for many narrative-related tasks. To implement it, the baseform of the name of the character (or lemma) needs to be identified, so different appearances of the same character in the narrative could be aligned. In this paper we tackle this problem in translated texts (English-Finnish translation direction), where the challenge regarding lemmatizing foreign names in an agglutinative language appears. To solve this problem, we present and compare several methods. The results show that the method based on a search for the shortest version of the name proves to be the easiest, best performing (83.4% F 1 ), and most resource-independent.

show abstract

Section: Related Workmentioning

confidence: 99%

Dr. Livingstone, I presume? Polishing of foreign character identification in literary texts

Konovalova¹,

Toral²,

Taivalkoski-Shilov³

2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…In particular the Bi-LSTM-based deep biaffine neural dependency parser by Dozat and Manning (2017) has been quite popular and used in three out of five of the top submissions to the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (Zeman et al, 2018), in particular in the top non-ensemble submission (Kanerva et al, 2018).…”

Section: Syntactic Parsingmentioning

confidence: 99%

Biaffine Dependency and Semantic Graph Parsing for EnhancedUniversal Dependencies

Attardi¹,

Sartiano²,

Simi³

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

This paper presents the system used in our submission to the IWPT 2021 Shared Task. This year the official evaluation metrics was ELAS, therefore dependency parsing might have been avoided as well as other pipeline stages like POS tagging and lemmatization. We nevertheless chose to deploy a combination of a dependency parser and a graph parser. The dependency parser is a biaffine parser, that uses transformers for representing input sentences, with no other feature. The graph parser is a semantic parser that exploits a similar architecture except for using a sigmoid crossentropy loss function to return multiple values for the predicted arcs. The final output is obtained by merging the output of the two parsers. The dependency parser achieves top or close to top LAS performance with respect to other systems that report results on such metrics, except on low resource languages (Tamil, Estonian, Latvian).

show abstract

“…Parser Analyses and Comparisons. Recent years have seen a wide range of studies comparing different language models for dependency parsing (e.g., Kanerva et al, 2018;Smith et al, 2018). Additionally, several studies have investigated the amount of implicit syntactic information captured in pre-trained LMs such as ELMo and BERT (Tenney et al, 2019a,b;Hewitt and Manning, 2019).…”

Section: Related Workmentioning

confidence: 99%

“…(2) the rise of pre-trained distributed word representations, particularly transformer-based contextualized embeddings such as BERT (Devlin et al, 2019) or RoBERTa (Liu et al, 2019). Both characteristics are present in recent top-performing systems (Che et al, 2018;Kondratyuk and Straka, 2019;Kanerva et al, 2018Che et al, 2018). However, there remain a considerable number of implementation and configuration choices whose impact on parser performance is less well understood.…”

Section: Introductionmentioning

confidence: 99%

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

Untitled

Cited by 28 publications

References 9 publications

Dr. Livingstone, I presume? Polishing of foreign character identification in literary texts

Dr. Livingstone, I presume? Polishing of foreign character identification in literary texts

Biaffine Dependency and Semantic Graph Parsing for EnhancedUniversal Dependencies

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

Contact Info

Product

Resources

About