RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy

2016-04-05 · SEMEVAL 2016 6 · Guntis Barzdins, Didzis Gosko

Two extensions to the AMR smatch scoring script are presented. The first extension com-bines the smatch scoring script with the C6.0 rule-based classifier to produce a human-readable report on the error patterns frequency observed in the scored AMR graphs. This first extension results in 4% gain over the state-of-art CAMR baseline parser by adding to it a manually crafted wrapper fixing the identified CAMR parser errors. The second extension combines a per-sentence smatch with an en-semble method for selecting the best AMR graph among the set of AMR graphs for the same sentence. This second modification au-tomatically yields further 0.4% gain when ap-plied to outputs of two nondeterministic AMR parsers: a CAMR+wrapper parser and a novel character-level neural translation AMR parser. For AMR parsing task the character-level neural translation attains surprising 7% gain over the carefully optimized word-level neural translation. Overall, we achieve smatch F1=62% on the SemEval-2016 official scor-ing set and F1=67% on the LDC2015E86 test set.

📄 PDF Abstract BibTeX arXiv:1604.01278

Code (2)

didzis/smatchTools 공식 구현

didzis/tensorflowAMR 공식 구현 tf

Tasks

AMR ParsingSentenceTranslation

RIGOTRIO at SemEval-2017 Task 9: Combining Machine Learning and Grammar Engineering for AMR Parsing and Generation

2017-08-01 · SEMEVAL 2017 8 · Normunds Gruzitis, Didzis Gosko, Guntis Barzdins

By addressing both text-to-AMR parsing and AMR-to-text generation, SemEval-2017 Task 9 established AMR as a powerful semantic interlingua. We strengthen the interlingual aspect of AMR by applying the multilingual Grammat…

AMR Parsing AMR-to-Text Generation BIG-bench Machine Learning NER+1

RIGA at SemEval-2022 Task 1: Scaling Recurrent Neural Networks for CODWOE Dictionary Modeling

2022-07-01 · SemEval (NAACL) 2022 7 · Eduards Mukans, Gus Strazds, Guntis Barzdins

Described are our two entries “emukans” and “guntis” for the definition modeling track of CODWOE SemEval-2022 Task 1. Our approach is based on careful scaling of a GRU recurrent neural network, which exhibits double desc…

L2F/INESC-ID at SemEval-2017 Tasks 1 and 2: Lexical and semantic features in word and textual similarity

2017-08-01 · SEMEVAL 2017 8 · Pedro Fialho, Hugo Patinho Rodrigues, Lu{\'\i}sa Coheur, Paulo Quaresma

This paper describes our approach to the SemEval-2017 {``}Semantic Textual Similarity{''} and {``}Multilingual Word Similarity{''} tasks. In the former, we test our approach in both English and Spanish, and use a linguis…

Abstract Meaning Representation Semantic Textual Similarity Word Embeddings Word Similarity

High-resolution global irrigation prediction with Sentinel-2 30m data

2020-12-09 · Weixin, Wu, Sonal Thakkar, Will Hawkins 외

An accurate and precise understanding of global irrigation usage is crucial for a variety of climate science efforts. Irrigation is highly energy-intensive, and as population growth continues at its current pace, increas…

Clustering Vocal Bursts Intensity Prediction

RUFINO at SemEval-2017 Task 2: Cross-lingual lexical similarity by extending PMI and word embeddings systems with a Swadesh's-like list

2017-08-01 · SEMEVAL 2017 8 · Sergio Jimenez, George Due{\~n}as, Lorena Gaitan, Jorge Segura

The RUFINO team proposed a non-supervised, conceptually-simple and low-cost approach for addressing the Multilingual and Cross-lingual Semantic Word Similarity challenge at SemEval 2017. The proposed systems were cross-l…

Semantic Textual Similarity Task 2 Word Embeddings Word Sense Disambiguation+1