FrameNet Annotations Alignment using Attention-based Machine Translation

2020-05-01 · LREC 2020 5 · Gabriel Marzinotto

This paper presents an approach to project FrameNet annotations into other languages using attention-based neural machine translation (NMT) models. The idea is to use an NMT encoder-decoder attention matrix to propose a word-to-word correspondence between the source and the target language. We combine this word alignment along with a set of simple rules to securely project the FrameNet annotations into the target language. We successfully implemented, evaluated and analyzed this technique on the English-to-French configuration. First, we analyze the obtained FrameNet lexicon qualitatively. Then, we use existing French FrameNet corpora to assert the quality of the translation. Finally, we trained a BERT-based FrameNet parser using the projected annotations and compared it to a BERT baseline. Results show substantial improvements in the French language, giving evidence to support that our approach could help to propagate FrameNet data-set on other languages.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder Machine TranslationNMTTranslation Word Alignment

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Weight Decay 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Adam 설명 없음

Multi-Head Attention 설명 없음

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Graph Methods for Multilingual FrameNets

2017-08-01 · WS 2017 8 · Collin F. Baker, Michael Ellsworth

This paper introduces a new, graph-based view of the data of the FrameNet project, which we hope will make it easier to understand the mixture of semantic and syntactic information contained in FrameNet annotation. We sh…

Semantic Role Labeling Sentence

Applying FrameNet to Chinese(Poetry)

2022-10-11 · Zirong Chen

FrameNet( Fillmore and Baker [2009] ) is well-known for its wide use for knowledge representation in the form of inheritance-based ontologies and lexica( Trott et al. [2020] ). Although FrameNet is usually applied to lan…

Translation

Towards Reference-Aware FrameNet Annotation

2020-05-01 · LREC 2020 5 · Levi Remijnse, Gosse Minnema

In this paper, we introduce the task of using FrameNet to link structured information about real-world events to the conceptual frames used in texts describing these events. We show that frames made relevant by the knowl…

Greek within the Global FrameNet Initiative: Challenges and Conclusions so far

2020-05-01 · LREC 2020 5 · Voula Giouli, Vera Pilitsidou, Hephaestion Christopoulos

Large coverage lexical resources that bear deep linguistic information have always been considered useful for many natural language processing (NLP) applications including Machine Translation (MT). In this respect, Frame…

Machine Translation Translation

Relating Frames and Constructions in Japanese FrameNet

2014-05-01 · LREC 2014 5 · Kyoko Ohara

Relations between frames and constructions must be made explicit in FrameNet-style linguistic resources such as Berkeley FrameNet (Fillmore {\&} Baker, 2010, Fillmore, Lee-Goldman {\&} Rhomieux, 2012), Japanese FrameNet …