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

2020-10-05 · EMNLP 2020 11 · Angel Daza, Anette Frank

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 high-quality 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 mono- and multilingual SRL, showing that the multilingual annotations improve performance especially for the weaker languages.

📄 PDF Abstract BibTeX arXiv:2010.01998

Code (1)

Heidelberg-NLP/xsrl_mbert_aligner 공식 구현

Tasks

Machine Translation Semantic Role Labeling Translation

Methods 이 논문이 사용한 방법론

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

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

WordPiece 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…

Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

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

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

2019-08-29 · IJCNLP 2019 11 · Angel Daza, Anette Frank

We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language. Unlike annotation projection techniques,…

Decoder Semantic Role Labeling

Alignment-free Cross-lingual Semantic Role Labeling

2020-11-01 · EMNLP 2020 11 · Rui Cai, Mirella Lapata

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 al…

Machine Translation Multilingual Word Embeddings Semantic Role Labeling Translation+1

UniteD-SRL: A Unified Dataset for Span- and Dependency-Based Multilingual and Cross-Lingual Semantic Role Labeling

2021-11-01 · Findings (EMNLP) 2021 11 · Rocco Tripodi, Simone Conia, Roberto Navigli

Multilingual and cross-lingual Semantic Role Labeling (SRL) have recently garnered increasing attention as multilingual text representation techniques have become more effective and widely available. While recent work ha…

Cross-Lingual Transfer Semantic Role Labeling

Polyglot Semantic Role Labeling

2018-05-29 · ACL 2018 7 · Phoebe Mulcaire, Swabha Swayamdipta, Noah Smith

Previous approaches to multilingual semantic dependency parsing treat languages independently, without exploiting the similarities between semantic structures across languages. We experiment with a new approach where we …

Dependency Parsing Semantic Dependency Parsing Semantic Role Labeling

Building a Hebrew Semantic Role Labeling Lexical Resource from Parallel Movie Subtitles

2020-05-17 · LREC 2020 5 · Ben Eyal, Michael Elhadad

We present a semantic role labeling resource for Hebrew built semi-automatically through annotation projection from English. This corpus is derived from the multilingual OpenSubtitles dataset and includes short informal …

Morphological Analysis Semantic Role Labeling