Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text

2020-05-19 · WS 2020 7 · Lukas Lange, Anastasiia Iurshina, Heike Adel, Jannik Strötgen

Although temporal tagging is still dominated by rule-based systems, there have been recent attempts at neural temporal taggers. However, all of them focus on monolingual settings. In this paper, we explore multilingual methods for the extraction of temporal expressions from text and investigate adversarial training for aligning embedding spaces to one common space. With this, we create a single multilingual model that can also be transferred to unseen languages and set the new state of the art in those cross-lingual transfer experiments.

📄 PDF Abstract BibTeX arXiv:2005.09392

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual Transfer Temporal Tagging

Methods 이 논문이 사용한 방법론

BERT BERT, or Bidirectional Encoder Representations from Transformers, improves upon standard Transformers by removing the…

fastText fastText embeddings exploit subword information to construct word embeddings. Representations are learnt of character $n$-grams, and words represented as the sum of the…

Multilingual Normalization of Temporal Expressions with Masked Language Models

2022-05-20 · Lukas Lange, Jannik Strötgen, Heike Adel, Dietrich Klakow

The detection and normalization of temporal expressions is an important task and preprocessing step for many applications. However, prior work on normalization is rule-based, which severely limits the applicability in re…

Language Modeling Language Modelling Masked Language Modeling

Romanian Multiword Expression Detection Using Multilingual Adversarial Training and Lateral Inhibition

2023-04-22 · Andrei-Marius Avram, Verginica Barbu Mititelu, Dumitru-Clementin Cercel

Multiword expressions are a key ingredient for developing large-scale and linguistically sound natural language processing technology. This paper describes our improvements in automatically identifying Romanian multiword…

Time-Independent and Language-Independent Extraction of Multiword Expressions From Twitter

2016-12-01 · COLING 2016 12 · Nikhil Londhe, Rohini Srihari, Vishrawas Gopalakrishnan

Multiword Expressions (MWEs) are crucial lexico-semantic units in any language. However, most work on MWEs has been focused on standard monolingual corpora. In this work, we examine MWE usage on Twitter - an inherently m…

Sentiment Analysis

Extending HeidelTime for Temporal Expressions Referring to Historic Dates

2014-05-01 · LREC 2014 5 · Jannik Str{\"o}tgen, Thomas B{\"o}gel, Julian Zell, Ayser Armiti 외

Research on temporal tagging has achieved a lot of attention during the last years. However, most of the work focuses on processing news-style documents. Thus, references to historic dates are often not well handled by t…

Articles Document Summarization Machine Translation Temporal Information Extraction+1

French Resources for Extraction and Normalization of Temporal Expressions with HeidelTime

2014-05-01 · LREC 2014 5 · V{\'e}ronique Moriceau, Xavier Tannier

In this paper, we describe the development of French resources for the extraction and normalization of temporal expressions with HeidelTime, a open-source multilingual, cross-domain temporal tagger. HeidelTime extracts t…

Articles Information Retrieval