581 |
Multilingual Irony Detection with Dependency Syntax and Neural Models ...
|
|
|
|
BASE
|
|
Show details
|
|
582 |
SaSAKE: Syntax and Semantics Aware Keyphrase Extraction from Research Papers ...
|
|
|
|
BASE
|
|
Show details
|
|
583 |
Sampling, Syntax, and Sentence Completions.The (Overlooked?) Impact of Gender on NLP Tools ...
|
|
|
|
BASE
|
|
Show details
|
|
584 |
Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
585 |
Bridging the Gap in Multilingual Semantic Role Labeling: A Language-Agnostic Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
586 |
Syntactically Aware Cross-Domain Aspect and Opinion Terms Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
587 |
Exploring diachronic syntactic shifts with dependency length: the case of scientific English ...
|
|
|
|
BASE
|
|
Show details
|
|
589 |
Style Analysis of Argumentative Texts by Mining Rhetorical Devices ...
|
|
|
|
BASE
|
|
Show details
|
|
590 |
Anaphoric Zero Pronoun Identification: A Multilingual Approach ...
|
|
|
|
Abstract:
Pro-drop languages such as Arabic, Chinese, Italian or Japanese allow morphologically null but referential arguments in certain syntactic positions, called anaphoric zero-pronouns. Much NLP work on anaphoric zero-pronouns (AZP) is based on gold mentions, but models for their identification are a fundamental prerequisite for their resolution in real-life applications. Such identification requires complex language understanding and knowledge of real-world entities. Transfer learning models, such as BERT, have recently shown to learn surface, syntactic, and semantic information,which can be very useful in recognizing AZPs. We propose a BERT-based multilingual model for AZP identification from predicted zero pronoun positions, and evaluate it on the Arabic and Chinese portions of OntoNotes 5.0. As far as we know, this is the first neural network model of AZP identification for Arabic; and our approach outperforms the state-of-the-art for Chinese. Experiment results suggest that BERT implicitly encode information ...
|
|
Keyword:
Computer and Information Science; Digital Media; Engineering; Information and Knowledge Engineering; Natural Language Processing; Neural Network
|
|
URL: https://underline.io/lecture/6575-anaphoric-zero-pronoun-identification-a-multilingual-approach https://dx.doi.org/10.48448/ysaj-n577
|
|
BASE
|
|
Hide details
|
|
591 |
Collective Wisdom: Improving Low-resource Neural Machine Translationusing Adaptive Knowledge Distillation ...
|
|
|
|
BASE
|
|
Show details
|
|
592 |
Learning to Decouple Relations: Few-Shot Relation Classification with entity-Guided Attention and Confusion-Aware Training ...
|
|
|
|
BASE
|
|
Show details
|
|
596 |
Automatic Topological Field Identification in (Historical) German Texts ...
|
|
|
|
BASE
|
|
Show details
|
|
597 |
A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
598 |
Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation ...
|
|
|
|
BASE
|
|
Show details
|
|
600 |
Variation in Coreference Strategies across Genres and Production Media ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|