Another Dead End for Morphological Tags? Perturbed Inputs and Parsing
The usefulness of part-of-speech tags for parsing has been heavily questioned due to the success of word-contextualized parsers. Yet, most studies are limited to coarse-grained tags and high quality written content; while we know little about their influence when it comes to models in production that face lexical errors. We expand these setups and design an adversarial attack to verify if the use of morphological information by parsers: (i) contributes to error propagation or (ii) if on the other hand it can play a role to correct mistakes that word-only neural parsers make. The results on 14 diverse UD treebanks show that under such attacks, for transition- and graph-based models their use contributes to degrade the performance even faster, while for the (lower-performing) sequence labeling parsers they are helpful. We also show that if morphological tags were utopically robust against lexical perturbations, they would be able to correct parsing mistakes.
Code (1)
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
Improving neural morphological Tagging using Language Models
This paper addresses the task of morphological tagging and demonstrates how neural network architectures bene t from using language models for morphological tags. We show that incorporating the probabilities from languag…
Language ModelingLanguage ModellingMorphological TaggingNLP@UIT at SemEval-2019 Task 4: The Paparazzo Hyperpartisan News Detector
This paper describes the system of NLP@UIT that participated in Task 4 of SemEval-2019. We developed a system that predicts whether an English news article follows a hyperpartisan argumentation. Paparazzo is the name of …
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Cross-Lingual Morphological Tagging for Low-Resource Languages
Morphologically rich languages often lack the annotated linguistic resources required to develop accurate natural language processing tools. We propose models suitable for training morphological taggers with rich tagsets…
Morphological TaggingMorpheus: A Neural Network for Jointly Learning Contextual Lemmatization and Morphological Tagging
In this study, we present Morpheus, a joint contextual lemmatizer and morphological tagger. Morpheus is based on a neural sequential architecture where inputs are the characters of the surface words in a sentence and the…
DecoderLemmatizationMorphological TaggingSentence+1Do LSTMs really work so well for PoS tagging? -- A replication study
A recent study by Plank et al. (2016) found that LSTM-based PoS taggers considerably improve over the current state-of-the-art when evaluated on the corpora of the Universal Dependencies project that use a coarse-grained…
Feature EngineeringPart-Of-Speech TaggingPOSPOS Tagging