paper-with-me

홈 › Papers

A Joint Multitask Model for Morpho-Syntactic Parsing

2025-08-19 · Demian Inostroza, Mel Mistica, Ekaterina Vylomova, Chris Guest, Kemal Kurniawan arxiv

We present a joint multitask model for the UniDive 2025 Morpho-Syntactic Parsing shared task, where systems predict both morphological and syntactic analyses following novel UD annotation scheme. Our system uses a shared XLM-RoBERTa encoder with three specialized decoders for content word identification, dependency parsing, and morphosyntactic feature prediction. Our model achieves the best overall performance on the shared task's leaderboard covering nine typologically diverse languages, with an average MSLAS score of 78.7 percent, LAS of 80.1 percent, and Feats F1 of 90.3 percent. Our ablation studies show that matching the task's gold tokenization and content word identification are crucial to model performance. Error analysis reveals that our model struggles with core grammatical cases (particularly Nom-Acc) and nominal features across languages.

📄 PDF Abstract BibTeX arXiv:2508.14307

Code (0)

등록된 구현이 없습니다.

Tasks

Dependency Parsing

Similar Papers 제목 키워드 기반

Joint Transition-Based Models for Morpho-Syntactic Parsing: Parsing Strategies for MRLs and a Case Study from Modern Hebrew

2019-03-01 · TACL 2019 3 · Amir More, Amit Seker, Victoria Basmova, Reut Tsarfaty

In standard NLP pipelines, morphological analysis and disambiguation (MA{\&}D) precedes syntactic and semantic downstream tasks. However, for languages with complex and ambiguous word-internal structure, known as morphol…

Dependency ParsingMorphological Analysis

Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit

2020-11-01 · EMNLP 2020 11 · Amrith Krishna, Ashim Gupta, Deepak Garasangi, Pavankumar Satuluri 외

Morphologically rich languages seem to benefit from joint processing of morphology and syntax, as compared to pipeline architectures. We propose a graph-based model for joint morphological parsing and dependency parsing …

Dependency ParsingGraph GenerationStructured Prediction

Joint Morphological and Syntactic Analysis for Richly Inflected Languages

2013-01-01 · TACL 2013 1 · Bernd Bohnet, Joakim Nivre, Igor Boguslavsky, Rich{\'a}rd Farkas 외

Joint morphological and syntactic analysis has been proposed as a way of improving parsing accuracy for richly inflected languages. Starting from a transition-based model for joint part-of-speech tagging and dependency p…

Dependency ParsingPart-Of-Speech Tagging

A Graph-based Lattice Dependency Parser for Joint Morphological Segmentation and Syntactic Analysis

2015-01-01 · TACL 2015 1 · Wolfgang Seeker, {\"O}zlem {\c{C}}etino{\u{g}}lu

Space-delimited words in Turkish and Hebrew text can be further segmented into meaningful units, but syntactic and semantic context is necessary to predict segmentation. At the same time, predicting correct syntactic str…

Dependency ParsingMorphological AnalysisMorphological TaggingSegmentation+1

A Truly Joint Neural Architecture for Segmentation and Parsing

2024-02-04 · Danit Yshaayahu Levi, Reut Tsarfaty

Contemporary multilingual dependency parsers can parse a diverse set of languages, but for Morphologically Rich Languages (MRLs), performance is attested to be lower than other languages. The key challenge is that, due t…

ARCSegmentation