Joakim Nivre · page 2
Papers
- Analyzing and Integrating Dependency Parsers (2011 · 179 citations)
After the CoNLL shared tasks released treebanks for many languages, research on data-driven dependency parsing grew rapidly. - Talbanken05: A Swedish Treebank with Phrase Structure and Dependency Annotation (2006 · 164 citations)
For a long time Swedish had no large publicly available treebank, even though one of the very first syntactically annotated corpora, the Talbanken of the 1970s, was Swedish. - Dependency Parsing of Turkish (2008 · 124 citations)
The paper asks how well data-driven dependency parsing works for Turkish, a language with agglutinative morphology, flexible constituent order and mostly head-final structure. - Evaluation of Dependency Parsers on Unbounded Dependencies (2010 · 85 citations)
Unbounded dependencies, such as an object that is extracted from a relative clause, are a standard test of grammar-based parsers, but had not been applied to dependency parsers. - Single Malt or Blended? A Study in Multilingual Parser Optimization (2007 · 65 citations)
This paper describes how the Växjö/Uppsala team adapted MaltParser to the ten languages of the CoNLL 2007 multilingual dependency parsing shared task: Arabic, Basque, Catalan, Chinese, Czech, English, Greek, Hungarian, Italian and Turkish. The work proceeded in two stages. - Enhancing Universal Dependency Treebanks: A Case Study (2018 · 59 citations)
Only five of the 102 UD 2.1 treebanks have enhanced dependencies, so the authors test whether enhanced graphs can be added to other treebanks automatically. - Latent Anaphora Resolution for Cross-Lingual Pronoun Prediction (2013 · 58 citations)
The paper defines cross-lingual pronoun prediction as a task. The input is an English text containing one of the subject pronouns he, she, it or they, its human French translation, and automatic GIZA++ word alignments. The system must predict which French word the pronoun is aligned to. The correct French form often… - Divisible Transition Systems and Multiplanar Dependency Parsing (2013 · 54 citations)
Transition-based dependency parsers are fast, but the many existing transition systems were described in different formalisms, and efficient handling of non-projective structure remained difficult. - Normalisation of Historical Text Using Context-Sensitive Weighted Levenshtein Distance and Compound Splitting (2013 · 53 citations)
The paper normalizes historical Swedish spelling to modern forms by comparing each historical token with a modern dictionary. - Evaluating Dependency Parsing: Robust and Heuristics-Free Cross-Annotation Evaluation (2011 · 46 citations)
Attachment scores compare parsers only within one treebank scheme. Two parsers trained on different conversions of the Penn Treebank can differ mainly because of annotation choices, such as the head of a prepositional phrase or of a copula. The authors propose TEDEVAL: each dependency tree is mapped by deterministic… - Sentences with Gapping: Parsing and Reconstructing Elided Predicates (2018 · 40 citations)
In "Paul likes coffee and Mary tea" the verb is elided, so standard parsers attach the remnants badly and downstream relation extraction misses the predicate. - Continual Learning Under Language Shift (2023 · 24 citations)
Retraining large language models from scratch each time new data appears is costly. This paper asks what happens when an existing model is instead updated with text in previously unseen languages. The authors train GPT-style models with 126M, 356M and 1.3B parameters, first on English. They then add Danish, Icelandic… - Anaphora Models and Reordering for Phrase-Based SMT (2014 · 13 citations)
This WMT14 system description from Uppsala University explores how discourse-level and word-order phenomena can be modelled in phrase-based SMT. - Nucleus Composition in Transition-based Dependency Parsing (2022 · 9 citations)
Following Tesnière, the paper takes the syntactic nucleus, a unit that can be one word or several (for example an auxiliary with its verb, or a case marker with its noun), as the elementary unit of parsing. - Constructions and Strategies in Universal Dependencies (2025 · 6 citations)
This is a position paper. The author examines whether the Universal Dependencies (UD) annotation scheme is compatible with data from linguistic typology. As a reference point, he takes William Croft's book "Morphosyntax" (2022). Croft distinguishes between constructions and strategies. Constructions are universal… - A Dataset of Wolof Ajami Manuscripts for HTR and OCR (2026)
Systems for recognizing Arabic-script text struggle with African languages that use Ajami, the adapted Arabic orthographies of West Africa. - Named Entity Recognition for Persian Literary Text: A Case Study on The Little Prince (2026)
Persian NER work has so far targeted news, social media and Wikipedia. Literary prose has been left aside, even though fiction often refers to entities through descriptions, figurative wording or story context rather than explicit proper names. According to the authors, their corpus is the earliest Persian dataset of…
This page in Markdown → https://md.research.elamur.ai/free/en/authors/joakim-nivre/page/2/