Comparing learnability of two dependency schemes: ‘semantic’ (UD) and ‘syntactic’ (SUD) (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Several studies have suggested that choosing syntactic criteria for assigning heads in dependency trees improves the performance of dependency parsers. |
| Approach: | They propose to use syntactic criteria to assign heads to dependency trees to improve the performance of dependency parsers by using a selection of 21 treebanks. |
| Outcome: | The proposed approach favours content words over function words as heads of dependency relations, while the other favours syntactic heads. |
Similar Papers
Do Neural Language Models Show Preferences for Syntactic Formalisms? (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work on interpretability of deep neural language models concludes that many properties of natural language syntax are encoded in their representational spaces. |
| Approach: | They propose to examine whether syntactic structure adheres to a surface-syntactical or deep syntaktic style of analysis. |
| Outcome: | The proposed model prefers Universal Dependencies (UD) over Surface-Syntactic Universal Dependency (SUD) with interesting variations across languages and layers. |
Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations (2022.coling-1)
Copied to clipboard
| Challenge: | Existing semantic parsers are based on deep learning, but rule-based approaches offer advantages . a drawback of neural semantic parses is that their output lacks explainability . |
| Approach: | They propose a method that maps a syntactic dependency tree to a formal meaning representation using a series of graph transformations. |
| Outcome: | The proposed method outperforms neural parsers in English, German, Italian and Dutch. |
Annotations Matter: Leveraging Multi-task Learning to Parse UD and SUD (2021.findings-acl)
Copied to clipboard
| Challenge: | Multi-task learning (MTL) has shown promise in various NLP tasks such as semantic dependency parsing. |
| Approach: | They propose to use two parallel treebanks to improve parsing performance. |
| Outcome: | The proposed model is based on two parallel treebanks with similar annotation schemes but differing in linguistic annotation preferences. |
Spoken Language Treebanks in Universal Dependencies: an Overview (2022.lrec-1)
Copied to clipboard
| Challenge: | spoken language treebanks have divergent annotation schemes limiting cross-resource explorations . many spoken language trees have no written form, but many of the world languages have no spoken form at all. |
| Approach: | They propose to use the Universal Dependencies annotation scheme to annotate spoken language treebanks using a morphosyntactic annotation scheme. |
| Outcome: | The proposed treebanks differ significantly with respect to the inventory and format of transcribed phenomena and the principles adopted in their morphosyntactic annotation. |
Universal Dependencies According to BERT: Both More Specific and More General (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies show that individual BERT heads encode particular dependency relation types, but they do not match one-to-one. |
| Approach: | They propose a method for relation identification and syntactic tree construction that can be applied with minimal supervision and generalizes well across languages. |
| Outcome: | The proposed method produces significantly more consistent dependency trees than previous work and can be applied with only a minimal amount of supervision and generalizes well across languages. |
75 Languages, 1 Model: Parsing Universal Dependencies Universally (D19-1)
Copied to clipboard
| Challenge: | UDify is a multilingual multi-task model that can predict universal part-of-speech, morphological features, lemmas, and dependency trees. |
| Approach: | They evaluate UDify, a multilingual multi-task model capable of predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages. |
| Outcome: | The proposed model can predict universal part-of-speech, morphological features, lemmas, and dependency trees for all 124 treebanks across 75 languages. |
On the Continued Value of Universal Dependencies in the Era of Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | a growing belief that explicit linguistic representations are no longer necessary is questioned in large language models . a recent study examines whether and in what ways this cross-lingual syntactic framework can still benefit LLMs . |
| Approach: | They use Universal Dependencies (UD) to examine whether and in what ways it can still benefit LLMs. |
| Outcome: | The proposed model outperforms its syntax-agnostic counterparts in a cross-lingual evaluation task. |
Do UD Trees Match Mention Spans in Coreference Annotations? (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to annotate mention spans are based on delimiting token intervals, but there is no syntactic representation of the mention span. |
| Approach: | They propose to integrate coreference annotation with syntactic annotation to make them convergent in the long term. |
| Outcome: | The proposed approach could be advantageous in the long term, the authors argue. |
Parsing All: Syntax and Semantics, Dependencies and Spans (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Syntactic and semantic structures are key linguistic contextual clues, but few studies have explored how they can be used to improve syntactical parsing. |
| Approach: | They propose a syntactic and semantic parsing model which integrates syntaktic information in the encoder of neural network and benefits from two representation formalisms in a uniform way. |
| Outcome: | The proposed model achieves state-of-the-art or competitive results on both span and dependency representations and on Penn Treebank. |
Simpler but More Accurate Semantic Dependency Parsing (P18-2)
Copied to clipboard
| Challenge: | Syntactic dependency parsing is the most popular method for automatically extracting low-level relationships between words in a sentence. |
| Approach: | They extend a syntactic dependency parser to train on and generate graph-structured representations that capture between-word relationships that are more closely related to the meaning of a sentence. |
| Outcome: | The proposed system beats the current state-of-the-art system by 0.6% and linguistically richer representations push the margin even higher. |