Challenge: Contextual word embedding models rely on sub-word tokenization to represent single orthographic words but are often suboptimal in under-resourced contexts.
Approach: They propose to use a masked language modelling task to evaluate the model's performance . they use re-trained tokenizers to pre-split compounds into constituents .
Outcome: The proposed models improve on the masked language modelling task and compositionality prediction by pre-splitting compounds into constituents.

Similar Papers

Modeling the Evolution of English Noun Compounds with Feature-Rich Diachronic Compositionality Prediction (2025.acl-long)

Copied to clipboard

Challenge: Empirical research directly addressing these issues is limited to a small number of studies suggesting that compounding is a highly productive process.
Approach: They represent English noun compounds as vectors of time-specific values and implement a set of features to classify them for present-day compositionality and assess the informativeness of the corresponding linguistic patterns.
Outcome: The proposed method captures relevant and complementary information across approaches and shows that low-compositional meanings are reflected by a parallel drop in compositionality and sustained semantic change.
Variants of Vector Space Reductions for Predicting the Compositionality of English Noun Compounds (2020.lrec-1)

Copied to clipboard

Challenge: Existing approaches to predict the degree of compositionality of noun compounds are based on comparing compounds and their constituents within a vector space and using distributional similarity as a proxy to predict their degree of semantic relatedness.
Approach: They propose to use distributional similarity as a proxy to predict the semantic relatedness between the compounds and their constituents as the compound’s degree of compositionality.
Outcome: The proposed methods are most successful and stable in terms of dimensionality and part-of-speech reductions.
Splintering Nonconcatenative Languages for Better Tokenization (2025.findings-acl)

Copied to clipboard

Challenge: Subword tokenizers are not effective in nonconcatenative languages such as Hebrew and Arabic, where morphology is encoded in root-template patterns, or Malay and Georgian, where split affixes are common.
Approach: They propose a pre-processing step which rearranges text into a linear form that better represents nonconcatenative morphologies.
Outcome: The proposed method is based on measures evaluating token vocabularies in Hebrew, Arabic, and Malay, and on BERT-architecture models trained for Hebrew.
CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Currently, there is no dataset containing compound and non-compound words across languages . however, current LLMs perform poorly on words tokenized unfavorably by subword tokenization.
Approach: They propose to use a Wiktionary dataset to evaluate large language models on decompounding . they find that current LLMs perform poorly on words tokenized unfavorably .
Outcome: The proposed model outperforms the best unsupervised models by 13.9% accuracy on average.
A Systematic Search for Compound Semantics in Pretrained BERT Architectures (2023.eacl-main)

Copied to clipboard

Challenge: Existing models for noun compounds have been less successful in predicting compositionality than transformers . authors: suboptimal use of encoded information may be a contributing factor . performance of transformer-based models is poor, authors say .
Approach: They propose to use semantic knowledge derived from pretrained BERT to predict compositionality . they find distinct linguistic roles of heads and modifiers are reflected by differences in BERT representations .
Outcome: The proposed model improves on unsupervised implementations of pretrained BERT . empirical properties such as frequency, productivity, and ambiguity affect performance .
A Joint Approach to Compound Splitting and Idiomatic Compound Detection (2020.lrec-1)

Copied to clipboard

Challenge: Compounding is a common word-formation process in Germanic languages . high productivity and low corpus frequency of compounds increase vocabulary size .
Approach: They develop a deep learning-based approach to noun compound splitting and idiomatic compound detection for the German language.
Outcome: The proposed approach outperforms the current state of the art in noun compound splitting and idiomatic compound detection for the German language.
What Can Diachronic Contexts and Topics Tell Us about the Present-Day Compositionality of English Noun Compounds? (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to determine the semantic relatedness between compounds and constituents have applied a synchronic perspective, but this study examines what diachronic changes in contexts and semantic topics reveal about the compounds’ present-day compositionality.
Approach: They propose to use two diachronic vector spaces to model compositional patterns between compounds with low and high present-day compositionality.
Outcome: The proposed model performs on par with co-occurrence space and captures similar information.
Representing Compounding with OntoLex. An Evaluation of Vocabularies for Word Formation Resources (2024.lrec-main)

Copied to clipboard

Challenge: OntoLex is a de facto standard for the modelling of lexical resources in the framework of Linguistic Linked Open Data.
Approach: They propose to use OntoLex to convert Linked Open Data into compounds by using the RDF model.
Outcome: The proposed model can be applied to all resources harmonized in that format, potentially allowing for the conversion into Linked Open Data of a large amount of structured data.
Can Large Language Models Interpret Noun-Noun Compounds? A Linguistically-Motivated Study on Lexicalized and Novel Compounds (2024.acl-long)

Copied to clipboard

Challenge: Noun-noun compounds represent an important challenge for Natural Language Understanding . correct interpretation of noun-nomin compounds is essential for many applications .
Approach: They test whether Large Language Models can interpret the semantic relation between nouns . they also test whether they can abstract from such knowledge to predict the relation .
Outcome: The proposed models can interpret the semantic relation between nouns and compounds using analogical comparisons.
Improving Tokenisation by Alternative Treatment of Spaces (2022.emnlp-main)

Copied to clipboard

Challenge: Subword tokenisation is a key initial step in processing natural language . it uses a number of different methods to tokenise text, including a stringsearching technique and a word-matching technique.
Approach: They propose to use a vocabulary-based approach to tokenise text using a numerical ID and a mathematical function to manipulate it.
Outcome: The method is based on a set of training data and learning from it to build a vocabulary and tokenise it at inference time using this vocabulary and learnt parameters.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations