Papers with dictionaries

31 papers
Detecting Subtle Sense Shift with Polysemy-Aware Trends (2026.eacl-short)

Copied to clipboard

Challenge: Existing research on lexical semantic change focuses on century-scale, well-curated corpora and binary "changed / unchanged" judgements.
Approach: They propose a language-independent pipeline that detects word-sense shifts in large, time-stamped web corpora.
Outcome: The proposed pipeline detects word-sense shifts in large, time-stamped web corpora.
Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions (2024.eacl-long)

Copied to clipboard

Challenge: a fundamental characteristic of natural language definitions is that they are widely abundant, pos-1.
Approach: They propose a multi-relational model that explicitly leverages definitions' semantic structure to derive word embeddings.
Outcome: The proposed model can preserve the semantic mapping required for interpretable traversal while imposing constraints on definitions while maintaining the recursive semantic structure.
ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus (2021.acl-demo)

Copied to clipboard

Challenge: 7000 languages worldwide are spoken, but most research is focused on English . multilinguality is essential for multilingual research, and is a key component of the process.
Approach: They propose a wordaligned parallel corpus that can be browsed using an online tool . they use the word alignment tools SimAlign and BabelNet to find the alignments .
Outcome: The proposed tool can be set up for any parallel corpus and explores its quality and properties.
Sentiment as an Ordinal Latent Variable (2023.eacl-main)

Copied to clipboard

Challenge: Existing dictionaries are limited in coverage and sentiment scales vary widely; some are discrete others continuous.
Approach: They propose a Bayesian generative model that learns a composite sentiment dictionary as an interpolation between six existing dictionaries with different scales.
Outcome: The proposed model learns a composite sentiment dictionary as an interpolation between six existing dictionaries with different scales.
Dictionary-based Debiasing of Pre-trained Word Embeddings (2021.eacl-main)

Copied to clipboard

Challenge: Existing methods for learning word embeddings using dictionaries do not require access to training resources or knowledge regarding the word embeds used.
Approach: They propose a method for debiasing pre-trained word embeddings using dictionaries . they learn constraints that must be satisfied by unbiased word embeds from dictionary definitions .
Outcome: The proposed method removes unfair biases encoded in pre-trained word embeddings while preserving useful semantics.
MIC: A Multi-task Interactive Curation Tool (2022.emnlp-demos)

Copied to clipboard

Challenge: MIC is a human-machine collaborative curation tool for multiple NLP tasks.
Approach: They propose to use a multi-task interactive curation tool for multiple NLP tasks to help solve pain points in real NLP.
Outcome: The proposed tool supports multiple projects with multiple users and allows for collaborative annotations.
Nakdan: Professional Hebrew Diacritizer (2020.acl-demos)

Copied to clipboard

Challenge: a system for automatic diacritization of Hebrew Text is available for both casual and expert users.
Approach: They propose a system for automatic diacritization of Hebrew Text . the system combines declarative linguistic knowledge with machine learning models .
Outcome: The proposed system is available for both casual and expert users.
Reinforcement-based denoising of distantly supervised NER with partial annotation (D19-61)

Copied to clipboard

Challenge: Existing named entity recognition systems rely on large amounts of human-labeled data for supervision, but the result is noisy.
Approach: They propose to use partial annotation to address false negative cases and implement a reinforcement learning strategy to identify false positive instances.
Outcome: The proposed model reduces the amount of manually annotated data required to perform NER in a new domain.
BiSync: A Bilingual Editor for Synchronized Monolingual Texts (2023.acl-demo)

Copied to clipboard

Challenge: CAT systems often interfere with writing process by requiring users to access external resources.
Approach: They propose a bilingual writing assistant that allows users to freely compose text in two languages while maintaining the two monolingual texts synchronized.
Outcome: The proposed bilingual writing assistant can produce high accuracy with limited computational resources.
DefSent: Sentence Embeddings using Definition Sentences (2021.acl-short)

Copied to clipboard

Challenge: Sentence embedding methods using natural language inference datasets are limited for limited languages due to large datasets.
Approach: They propose a sentence embedding method that uses definition sentences from a word dictionary.
Outcome: The proposed method performs comparably on unsupervised semantics textual similarity tasks and slightly better on SentEval tasks than methods using large NLI datasets.
Design Challenges in Named Entity Transliteration (C18-1)

Copied to clipboard

Challenge: Named entity transliteration is an important component in many search and language understanding tasks.
Approach: They empirically evaluate a named entity transliteration task using traditional methods . they use a stack of convolutional layers to create a neural network with a new approach .
Outcome: The proposed system outperforms two neural approaches in the named entity transliteration task.
JSON Whisperer: Efficient JSON Editing with LLMs (2025.emnlp-industry)

Copied to clipboard

Challenge: Large language models can modify JSON documents through natural language commands . current approaches regenerate entire structures for each edit, consuming computational resources .
Approach: They propose a framework that enables large language models to generate diff patches instead of complete documents.
Outcome: The proposed framework reduces token usage by 31% while maintaining edit quality within 5% of full regeneration.
LGPSolver - Solving Logic Grid Puzzles Automatically (2020.findings-emnlp)

Copied to clipboard

Challenge: Logic grid puzzle solvers can solve word algebra and logic puzzles in any domain with 100% accuracy.
Approach: They propose a method that uses a DistilBERT-based classifier to classify a clue into one of the predefined predicate types for logic grid puzzles.
Outcome: The proposed solution outperforms state-of-the-art solutions by a large margin on a given dataset.
Multilingual Multi-class Sentiment Classification Using Convolutional Neural Networks (L18-1)

Copied to clipboard

Challenge: a new language-independent model for sentiment analysis is proposed for social media . a sentiment dictionary cannot list all the possible ways people can express their opinions .
Approach: They propose a language-independent model for multi-class sentiment analysis using a neural network architecture.
Outcome: The proposed model does not rely on language-specific features such as ontologies, dictionaries, or morphological or syntactic pre-processing.
Combining Concepts and Their Translations from Structured Dictionaries of Uralic Minority Languages (L18-1)

Copied to clipboard

Challenge: a new method to expand the knowledge in existing dictionaries is proposed . small Uralic languages are facing a problem of limited language resources .
Approach: They propose to combine conceptually divided translations from multilingual dictionaries for small Uralic languages into a single lexical entry.
Outcome: The proposed method can be used to expand existing dictionaries and provide translations when adding new entries.
Toward Fully Exploiting Heterogeneous Corpus:A Decoupled Named Entity Recognition Model with Two-stage Training (2021.findings-acl)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a fundamental and widely used task in natural language processing.
Approach: They propose a decoupled NER model with two-stage training to take advantage of heterogeneous corpus, including dictionaries, distantly supervised instances, and human-annotated instances.
Outcome: Empirical results show that the proposed model improves against baselines and can be scaled to a large extent.
Cross-Lingual Suicidal-Oriented Word Embedding toward Suicide Prevention (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing suicide dictionaries for other languages have been limited to Korean . a model that uses social media data to identify whether a post includes suicidal ideation is useful .
Approach: They propose a model that uses existing suicide dictionaries for Korean to predict suicidal ideation . they use the existing dictionary for English and Chinese to translate a post into English and then use the separate suicide-oriented embeddings for English.
Outcome: The proposed model can detect whether a given social media post includes suicidal ideation in Korean . it uses existing suicide dictionaries for other languages to translate the post into English and Chinese, and then embeds the suicide-oriented embeddings for English and China.
Lacking the Embedding of a Word? Look it up into a Traditional Dictionary (2022.findings-acl)

Copied to clipboard

Challenge: Word embeddings are powerful dictionaries, but they fail to give sense to rare words . a large body of research is devoted to devising ways to capture word meaning .
Approach: They propose to use definitions retrieved from traditional dictionaries to build word embeddings for rare words.
Outcome: The proposed methods outperform state-of-the-art methods for embeddings of unknown words . the proposed methods significantly outperformed the BERT method for OOV words compared to the proposed method .
Learning Named Entity Tagger using Domain-Specific Dictionary (D18-1)

Copied to clipboard

Challenge: Existing methods to build reliable named entity recognition systems require large amounts of manually-labeled training data.
Approach: They propose a revised fuzzy CRF layer to handle tokens with multiple possible labels to address noisy distant supervision.
Outcome: The proposed model can handle tokens with multiple possible labels under the traditional framework and improves on the existing model with a new Tie or Break scheme.
Unsupervised Paraphrasing of Multiword Expressions (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for paraphrasing multiword expressions in context are unsupervised . multiwords are notoriously difficult to model because the meaning of the whole can diverge substantially from that of the component words.
Approach: They propose an unsupervised approach to paraphrasing multiword expressions in context using monolingual corpus data and pre-trained language models.
Outcome: The proposed method outperforms all unsupervised systems and rivals supervised systems on the SemEval 2022 idiomatic text similarity task.
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation (P19-1)

Copied to clipboard

Challenge: Using a dictionary, given a rough, target language natives can uncover the latent, fully-fluent rendering of the translation.
Approach: They propose a method that breaks translation into two steps by generating a dictionary and then ‘translating’ the resulting pseudo-translation into a fully fluent translation.
Outcome: The proposed method 'gets better translation results on high-resource languages than previously published unsupervised MT studies'
Elections go bananas: A First Large-scale Multilingual Study of Pluralia Tantum using LLMs (2026.eacl-long)

Copied to clipboard

Challenge: a large amount of annotated sentences for each feature can be used for in-depth analysis.
Approach: They propose an annotation framework for lexicalization of pluralia tantum . they use an LLM to annotate each instance from the reference corpus .
Outcome: The proposed framework provides useful annotators for semantic, syntactic and sense categories with accuracy ranging from 51% to 89% on a hand-annotated testset.
Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings (2020.emnlp-main)

Copied to clipboard

Challenge: Multi-Word Expressions (MWEs) are common in every language, but they are not translated by cross-lingual word embeddings.
Approach: They propose a method for word translation of Multi-Word Expressions (MWEs) they compile lists of MWEs in each language and tokenize them as single tokens before training word embeddings.
Outcome: The proposed method can translate multi-word expressions to and from English in 10 languages.
Media of Langue: Exploring Word Translation Network (2025.findings-naacl)

Copied to clipboard

Challenge: a new interface for word translation is proposed to explore the semantic configurations of words in multiple languages at once.
Approach: They propose a web interface for word translation that points to the semantic configurations of many words in multiple languages at once.
Outcome: The proposed interface is available as a web application on seven language pairs . it points to the semantic configurations of many words in multiple languages at once .
Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations (2023.acl-long)

Copied to clipboard

Challenge: Named entity recognition models rely on domain-specific dictionaries provided by experts . however, such dictionary sets are infeasible in many domains where they do not exist .
Approach: They propose a framework that generates NER datasets with high-coverage pseudo-dictionaries . phrase retrieval models are used to retrieve popular entities rather than rare ones .
Outcome: The proposed framework outperforms the previous best model by an average F1 score of 4.7 across five NER benchmark datasets.
Better Together: Modern Methods Plus Traditional Thinking in NP Alignment (2020.lrec-1)

Copied to clipboard

Challenge: a recent study shows that end-to-end systems are not structurally free.
Approach: They propose to use dictionary- and word vector-based baselines to align NPs in the bitext . they argue that alignment of NP's in MT can be improved by using old-fashioned methods .
Outcome: a new study shows that alignment of NPs in the bitext is relevant even in an end-to-end paradigm . the proposed system can be improved by bringing in old-fashioned methods, the authors argue .
RoBoCoP: A Comprehensive ROmance BOrrowing COgnate Package and Benchmark for Multilingual Cognate Identification (2023.emnlp-main)

Copied to clipboard

Challenge: Existing databases for romance cognates are scattered, incomplete, noisy, or have uncertain availability.
Approach: They propose to use etymological information to identify Romance cognates and borrowings from dictionaries to identify their ethymology.
Outcome: The proposed method achieves 94% accuracy on two pairs of Romance languages.
EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for CS use dictionaries or parallel sentences with word-alignment to generate CS data by randomly switching words in a sentence.
Approach: They propose a method that focuses on Entity-level Code-Switching to capture fine-grained cross-lingual semantics without corrupting syntax.
Outcome: The proposed method captures fine-grained cross-lingual semantics without corrupting syntax.
DictDis: Dictionary Constrained Disambiguation for Improved NMT (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to domain-specific neural machine translation (NMT) are lexically constrained and draw from domain- specific dictionaries.
Approach: They propose a lexically constrained neural machine translation system that disambiguates between multiple dictionary candidates.
Outcome: The proposed system disambiguates between multiple candidate translations derived from dictionaries on English-Hindi, English-German, and English-French datasets.
PopAut: An Annotated Corpus for Populism Detection in Austrian News Comments (2024.lrec-main)

Copied to clipboard

Challenge: Populism is a phenomenon that is noticeably present in political landscapes worldwide . prior work on populism analysis focused on analyzing populist content expressed by politicians .
Approach: They present a corpus of news comments annotated for populism in the german language . they use machine learning to detect populist comments in text .
Outcome: The proposed corpus outperforms existing dictionaries for populism detection in text . it features 1,200 comments collected between 2019-2021 .
WordNet under Scrutiny: Dictionary Examples in the Era of Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Lexical resources are a repository of knowledge and are used for many tasks, including word sense disambiguation and etymology.
Approach: They compare WordNet, the most commonly used lexical resource in NLP, with a variety of dictionaries and examples that were generated by ChatGPT.
Outcome: The most commonly used lexical resource in NLP, with a variety of dictionaries and examples that were generated by ChatGPT.

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