Papers with dictionaries
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
Elena Sofia Ruzzetti, Leonardo Ranaldi, Michele Mastromattei, Francesca Fallucchi, Noemi Scarpato, Fabio Massimo Zanzotto
| 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
Liviu Dinu, Ana Uban, Alina Cristea, Anca Dinu, Ioan-Bogdan Iordache, Simona Georgescu, Laurentiu Zoicas
| 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. |