WORDNET

Knowledge Enhanced Contextual Word Representations (D19-1)

Challenge:	Existing studies have used pre-trained language models for domain adaptation or transfer learning to improve natural language processing performance.
Approach:	They propose to fine-tune word sense disambiguation on sequence-pair ranking task and to use existing WordNet examples to augment the model.
Outcome:	The proposed model achieves state-of-the-art on the English all-words benchmark datasets.

Copied to clipboard

Matthew E. Peters, Mark Neumann, Robert Logan, Roy Schwartz, Vidur Joshi, Sameer Singh, Noah A. Smith

TaxFree: a Visualization Tool for Candidate-free Taxonomy Enrichment (2022.aacl-demo)

Challenge:	Existing methods to embed knowledge bases into large pre-training models do not contain any explicit grounding to real world entities and are difficult to recover factual knowledge.
Approach:	They propose a method to embed multiple knowledge bases (KBs) into large pretrained models with a Knowledge Attention and Recontextualization mechanism.
Outcome:	The proposed model improves perplexity, ability to recall facts and word sense disambiguation.

Copied to clipboard

Irina Nikishina, Ivan Andrianov, Alsu Vakhitova, Alexander Panchenko

Challenge:	In this paper, we present an open source system for taxonomy visualisation and automatic taxonomies enrichment without pre-defined candidates.
Approach:	They propose an open source system for taxonomy visualisation and automatic taxonomie enrichment without pre-defined candidates on the example of WordNet-3.0.
Outcome:	The proposed system can be used for visualisation and inspection of taxonomies without pre-defined candidates on WordNet-3.0.

Metaphorical Polysemy Detection: Conventional Metaphor Meets Word Sense Disambiguation (2022.coling-1)

Copied to clipboard

Rowan Hall Maudslay, Simone Teufel

Improving Knowledge Graph Embedding Using Simple Constraints (P18-1)

Challenge:	Linguists distinguish between novel and conventional metaphors, a distinction which the metaphor detection task in NLP does not take into account.
Approach:	They propose a method which treats conventional metaphors as a property of word senses in a lexicon and combines metaphor detection with word sense disambiguation to train it.
Outcome:	The proposed model outperforms a state-of-the-art model in annotating metaphor in two subsets of WordNet and achieves .78 ROC-AUC score compared to baseline model .

Copied to clipboard

Boyang Ding, Quan Wang, Bin Wang, Li Guo

Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks (D19-60)

Challenge:	Recent efforts focused on designing more complicated models or incorporating extra information beyond triples.
Approach:	They propose to use non-negativity constraints on entity representations and approximate entailment constraints on relation representations to improve KG embedding.
Outcome:	The proposed model outperforms baseline models on WordNet, Freebase, and DBpedia.

Copied to clipboard

Xiepeng Li, Zhexi Zhang, Wei Zhu, Zheng Li, Yuan Ni, Peng Gao, Junchi Yan, Guotong Xie

Analysing the Correlation between Lexical Ambiguity and Translation Quality in a Multimodal Setting using WordNet (2022.naacl-srw)

Challenge:	Existing approaches to represent knowledge in the low-dimensional space are to leverage large-scale unsupervised text corpus to train fixed or contextual representations.
Approach:	They propose to leverage large-scale unsupervised text corpus to train fixed or contextual language representations and to express knowledge into a knowledge graph (KG) they incorporate distributional representations of a KG onto the representations from pre-trained language models, via simply concatenation or multi-head attention.
Outcome:	The proposed models outperform the other models on the COIN: COmmonsense INference in Natural Language Processing (COIN) Workshop datasets.

Copied to clipboard

Ali Hatami, Paul Buitelaar, Mihael Arcan

Multimodality

Challenge:	Recent studies in machine translation have been focusing on using visual information to improve the translation quality of sentences.
Approach:	They propose to use visual information to improve the output quality of a text-based translation model by extracting ambiguity scores from WordNet.
Outcome:	The proposed model improves translation quality for all sentences in the English-German dataset.

Exploiting WordNet Synset and Hypernym Representations for Answer Selection (2020.aacl-main)

Copied to clipboard

Weikang Li, Yunfang Wu

SemAttack: Natural Textual Attacks via Different Semantic Spaces (2022.findings-naacl)

Challenge:	Answer selection (AS) is a challenging subtask of document-based question answering (DQA).
Approach:	They propose to use WordNet to enrich the word representation and sentence encoding to incorporate similarity scores of two concepts that share synset or hypernym relations into the attention mechanism.
Outcome:	The proposed model outperforms existing state-of-the-art models on the public WikiQA and SelQA datasets and significantly improves the baseline system.

Copied to clipboard

Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li

Providing Semantic Knowledge to a Set of Pictograms for People with Disabilities: a Set of Links between WordNet and Arasaac: Arasaac-WN (2020.lrec-1)

Challenge:	Existing approaches to attack pre-trained language models suffer from low success rates or fail to search efficiently in the exponentially large perturbation space.
Approach:	They propose an efficient framework to generate natural adversarial text by constructing different semantic perturbation functions.
Outcome:	The proposed framework generates natural adversarial texts for different languages with high success rates.

Copied to clipboard

Didier Schwab, Pauline Trial, Céline Vaschalde, Loïc Vial, Emmanuelle Esperanca-Rodier, Benjamin Lecouteux

Multimodality

Challenge:	Pictograms are a tool that is increasingly used by people with cognitive or communication disabilities.
Approach:	They propose a database that links WordNet and Arasaac to link pictograms to semantic knowledge.
Outcome:	The proposed database links pictograms with WordNet and Arasaac to create language-independent prototypes.

Latent semantic network induction in the context of linked example senses (D19-55)

Copied to clipboard

Hunter Heidenreich, Jake Williams

Challenge:	Using the Princeton WordNet, we construct a network using the entirety of Wiktionary.
Approach:	They propose to use Wiktionary to construct a wordnet using the entirety of the open-source dictionary.
Outcome:	The proposed network induction process is similar to the Princeton WordNet, but with a more data-driven approach.

Embedding WordNet Knowledge for Textual Entailment (C18-1)

Copied to clipboard

Yunshi Lan, Jing Jiang

Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization (D18-1)

Challenge:	Existing deep learning models for textual entailment do not require any feature engineering or linguistic analysis.
Approach:	They propose to embed WordNet-derived lexical entailment relations into specially-learned word vectors and incorporate them into a decomposable attention model for textual enlightment.
Outcome:	The proposed model significantly improves on the SICK and SNLI datasets.

Copied to clipboard

Edoardo Maria Ponti, Ivan Vulić, Goran Glavaš, Nikola Mrkšić, Anna Korhonen

TEAM: A multitask learning based Taxonomy Expansion approach for Attach and Merge (2022.findings-naacl)

Challenge:	Semantic specialization is a process of fine-tuning pre-trained distributional word vectors using external lexical knowledge to accentuate a particular semantic relation in the specialized vector space.
Approach:	They propose a method for specializing distributional word vectors using external lexical knowledge.
Outcome:	The proposed method improves on word similarity, dialog state tracking, and lexical simplification across three languages and on three tasks.

Copied to clipboard

Bornali Phukon, Anasua Mitra, Ranbir Sanasam, Priyankoo Sarmah

Overcoming the Rare Word Problem for low-resource language pairs in Neural Machine Translation (D19-52)

Challenge:	Existing methods for automating taxonomy expansion are attach and merge . elucidating the problem of limited coverage of WordNets is presented .
Approach:	They propose a multitask learning-based deep learning method that performs both merge and attach operations in a single model.
Outcome:	The proposed method outperforms state-of-the-art models on three WordNet taxonomies . it performs both merge and attach operations and also provides encouraging performance for merge operation .

Copied to clipboard

Thi-Vinh Ngo, Thanh-Le Ha, Phuong-Thai Nguyen, Le-Minh Nguyen

Machine Translation

Challenge:	Despite above approaches can improve the prediction of rare words, they still have challenges which have adverse effects on its effectiveness.
Approach:	They propose three ways to address rare-word problem in neural machine translation systems . they propose an algorithm to learn morphology of unknown words for English in supervised way to minimize adverse effect of rare- word problem.
Outcome:	The proposed approaches improve accuracy on two low-resource language pairs.

Exploiting Emojis for Abusive Language Detection (2021.eacl-main)

Copied to clipboard

Michael Wiegand, Josef Ruppenhofer

Visual Data in NLP

Challenge:	emojis can be used as a proxy for learning a lexicon of abusive words . eliot safina and samuel khan are the authors of this paper .
Approach:	They propose to use abusive emojis as a proxy for learning a lexicon of abusive words.
Outcome:	The proposed approach generates a lexicon that performs as well as the most advanced lexical induction method.

Knowledge-Enriched Two-Layered Attention Network for Sentiment Analysis (N18-2)

Copied to clipboard

Abhishek Kumar, Daisuke Kawahara, Sadao Kurohashi

Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection (N18-1)

Challenge:	Existing sentiment analysis systems are prone to word shortening, exaggeration, lack of grammar and appropriate punctuation.
Approach:	They propose a two-layered attention network based on Bidirectional Long Short-Term Memory for sentiment analysis using the Knowledge Graph Embedding generated using the WordNet.
Outcome:	The proposed model outperforms the state-of-the-art system on the benchmark dataset of SemEval 2017 Task 5 by 1.7 and 3.7 points respectively.

Copied to clipboard

Haw-Shiuan Chang, Ziyun Wang, Luke Vilnis, Andrew McCallum

Low-Resource NLP

Challenge:	Existing unsupervised methods for learning hypernyms from unlabeled text are not scaled to large vocabularies or yield unacceptably poor accuracy.
Approach:	They propose an unsupervised method of hypernym discovery using word contexts . they use word2vec to embed word context distributions without supervision .
Outcome:	The proposed method provides double the precision and highest average performance on 11 datasets.

Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources (N18-1)

Copied to clipboard

Ivan Vulić, Goran Glavaš, Nikola Mrkšić, Anna Korhonen

VerbAtlas: a Novel Large-Scale Verbal Semantic Resource and Its Application to Semantic Role Labeling (D19-1)

Challenge:	Word vector specialisation is a portable, light-weight approach to fine-tuning distributional word vector spaces by injecting external knowledge from rich lexical resources such as WordNet.
Approach:	They propose a constraint-driven vector space specialisation method that embeds external knowledge into lexical resources into a deep neural network to specialise unseen words.
Outcome:	The proposed method preserves useful linguistic knowledge for seen words while propagating external signal to unseen words to improve their vector representations.

Copied to clipboard

Andrea Di Fabio, Simone Conia, Roberto Navigli

Explicit Semantic Decomposition for Definition Generation (2020.acl-main)

Challenge:	VerbAtlas is a lexical-semantic resource that combines WordNet synsets into semantically-coherent frames.
Approach:	They propose a lexical-semantic resource that brings together WordNet synsets into semantically-coherent frames.
Outcome:	The proposed resource brings together all WordNet synsets into semantically-coherent frames.

Copied to clipboard

Jiahuan Li, Yu Bao, Shujian Huang, Xinyu Dai, Jiajun Chen

Challenge:	Existing definition generation methods rely on decoding to extract semantic components of words.
Approach:	They propose a method which explicitly decomposes meaning of words into semantic components and models them with discrete latent variables for definition generation.
Outcome:	The proposed method outperforms existing methods on WordNet and Oxford benchmarks.

Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models (2024.lrec-main)

Copied to clipboard

Lorenzo Proietti, Stefano Perrella, Simone Tedeschi, Giulia Vulpis, Leonardo Lavalle, Andrea Sanchietti, Andrea Ferrari, Roberto Navigli

Data Augmentation for Hypernymy Detection (2021.eacl-main)

Challenge:	Word Sense Disambiguation (WSD) is a key task in Natural Language Processing (NLP) but current pretrained language models lack the granularity to perform disambiguation .
Approach:	They propose a large-scale resource that leverages homonymy relations to cluster WordNet senses and train Homonymy Disambiguation systems.
Outcome:	The proposed model can distinguish homonyms with up to 95% accuracy even without fine-tuning the underlying PLM.

Copied to clipboard

Thomas Kober, Julie Weeds, Lorenzo Bertolini, David Weir

Enriching Frame Representations with Distributionally Induced Senses (L18-1)

Challenge:	Existing methods for supervised inference have limited quality training data.
Approach:	They propose two techniques which generate new training examples from existing ones . they combine linguistic principles of hypernym transitivity and intersective modifier-noun composition .
Outcome:	The proposed techniques generate new training examples from existing datasets.

Copied to clipboard

Stefano Faralli, Alexander Panchenko, Chris Biemann, Simone Paolo Ponzetto

Grounded Compositional Outputs for Adaptive Language Modeling (2020.emnlp-main)

Challenge:	lexical resource that enriches Framester knowledge graph with semantic features from text corpora . paves way for development of novel, deeper semantic-aware applications .
Approach:	They propose a lexical resource that enriches the Framester knowledge graph with semantic features from text corpora.
Outcome:	The proposed resource enables the development of deeper semantic-aware applications . it combines knowledge from text and symbolic representations of events and participants .

Copied to clipboard

Nikolaos Pappas, Phoebe Mulcaire, Noah A. Smith

Better Language Model with Hypernym Class Prediction (2022.acl-long)

Challenge:	Language models are a key component of natural language processing, but their size is a problem because they are typically trained with a closed output vocabulary derived from the training data.
Approach:	They propose a fully compositional output embedding layer for language models that is grounded in semantically related words and free-text definitions.
Outcome:	The proposed model outperforms state-of-the-art methods and adaptation approaches on cross-domain modeling and cross-learning tasks.

Copied to clipboard

He Bai, Tong Wang, Alessandro Sordoni, Peng Shi

Language Models

Challenge:	Class-based language models (LMs) have been devised to address context sparsity in n-gram LMs for decades.
Approach:	They propose to use class-based prediction to improve generalization for rare words by annealing from predicting the class to token prediction during training.
Outcome:	The proposed model improves perplexity without sacrificing performance on rare words.

HyperText: Endowing FastText with Hyperbolic Geometry (2020.findings-emnlp)

Copied to clipboard

Yudong Zhu, Di Zhou, Jinghui Xiao, Xin Jiang, Xiao Chen, Qun Liu

Information Extraction & Text Mining

Challenge:	Empirically, we show that HyperText outperforms FastText on a range of text classification tasks with much reduced parameters.
Approach:	They propose a model that uses hyperbolic geometry to model tree-like hierarchies in natural language sentences by embedding words or ngrams in hyperbolical space.
Outcome:	Empirically, the proposed model outperforms FastText on a range of text classification tasks with much reduced parameters.

A Retrofitting Model for Incorporating Semantic Relations into Word Embeddings (2020.coling-main)

Copied to clipboard

Sapan Shah, Sreedhar Reddy, Pushpak Bhattacharyya

How Much Do Encoder Models Know About Word Senses? (2025.acl-long)

Challenge:	Existing word embedding models mix semantic similarity with other types of relatedness.
Approach:	They propose a model that leverages relational knowledge available in a knowledge resource to improve word embeddings.
Outcome:	The proposed model improves word embeddings on synonymy, antonymy and hypernymy relations in WordNet and significantly improves lexical entailment detection task.

Copied to clipboard

Simone Teglia, Simone Tedeschi, Roberto Navigli

TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks (2024.acl-long)

Challenge:	Word Sense Disambiguation (WSD) is a key task in Natural Language Processing (NLP) however, how well these models inherently disambiguate word senses remains uncertain.
Approach:	They evaluate several encoder-only PLMs across WordNet and ODE sense inventories to evaluate their ability to separate word senses without any task-specific fine-tuning.
Outcome:	The proposed model outperforms output layer on WordNet and ODE sense inventories by 15 percentage points.

Copied to clipboard

Viktor Moskvoretskii, Ekaterina Neminova, Alina Lobanova, Alexander Panchenko, Irina Nikishina

Exploring Data Augmentation in Neural DRS-to-Text Generation (2024.eacl-long)

Challenge:	Recent studies in Natural Language Processing widely utilize Large Language Models (LLMs) for their capability to store extensive knowledge.
Approach:	They propose an LLM-based model that captures lexical-semantic knowledge from WordNet and test it on multiple lexicals.
Outcome:	The proposed model achieves 11 SOTA results and 4 top-2 results out of 16 taxonomy-related tasks.

Copied to clipboard

Muhammad Saad Amin, Luca Anselma, Alessandro Mazzei

Text Generation

Challenge:	Neural networks are notoriously data-hungry, resulting in ungrammatical texts . data augmentation requires a specific design for a structurally rich input format .
Approach:	They propose to selectively augment a training set with new data by adding and varying two specific lexical categories, i.e. proper and common nouns.
Outcome:	The proposed approach selectively augments a training set with new data by adding and varying two specific lexical categories, i.e. proper and common nouns.

Constructing High Quality Sense-specific Corpus and Word Embedding via Unsupervised Elimination of Pseudo Multi-sense (L18-1)

Copied to clipboard

Haoyue Shi, Xihao Wang, Yuqi Sun, Junfeng Hu

Multilingual Image Corpus – Towards a Multimodal and Multilingual Dataset (2022.lrec-1)

Challenge:	Existing word embedding frameworks distinguish different senses of words by their contexts.
Approach:	They propose a framework for unsupervised corpus sense tagging which trains multi-sense word embeddings on a given corpus.
Outcome:	The proposed framework detects pseudo multi-senses without extra language resources without additional language resources.

Copied to clipboard

Svetla Koeva, Ivelina Stoyanova, Jordan Kralev

Visual Data in NLP

Challenge:	The goal of the project Multilingual Image Corpus is to provide a large image dataset with annotated objects and object descriptions in 24 languages.
Approach:	They propose to provide a large image dataset with annotated objects and object descriptions in 24 languages.
Outcome:	The project provides a large image dataset with annotated objects and object descriptions in 24 languages.

Enhancing Modern Supervised Word Sense Disambiguation Models by Semantic Lexical Resources (L18-1)

Copied to clipboard

Stefano Melacci, Achille Globo, Leonardo Rigutini

UFSAC: Unification of Sense Annotated Corpora and Tools (L18-1)

Challenge:	Existing supervised models for Word Sense Disambiguation (WSD) are limited to knowledge-based approaches.
Approach:	They propose to use WordNet and WordNet Domains to enhance supervised WSD models by introducing semantic features into the classifiers and using the SLR structure to augment training data.
Outcome:	The proposed model improves the state-of-the-art in Word Sense Disambiguation (WSD) The proposed approach is compared with the state of the art in the most popular benchmarks.

Copied to clipboard

Loïc Vial, Benjamin Lecouteux, Didier Schwab

Spot the Odd Man Out: Exploring the Associative Power of Lexical Resources (D18-1)

Challenge:	a dozen sense annotated English corpora are used in Word Sense Disambiguation (WSD) a new format of corpus is proposed that can be used for training or testing a disambiguation system .
Approach:	They propose a format of corpus that can be used for training or testing a disambiguation system . they provide the source code and a complete Java API for manipulating corpora in this format .
Outcome:	The proposed format of corpus can be used for training or testing a disambiguation system . the source code and a complete Java API are provided for building the corpus .

Copied to clipboard

Gabriel Stanovsky, Mark Hopkins

Language-based General Action Template for Reinforcement Learning Agents (2021.findings-acl)

Challenge:	Existing word embeddings assign only one vector to each word, resulting in word disambiguation on smaller scales.
Approach:	They propose a task which aims to test different properties of word representations.
Outcome:	The proposed task is intuitive enough to annotate on a large scale while teasing out properties of popular lexical resources.

Copied to clipboard

Ryosuke Kohita, Akifumi Wachi, Daiki Kimura, Subhajit Chaudhury, Michiaki Tatsubori, Asim Munawar

Challenge:	Prior knowledge is important in decision-making, and humans preserve it in the form of natural language (NL).
Approach:	They propose an environmentagnostic action framework that incorporates prior knowledge into decision-making . they propose to use general semantic schemes to facilitate agent in finding plausible actions .
Outcome:	The proposed agent performs better than agents that rely on gamespecific actions.

Predicting Semantic Relations using Global Graph Properties (D18-1)

Copied to clipboard

Yuval Pinter, Jacob Eisenstein

External Knowledge-Driven Argument Mining: Leveraging Attention-Enhanced Multi-Network Models (2024.emnlp-main)

Challenge:	Semantic graphs encode the structural qualities of language as a representation of human knowledge.
Approach:	They propose a global-theoretic model that integrates global and local properties of semantic graphs to improve local prediction of relational relations between synsets.
Outcome:	The proposed model improves on the local task of predicting semantic relations between synsets, yielding state-of-the-art results on the WN18RR dataset.

Copied to clipboard

Debela Gemechu, Chris Reed

Knowledge Representation

Challenge:	Argument mining involves the identification of argument relations (AR) between Argumentative Discourse Units (ADUs).
Approach:	They propose to leverage external resources to identify semantic paths linking ADUs . they propose to use WordNet, ConceptNet, and Wikipedia to identify these paths .
Outcome:	The proposed architecture achieves F-scores of 0.85, 0.84, 0.70, and 0.87 on four datasets.

Explicit Utilization of General Knowledge in Machine Reading Comprehension (P19-1)

Copied to clipboard

Chao Wang, Hui Jiang

Reasoning

Challenge:	Existing MRC models are unable to integrate general knowledge with human knowledge.
Approach:	They propose a data enrichment method which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair.
Outcome:	The proposed model outperforms state-of-the-art models and is robust to noise.

Introducing a Lexicon of Verbal Polarity Shifters for English (L18-1)

Copied to clipboard

Marc Schulder, Michael Wiegand, Josef Ruppenhofer, Stephanie Köser

A Crowdsourced Frame Disambiguation Corpus with Ambiguity (N19-1)

Challenge:	Negation words can change the sentiment polarity of a phrase, but there are more than 1200 other polarities.
Approach:	They propose a lexicon of verbal polarity shifters that covers the entirety of verbs found in WordNet.
Outcome:	The proposed lexicon covers the entirety of verbs found in WordNet.

Copied to clipboard

Anca Dumitrache, Lora Aroyo, Chris Welty

Challenge:	Using crowdsourcing, we have found that inter-annotator disagreement is at least partly caused by ambiguity inherent to the text and frames.
Approach:	They propose a crowdsourcing approach to capture inter-annotator disagreement by a list of frames with disagreement-based scores that express the confidence with which each frame applies to the word.
Outcome:	The proposed approach captures disagreement between the annotations of 1,000 word-sentence pairs and scores on the likelihood that each frame applies to the word.

Cross-lingual Semantic Specialization via Lexical Relation Induction (D19-1)

Copied to clipboard

Edoardo Maria Ponti, Ivan Vulić, Goran Glavaš, Roi Reichart, Anna Korhonen

Automatic Wordnet Mapping: from CoreNet to Princeton WordNet (L18-1)

Challenge:	Semantic specialization is not available in many languages because of their incomplete or non-existent structure.
Approach:	They propose a method that transfers specialization from a resource-rich source language to virtually any target language.
Outcome:	The proposed method performs lexical simplification, dialog state tracking, and textual similarity tasks in 5 languages.

Copied to clipboard

Jiseong Kim, Younggyun Hahm, Sunggoo Kwon, Key-Sun Choi

Challenge:	Existing mappings focus on identifying the semantic categories of CoreNet, but not the word senses.
Approach:	They propose to map the word senses of CoreNet into Princeton WordNet synsets by lexical relations by a taxonomy.
Outcome:	The proposed mapping bridging the gap between CoreNet and WordNet shows that the word senses of CoreNet are mapped with precision of 91.2%.

Incorporating Glosses into Neural Word Sense Disambiguation (P18-1)

Copied to clipboard

Fuli Luo, Tianyu Liu, Qiaolin Xia, Baobao Chang, Zhifang Sui

Masked Language Models Know Which are Popular: A Simple Ranking Strategy for Commonsense Question Answering (2022.findings-emnlp)

Challenge:	Existing neural networks for Word Sense Disambiguation rely on labeled data and lexical knowledge.
Approach:	They propose a gloss-augmented WSD neural network which integrates context and glosses of the target word into a unified framework.
Outcome:	The proposed model outperforms the state-of-the-art systems on several English all-words WSD datasets.

Copied to clipboard

Xuan Luo, Chuang Fan, Yice Zhang, Wanguo Jiang, Bing Qin, Ruifeng Xu

Using Synchronic Definitions and Semantic Relations to Classify Semantic Change Types (2024.acl-long)

Challenge:	Empirical results show that pre-trained language models can improve the typical answer generation of GLMs.
Approach:	They propose a ranking strategy that exploits WordNet to train a ranker that picks out the most popular answers for commonsense questions.
Outcome:	The proposed ranking strategy is tested on a commonsense question answering (QA) dataset and on negative samples from WordNet.

Copied to clipboard

Pierluigi Cassotti, Stefano De Pascale, Nina Tahmasebi

Information Retrieval

Challenge:	Existing models for detecting semantic change in corpora have been disregarded due to lack of knowledge of the nature of semantic change and the way it takes place.
Approach:	They propose a model that leverages synchronic lexical relations and definitions of word meanings to detect these types of change.
Outcome:	The proposed model can detect changes in a digitized version of Blank's dataset and improve human judgments of semantic relatedness and binary Lexical Semantic Change Detection.

Inspecting the concept knowledge graph encoded by modern language models (2021.findings-acl)

Copied to clipboard

Carlos Aspillaga, Marcelo Mendoza, Alvaro Soto

ChainNet: Structured Metaphor and Metonymy in WordNet (2024.lrec-main)

Challenge:	Pre-trained language models are used to solve tasks such as summarization and information retrieval.
Approach:	They propose to use word embeddings, text generators, context encoders to extract underlying knowledge graphs of nine influential language models.
Outcome:	The proposed model is able to encode word embeddings, text generators, and context encoders, but suffers from several inaccuracies.

Copied to clipboard

Rowan Hall Maudslay, Simone Teufel, Francis Bond, James Pustejovsky

Challenge:	In a typical lexicon, word senses are encoded as a list, without inter-sense relations.
Approach:	They propose a lexical resource which explicitly identifies the senses of a word's senses by expressing how they are derived from one another.
Outcome:	The proposed resource expresses how senses in the Open English Wordnet are derived from one another.

Leveraging WordNet Paths for Neural Hypernym Prediction (2020.coling-main)

Copied to clipboard

Yejin Cho, Juan Diego Rodriguez, Yifan Gao, Katrin Erk

Challenge:	Existing work on lexical relations based on distributed representations has differed widely.
Approach:	They propose a model that generates taxonomy paths for hypernym prediction using WordNet sequences.
Outcome:	The hypo2path model outperforms the best model by 4.11 points in hit-at-one (H@1) The proposed model outpersforms previous models by a factor of 0.9.

WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition (D18-1)

Copied to clipboard

Yufeng Diao, Hongfei Lin, Di Wu, Liang Yang, Kan Xu, Zhihao Yang, Jian Wang, Shaowu Zhang, Bo Xu, Dongyu Zhang

Multiple Knowledge GraphDB (MKGDB) (2020.lrec-1)

Challenge:	Homographic puns have a long history in human writing, widely used in written and spoken literature, which intended as jokes.
Approach:	They propose a WordNet-encoded model to settle polysemy of homographic puns and a word weighted model for recognizing them.
Outcome:	The proposed model can distinguish between homographic pun and non-homographic pun texts.

Copied to clipboard

Stefano Faralli, Paola Velardi, Farid Yusifli

Don’t Neglect the Obvious: On the Role of Unambiguous Words in Word Sense Disambiguation (2020.emnlp-main)

Challenge:	ConceptNet, DBpedia, WebIsAGraph, WordNet and Wikipedia category hierarchy are used to create a large-scale graph database.
Approach:	They propose to use multiple taxonomy backbones extracted from 5 existing knowledge graphs to create a large-scale graph database.
Outcome:	The proposed database is intended to favour and support the development of open-domain natural language processing applications relying on knowledge bases.

Copied to clipboard

Daniel Loureiro, Jose Camacho-Collados

Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings (2021.eacl-main)

Challenge:	Existing senseannotated corpora lack coverage of many instances in WordNet . however, unambiguous words make up a large portion of WordNet while being poorly covered in existing senseannnotated .
Approach:	They propose a method to provide annotations for most unambiguous words in a large corpus by using a dataset.
Outcome:	The proposed method improves on the original results on Word Sense Disambiguation (WSD) using pre-trained language models and propagation algorithms.

Copied to clipboard

Christos Xypolopoulos, Antoine Tixier, Michalis Vazirgiannis

Towards Latvian WordNet (2022.lrec-1)

Challenge:	a new method to quantify polysemy is based on basic geometry in the contextual embedding space . word sense annotation has always been one of the tasks with the lowest interannotator agreement .
Approach:	They propose a method to estimate polysemy based on simple geometry in contextual embedding space.
Outcome:	The proposed method is fully unsupervised and data-driven . it can be used to sample sentences with different senses at no extra cost .

Copied to clipboard

Peteris Paikens, Mikus Grasmanis, Agute Klints, Ilze Lokmane, Lauma Pretkalniņa, Laura Rituma, Madara Stāde, Laine Strankale

Challenge:	Currently the dataset consists of 6432 words linked in 5528 synsets . the goal is to provide a structured lexical-semantic resource for Latvian word sense disambiguation .
Approach:	They propose to use Princeton's word sense definition and sense linking principles to create a Latvian wordnet . they use corpus evidence and an online dictionary to build a lexical-semantic resource .
Outcome:	The proposed resource is based on the Princeton WordNet and is available in Latvian . the initial portion of the data is available for download .

Mining Knowledge for Natural Language Inference from Wikipedia Categories (2020.findings-emnlp)

Copied to clipboard

Mingda Chen, Zewei Chu, Karl Stratos, Kevin Gimpel

Speakers Fill Lexical Semantic Gaps with Context (2020.emnlp-main)

Challenge:	Accurate lexical entailment (LE) and natural language inference (NLI) tasks require expensive annotations.
Approach:	They propose to pretrain Wikipedia categories for lexical entailment and natural language inference by pretraining them on WikiNLI and transferring them to other knowledge bases.
Outcome:	The proposed model can improve strong baselines such as BERT and RoBERTa by pretraining on WikiNLI and transferring the models on downstream tasks.

Copied to clipboard

Tiago Pimentel, Rowan Hall Maudslay, Damian Blasi, Ryan Cotterell

BERT-based Lexical Substitution (P19-1)

Challenge:	Lexical ambiguity is widespread in language, allowing for the reuse of economical word forms and thus making language more efficient.
Approach:	They propose two ways to estimate lexical ambiguity as the entropy of meanings a word can take . they validate this hypothesis by using WordNet and BERT .
Outcome:	The proposed method shows that on six high-resource languages, there are significant correlations between the estimate and the number of synonyms a word has in WordNet.

Copied to clipboard

Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou

Improving HowNet-Based Chinese Word Sense Disambiguation with Translations (2022.findings-emnlp)

Challenge:	Existing approaches to lexical substitution tend to overlook good substitute candidates that are not the synonyms of the target words in the lexicals and fail to take into account the substitution’s influence on the global context of the sentence.
Approach:	They propose an end-to-end BERT-based lexical substitution approach which proposes and validates substitute candidates without using annotated data or manually curated resources.
Outcome:	The proposed approach performs well in proposing and ranking substitute candidates, achieving the state-of-the-art results in both LS07 and LS14 benchmarks.

Copied to clipboard

Xiang Zhang, Bradley Hauer, Grzegorz Kondrak

Learning to Describe Unknown Phrases with Local and Global Contexts (N19-1)

Challenge:	Prior work on unsupervised WSD has leveraged lexical knowledge bases, such as WordNet and BabelNet, but these have proven to be less effective for Chinese.
Approach:	They propose a system which combines contextual information from a pretrained neural language model with bilingual information obtained via machine translation and sense translation information from HowNet.
Outcome:	The proposed system achieves a state-of-the-art for unsupervised Chinese WSD.

Copied to clipboard

Shonosuke Ishiwatari, Hiroaki Hayashi, Naoki Yoshinaga, Graham Neubig, Shoetsu Sato, Masashi Toyoda, Masaru Kitsuregawa

Explainability & Interpretability in NLP

Challenge:	Existing methods for contextual guessing and definition generation do not take clues from local contexts.
Approach:	They propose a neural description model that takes clues from local and global contexts . they assume that the target phrase is newly emerged and there is no global context .
Outcome:	The proposed model takes clues from local and global contexts over existing methods . it is more effective than existing methods for non-standard English explanation .

GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge (D19-1)

Copied to clipboard

Luyao Huang, Chi Sun, Xipeng Qiu, Xuanjing Huang

Word Sense Disambiguation with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension (2022.coling-1)

Challenge:	Word Sense Disambiguation (WSD) aims to find the exact sense of an ambiguous word in a particular context.
Approach:	They propose to integrate gloss knowledge into supervised neural networks for Word Sense Disambiguation (WSD) this paper proposes to fine-tune a pre-trained BERT model and achieve new state-of-the-art results on WSD task.
Outcome:	The proposed model achieves state-of-the-art on the word Sense Disambiguation (WSD) task.

Copied to clipboard

Guobiao Zhang, Wenpeng Lu, Xueping Peng, Shoujin Wang, Baoshuo Kan, Rui Yu

Knowledge Graph Embedding with Hierarchical Relation Structure (D18-1)

Challenge:	Word sense disambiguation (WSD) is one of the most challenging tasks in natural language processing.
Approach:	They propose a method to extract the right sense from a sentence context . they propose to incorporate additional examples and definitions of related senses in WordNet .
Outcome:	The proposed method achieves better performance than baseline models on public benchmark datasets.

Copied to clipboard

Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He

A Parallel WordNet for English, Swedish and Bulgarian (2020.lrec-1)

Challenge:	Existing knowledge graph embedding models embed entities and relations into latent vectors without leveraging rich information from relation structure.
Approach:	They extend existing KGE models to learn knowledge representations by leveraging relation structure . authors say their approach is capable of extending other KGEs .
Outcome:	The proposed approach can extend existing KGE models, and validates against baselines.

Copied to clipboard

Krasimir Angelov

Text Generation

Challenge:	a new WordNet resource for Swedish and Bulgarian is created that is tightly aligned with the Princeton WordNet.
Approach:	They propose a WordNet resource for Swedish and Bulgarian that is tightly aligned with Princeton WordNet.
Outcome:	The proposed resource is tightly aligned with the Princeton WordNet for Swedish and Bulgarian . the new resource is open-source and in its development used only existing resources.

Constructing Taxonomies from Pretrained Language Models (2021.naacl-main)

Copied to clipboard

Catherine Chen, Kevin Lin, Dan Klein

Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes (2021.emnlp-main)

Challenge:	A variety of NLP tasks use taxonomic information, including question answering and information retrieval.
Approach:	They propose a method for constructing taxonomic trees using pretrained language models by incorporating web-retrieved glosses into the model.
Outcome:	The proposed model achieves 66.7 ancestor F1, a 20.0% relative increase over the previous best published model on English WordNet.

Copied to clipboard

Tomasz Limisiewicz, David Mareček

A Broad-Coverage Deep Semantic Lexicon for Verbs (2020.lrec-1)

Challenge:	Existing studies on whether multilingual embeddings can be aligned in a shared space across languages are lacking.
Approach:	They propose to learn a projection based on monolingual annotated datasets and evaluate syntactic and lexical information encoded in a shared cross-lingual embedding space.
Outcome:	The proposed model can be used to learn representations for languages with low resources.

Copied to clipboard

James Allen, Hannah An, Ritwik Bose, Will de Beaumont, Choh Man Teng

Challenge:	a lack of a broad-coverage deep semantic lexicon hinders deep language understanding . we have developed a resource for verbs with the coverage of WordNet and syntactic and semantic details .
Approach:	They propose a deep lexical resource for verbs with the coverage of WordNet and syntactic and semantic details that meet or exceed existing resources.
Outcome:	The proposed resource has the coverage of WordNet and syntactic and semantic details that exceed existing resources.

Towards the Construction of a WordNet for Old English (2022.lrec-1)

Copied to clipboard

Fahad Khan, Francisco J. Minaya Gómez, Rafael Cruz González, Harry Diakoff, Javier E. Diaz Vera, John P. McCrae, Ciara O’Loughlin, William Michael Short, Sander Stolk

Challenge:	In this paper we discuss our preliminary work towards the construction of a WordNet for Old English, taking our inspiration from other similar WN construction projects for ancient languages such as Ancient Greek, Latin and Sanskrit.
Approach:	They propose to use a legacy Old English dictionary to build a WordNet for Old English using a lexicographic resource and the naisc system to automatically compile a provisional version of the WordNet.
Outcome:	The proposed OldEWN will be based on lemmas and definitions extracted from a legacy Old English dictionary and will be automatically compile and enriched by experts using the naisc system.

Generating a Gold Standard for a Swedish Sentiment Lexicon (L18-1)

Copied to clipboard

Jacobo Rouces, Nina Tahmasebi, Lars Borin, Stian Rødven Eide

SimplifyUR: Unsupervised Lexical Text Simplification for Urdu (2020.lrec-1)

Challenge:	Existing sentiment lexicons are compiled by (machine) translation from English resources, obscuring language-specific characteristics of sentiment-loaded vocabulary.
Approach:	They propose a gold standard for sentiment annotation of Swedish terms using the SALDO lexicon and the Gigaword corpus.
Outcome:	The proposed model is based on the free SALDO lexicon and the Gigaword corpus and is compared with existing models using human annotations.

Copied to clipboard

Namoos Hayat Qasmi, Haris Bin Zia, Awais Athar, Agha Ali Raza

Text Generation

Challenge:	Existing methods for text simplification for Urdu rely on manual lexicons and simplified corpora, but are not applicable to the language.
Approach:	They propose an unsupervised method for automatic text simplification for Urdu using word embeddings and morphological features.
Outcome:	The proposed method achieves BLEU score of 80.15 and SARI score of 42.02 on simple text generated on simplified corpora and human evaluations for correctness, grammaticality, meaning-preservation and simplicity.

Building a Multilingual Taxonomy of Olfactory Terms with Timestamps (2022.lrec-1)

Copied to clipboard

Stefano Menini, Teresa Paccosi, Serra Sinem Tekiroğlu, Sara Tonelli

World Knowledge for Abstract Meaning Representation Parsing (L18-1)

Challenge:	olfactory references play a crucial role in our memory and experiences . but only few works in NLP have attempted to capture this sensory dimension from a computational perspective.
Approach:	They describe a process that has led to the semi-automatic development of a taxonomy for olfactory information in four languages (English, French, German and Italian)
Outcome:	The proposed taxonomy can be extended using existing language models and n-grams to include olfactory terms in four languages.

Copied to clipboard

Charles Welch, Jonathan K. Kummerfeld, Song Feng, Rada Mihalcea

Data Collection vs. Knowledge Graph Completion: What is Needed to Improve Coverage? (2021.emnlp-main)

Challenge:	Abstract Meaning Representation (AMR) parsers are based on annotated graphs, but there is still room for improvement .
Approach:	They examine the role played by world knowledge in parsing errors in a state-of-the-art parser . they examine the effects of different types of world knowledge on parsers .
Outcome:	The proposed model improves on multiple fine-grained metrics, including a 6% increase in named entity F-score, and provides insight into the potential of world knowledge for future work in Abstract Meaning Representation parsing.

Copied to clipboard

Kenneth Church, Yuchen Bian

Learning Prototypical Functions for Physical Artifacts (2021.acl-long)

Challenge:	Knowledge Graph Completion (KGC) attempts to learn missing links from subsets.
Approach:	This survey/position paper discusses ways to improve coverage of resources such as WordNet.
Outcome:	The proposed method improves WordNet coverage by reducing the number of words in the sample and reducing unbalanced corpora.

Copied to clipboard

Tianyu Jiang, Ellen Riloff

Challenge:	a new task is designed to learn the prototypical uses of human-made physical objects . human beings are creative, and they create things for a reason . humans often infer that the object will be used in the most prototypical way unless told otherwise .
Approach:	They propose a task to learn the prototypical uses for human-made physical objects . they use frames from FrameNet to represent a set of common functions for objects based on their prototypical function .
Outcome:	The proposed task uses masked patterns to model prototypical uses for objects . the proposed model predicts the prototypical functions of objects and can be used to make models .

Building a Knowledge Graph from Natural Language Definitions for Interpretable Text Entailment Recognition (L18-1)

Copied to clipboard

Vivian Silva, André Freitas, Siegfried Handschuh

Are Embedded Potatoes Still Vegetables? On the Limitations of WordNet Embeddings for Lexical Semantics (2023.emnlp-main)

Challenge:	a conceptual model for dictionary definitions is used to construct a knowledge graph from natural language definitions.
Approach:	They propose a method for automatically building a graph world knowledge base from natural language definitions.
Outcome:	The proposed method was used in an interpretable text entailment recognition approach.

Copied to clipboard

Xuyou Cheng, Michael Schlichtkrull, Guy Emerson

Enriching Word Usage Graphs with Cluster Definitions (2024.lrec-main)

Challenge:	Knowledge Base Embedding (KBE) models are widely used to encode structured information from knowledge bases, including WordNet, but the evaluation task is often focused on link prediction, ignoring their semantic capabilities.
Approach:	They propose to evaluate the performance of Knowledge Base Embedding (KBE) models of WordNet on link prediction and their ability to encode semantic information.
Outcome:	The proposed model performs poorly on two semantic tasks and two downstream tasks.

Copied to clipboard

Andrey Kutuzov, Mariia Fedorova, Dominik Schlechtweg, Nikolay Arefyev

Multimodality

Challenge:	Existing word usage graphs lack human interpretability of senses.
Approach:	They propose to enrich existing word usage graphs with cluster labels functioning as sense definitions.
Outcome:	The proposed dataset matches the definitions chosen from WordNet by two baseline systems.

LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification (D19-1)

Copied to clipboard

Jingjing Xu, Liang Zhao, Hanqi Yan, Qi Zeng, Yun Liang, Xu Sun

Robustness in NLP

Challenge:	Existing text classification models are fragile and sensitive to simple perturbations.
Approach:	They propose a generator-classifier adversarial training approach to improve classification models . they use a large-scale lexical knowledge base to generate attacking examples .
Outcome:	The proposed approach outperforms strong baselines and reduces test errors on neural networks.

Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation (P19-1)

Copied to clipboard

Daniel Loureiro, Alípio Jorge

XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization (2020.emnlp-main)

Challenge:	Contextual embeddings address the problem of meaning conflation hampering word embeddables.
Approach:	They propose a method that creates sense-level embeddings with full-coverage of WordNet without recourse to explicit sense distributions or task-specific modelling.
Outcome:	The proposed method surpasses previous systems using powerful models and is robust when ignoring part-of-speech and lemma features.

Copied to clipboard

Alessandro Raganato, Tommaso Pasini, Jose Camacho-Collados, Mohammad Taher Pilehvar

Representation Learning for Unseen Words by Bridging Subwords to Semantic Networks (2020.lrec-1)

Challenge:	Existing evaluation benchmarks for assessing distinct meanings of words are tied to sense inventories, restricting their usage to knowledge-based representation techniques.
Approach:	They propose a multilingual benchmark that models distinct meanings of words in English . they use a binary disambiguation task with gold standards in 12 new languages .
Outcome:	The proposed model can model distinct meanings of words in English even when no tagged instances are available for a target language.

Copied to clipboard

Yeachan Kim, Kang-Min Kim, SangKeun Lee

Embedding Words in Non-Vector Space with Unsupervised Graph Learning (2020.emnlp-main)

Challenge:	Pre-trained word embeddings only include words that appeared in corpora where pre-tried embedds are learned.
Approach:	They propose a method to represent out-of-vocabulary words using subword information and knowledge.
Outcome:	The proposed method improves performance over baselines that only use subwords or knowledge to represent OOV words.

Copied to clipboard

Max Ryabinin, Sergei Popov, Liudmila Prokhorenkova, Elena Voita

Aligning Wikipedia with WordNet:a Review and Evaluation of Different Techniques (2020.lrec-1)

Challenge:	GraphGlove is an unsupervised graph word representations that are learned end-to-end.
Approach:	They propose a method to learn weighted graph word representations end-to-end using a weighteable weighte . they adopt a hierarchical graph representation method and modify the GloVe training algorithm to learn graph representations.
Outcome:	The proposed method outperforms vector-based methods on word similarity and analogy tasks.

Copied to clipboard

Antoni Oliver

The MWN.PT WordNet for Portuguese: Projection, Validation, Cross-lingual Alignment and Distribution (2020.lrec-1)

Challenge:	a reliable alignment between WordNet and Wikipedia is a valuable resource for the creation of new wordnets in other languages and for the development of existing wordnet.
Approach:	They evaluate methods for aligning Wikipedia articles with WordNet synsets . they use a new gold and silver standard and a method that creates wordnets in other languages .
Outcome:	The proposed methods can be used to evaluate the quality of alignments between Wikipedia and WordNet synsets.

Copied to clipboard

António Branco, Sara Grilo, Márcia Bolrinha, Chakaveh Saedi, Ruben Branco, João Silva, Andreia Querido, Rita de Carvalho, Rosa Gaudio, Mariana Avelãs, Clara Pinto

English WordNet Random Walk Pseudo-Corpora (2020.lrec-1)

Challenge:	Lexical semantic networks are pervasive in natural language processing . Lexical ontologies play a key role in virtually all major applications .
Approach:	The present paper presents the MWN.PT WordNet for Portuguese . it is the largest high quality, manually validated and cross-lingually integrated wordnet of Portuguese based on the Princeton WordNet of English .
Outcome:	The MWN.PT WordNet for Portuguese includes 41,000 concepts expressed by 38,000 lexical units.

Copied to clipboard

Filip Klubička, Alfredo Maldonado, Abhijit Mahalunkar, John Kelleher

Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories (2021.emnlp-main)

Challenge:	a random walk over the WordNet taxonomy generates a set of pseudo-corpora . a resource description paper describes the creation and properties of such pseudo-corporates .
Approach:	They propose to use random walk to generate a set of pseudo-corpora over the English WordNet taxonomy.
Outcome:	The proposed pseudo-corpora can be used to train taxonomic word embeddings . the proposed pseudo corpora are generated from a random walk over the English wordnet taxonomy .

Copied to clipboard

Wenlin Yao, Xiaoman Pan, Lifeng Jin, Jianshu Chen, Dian Yu, Dong Yu

WordNet Is All You Need: A Surprisingly Effective Unsupervised Method for Graded Lexical Entailment (2023.findings-emnlp)

Challenge:	Existing supervised models struggle to make correct predictions on rare word senses due to limited training data.
Approach:	They propose a gloss alignment algorithm that can align definition sentences with the same meaning from different sense inventories to collect rich lexical knowledge.
Outcome:	The proposed method outperforms previous methods on both frequent and rare word senses.

Copied to clipboard

Joseph Renner, Pascal Denis, Rémi Gilleron

Synthetic Textual Features for the Large-Scale Detection of Basic-level Categories in English and Mandarin (2021.emnlp-main)

Challenge:	a simple unsupervised method for predicting graded lexical entailment in English relies on WordNet . despite its simplicity, our method outperforms all previous methods using WordNet as weak supervision.
Approach:	They propose an unsupervised method which relies exclusively on WordNet for predicting graded lexical entailment in English.
Outcome:	The proposed method outperforms existing methods on the largest GLE dataset using WordNet.

Copied to clipboard

Yiwen Chen, Simone Teufel

Challenge:	Basic-level categories are an important psycholinguistic concept introduced by Rosch et al. . an at-scale algorithm for the automatic determination of BLC exists, but it operates without Rosch-style semantic features.
Approach:	They propose a method for the detection of BLC at scale that makes use of Rosch-style semantic features.
Outcome:	The proposed method outperforms the current SoA in detecting basic-level categories with an accuracy of 75.0% in English and 80.7% in Mandarin.

BERTie Bott’s Every Flavor Labels: A Tasty Introduction to Semantic Role Labeling for Galician (2023.emnlp-main)

Copied to clipboard

Micaella Bruton, Meriem Beloucif

Metaphor Suggestions based on a Semantic Metaphor Repository (L18-1)

Challenge:	Existing corpora, WordNet, and dependency parsing are used to build a semantic role labeling system.
Approach:	They use existing corpora, WordNet, and dependency parsing to build a Galician dataset for training semantic role labeling systems.
Outcome:	The proposed model outperforms the 2009 CoNLL Shared Task by 0.83 on Spanish datasets.

Copied to clipboard

Gerard de Melo

Challenge:	Existing algorithms for suggesting metaphors have been used to find related words . corpus studies have found that metaphors are very pervasive even in formal language .
Approach:	They propose an algorithm that suggests metaphoric means of referring to concepts . they use MetaNet, a repository of conceptual metaphor, and lexical resources .
Outcome:	The proposed model expands the potential of the original repository by enabling new connections to be drawn.

A Short Survey on Sense-Annotated Corpora (2020.lrec-1)

Copied to clipboard

Tommaso Pasini, Jose Camacho-Collados

An Unsupervised, Geometric and Syntax-aware Quantification of Polysemy (2022.emnlp-main)

Challenge:	Word Sense Disambiguation (WSD) is a key task in Natural Language Understanding.
Approach:	They propose to use sense-annotated corpora for supervised Word Sense Disambiguation.
Outcome:	The proposed methods have been compared with knowledge-based approaches and have shown to be more efficient when they are available.

Copied to clipboard

Anmol Goel, Charu Sharma, Ponnurangam Kumaraguru

Cross-checking WordNet and SUMO Using Meronymy (L18-1)

Challenge:	Polysemy is the phenomenon where a single word form possesses two or more related senses.
Approach:	They propose an unsupervised framework to quantify polysemy for words in multiple languages . they use syntactic knowledge to infuse the framework with syntaktic knowledge .
Outcome:	The proposed framework is based on syntactic knowledge and is compared with existing methods in English, French and Spanish.

Copied to clipboard

Javier Álvez, Itziar Gonzalez-Dios, German Rigau

Challenge:	Existing methods to validate knowledge encoded in WordNet, SUMO and their mapping have been mainly manual .
Approach:	They propose to use WordNet and SUMO to validate knowledge by using automated theorem provers to evaluate the competency of SU MO-based ontologies.
Outcome:	The proposed method enables validation of some pieces of information and also the detection of missing information or inconsistencies among knowledge resources.

SeCoDa: Sense Complexity Dataset (2020.lrec-1)

Copied to clipboard

David Strohmaier, Sian Gooding, Shiva Taslimipoor, Ekaterina Kochmar

Combination of Contextualized and Non-Contextualized Layers for Lexical Substitution in French (2022.lrec-1)

Challenge:	Sense Complexity Dataset (SeCoDa) provides a corpus that is annotated jointly for word senses and word tokens.
Approach:	They propose to use a hierarchical sense annotation scheme that draws on information available in the Cambridge Advanced Learner's Dictionary to provide more coarse-grained senses than WordNet.
Outcome:	The Sense Complexity Dataset (SeCoDa) provides a corpus that is annotated jointly for complexity and word senses.

Copied to clipboard

Kévin Espasa, Emmanuel Morin, Olivier Hamon

Lexical Resource Mapping via Translations (2022.lrec-1)

Challenge:	Lexical substitution task requires to substitute a target word by candidates in a given context.
Approach:	They propose a method to find synonyms for a target word and rank them based on the context of the sentence.
Outcome:	The proposed method increases the BERT based system on the OOT measure but decreases on the BEST measure in the SemDis 2014 benchmark.

Copied to clipboard

Hongchang Bao, Bradley Hauer, Grzegorz Kondrak

Talking the Talk Does Not Entail Walking the Walk: On the Limits of Large Language Models in Lexical Entailment Recognition (2024.findings-emnlp)

Challenge:	a lexical resource associates words with concepts in multiple languages, which makes it difficult to combine information from multiple resources.
Approach:	They propose a translation-based approach to mapping lexical resources . they use word-concept pairs to align WordNet/BabelNet to CLICS and OmegaWiki .
Outcome:	The proposed method achieves state-of-the-art accuracy without other sources of knowledge . it can be framed as word sense disambiguation, and it can improve on existing methods .

Copied to clipboard

Candida Greco, Lucio La Cava, Andrea Tagarelli

WordNet under Scrutiny: Dictionary Examples in the Era of Large Language Models (2024.lrec-main)

Challenge:	Verbs are crucial for expressing actions and relationships between entities, making it essential to properly capture their nuances.
Approach:	They propose to use prompting strategies and zero-shot prompting to recognize entailment relations among verbs from two lexical databases, WordNet and HyperLex.
Outcome:	The proposed models can tackle the lexical entailment recognition task with moderately good performance, although at varying degree of effectiveness and under different conditions.

Copied to clipboard

Fatemah Yousef Almeman, Steven Schockaert, Luis Espinosa Anke

Zero-shot Event Detection Using a Textual Entailment Model as an Enhanced Annotator (2024.lrec-main)

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.

Copied to clipboard

Ziqian Zeng, Runyu Wu, Yuxiang Xiao, Xiaoda Zhong, Hanlin Wang, Zhengdong Lu, Huiping Zhuang