Papers with FastText
Probabilistic FastText for Multi-Sense Word Embeddings (P18-1)
Copied to clipboard
| Challenge: | Probabilistic FastText model for word embeddings captures word senses, sub-word structure, and uncertainty information. |
| Approach: | They propose a model for word embeddings that captures multiple word senses . they represent each word with a Gaussian mixture density, with each vector representing an n-gram . |
| Outcome: | The proposed model outperforms dictionary-level probabilistic embeddings on word-similarity benchmarks. |
Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations (2023.starsem-1)
Copied to clipboard
| Challenge: | a recent study of the effect of visual grounding on language representations has given a new life to the debate around extractability and quality of semantic information in representations trained solely on textual input. |
| Approach: | They compare word embeddings from vision-and-language models to text-only models . they identify meaning properties and relations that characterize words whose embeddements are most affected by visual grounding . |
| Outcome: | The proposed model differs from text-only models on semantic representations of language . the study is the first large-scale study of the effect of visual grounding on language representations . |
Investigating the Frequency Distortion of Word Embeddings and Its Impact on Bias Metrics (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent research has shown that static word embeddings can encode words’ frequencies, but little has been studied about this behavior. |
| Approach: | They propose to use static word embeddings to encode words' frequencies and to assess the impact of this relationship on embeddable bias metrics. |
| Outcome: | The proposed model shows that word embeddings can produce higher similarity between high-frequency words than other embeddables. |
NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit (P19-3)
Copied to clipboard
| Challenge: | NeuralClassifier is a toolkit for hierarchical multi-label text classification. |
| Approach: | They propose a toolkit for neural hierarchical multi-label text classification . they use a variety of text encoders to implement the model . |
| Outcome: | The proposed model achieves comparable performance with reported results in the literature. |
Detecting Omissions in LLM-Generated Medical Summaries (2025.emnlp-industry)
Copied to clipboard
Achir Oukelmoun, Nasredine Semmar, Gaël de Chalendar, Clement Cormi, Mariame Oukelmoun, Eric Vibert, Marc-Antoine Allard
| Challenge: | Large Language Models (LLMs) have created a number of use cases in the medical field . omissions in summaries can jeopardize the decision-making process . |
| Approach: | They propose a dataset to evaluate omissions in large-scale medical summaries . they propose 'embedKDECheck' method that uses embeddings generated by a third-party NLP model . |
| Outcome: | The proposed method is well-suited for resource-constrained environments. |
Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation (P19-1)
Copied to clipboard
| Challenge: | Pretrained contextual and non-contextual subword embeddings are available in over 250 languages, allowing massively multilingual NLP. |
| Approach: | They compare pretrained contextual and non-contextual subword embeddings with a contextual representation method, namely BERT, on multilingual named entity recognition and part-of-speech tagging. |
| Outcome: | The proposed method outperforms non-contextual embeddings on multilingual named entity recognition and part-of-speech tagging. |
Comparing Pretrained Multilingual Word Embeddings on an Ontology Alignment Task (L18-1)
Copied to clipboard
| Challenge: | Existing word embeddings capture a string's semantics and can be trained for multiple languages. |
| Approach: | They propose to compare three different multilingual pretrained word embedding repositories with a string-matching baseline and use it to compute semantic similarities of strings in different languages. |
| Outcome: | The proposed method produces correct alignments on a non-standard dataset on all four languages. |
MaskLID: Code-Switching Language Identification through Iterative Masking (2024.acl-short)
Copied to clipboard
| Challenge: | Sentence-level LIDs are classifiers trained on monolingual texts to provide single labels, typically using a softmax layer to turn scores into probabilities. |
| Approach: | They propose a simple yet effective code-switching language identification method that uses the LID itself to mask features associated with L1 and L2 in the next round. |
| Outcome: | The proposed method is based on two open-source LIDs based in the FastText architecture and does not require any external resources. |
Can vectors read minds better than experts? Comparing data augmentation strategies for the automated scoring of children’s mindreading ability (2021.acl-long)
Copied to clipboard
| Challenge: | In-domain experts are recruited to reannotate augmented samples and determine to what extent each strategy preserves the original rating. |
| Approach: | They implement 7 different data augmentation strategies for the task of automatic scoring of children’s ability to understand others’ thoughts, feelings, and desires. |
| Outcome: | The data augmentation strategies outperform task-agnostic augmentations and automatic augmentation systems perform worst on the MIND-CA corpus. |
HyperText: Endowing FastText with Hyperbolic Geometry (2020.findings-emnlp)
Copied to clipboard
| 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 First Dataset for Film Age Appropriateness Investigation (2020.lrec-1)
Copied to clipboard
| Challenge: | Several studies in CL have examined the genre in terms of Sentiment Analysis (Phan and Matsumoto, 2018) . but the actual film content (the script, audio, and video for example) has not received as much interest in spite of the potential availability of huge datasets. |
| Approach: | They use a corpus of 17000 films along with their age ratings to predict the correct age classification for the United States and the UK. |
| Outcome: | The proposed model outperforms FastText and Deep Learning architectures in the US and UK and is 79.3% accurate for the US compared to 80% for the UK. |
Evaluating Word Embeddings with Categorical Modularity (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing word embeddings use different bilingual supervision signals with varying levels of strength. |
| Approach: | They propose a graph modularity metric to measure word embedding quality . they use a set of 500 words belonging to 59 neurobiologically motivated semantic categories . |
| Outcome: | The proposed metric measures word embedding quality on monolingual and cross-lingual tasks. |
Data Expansion Using WordNet-based Semantic Expansion and Word Disambiguation for Cyberbullying Detection (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to identify cyberbullying from text are limited due to the complexity of the content and the lack of labeled large-scale corpus. |
| Approach: | They propose a data augmentation-based approach that could enhance the automatic detection of cyberbullying in social media texts. |
| Outcome: | The proposed approach overcomes limitations of social media posts with word sense disambiguation and synonymy relation . results show that the proposed approach improves on the existing classifiers with and without data augmentation. |
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 . |
Word Embedding Evaluation for Sinhala (2020.lrec-1)
Copied to clipboard
| Challenge: | Word embeddings are a key component of the natural language processing process. |
| Approach: | They evaluate three standard word embedding models for Sinhala language using two evaluation methods: intrinsic evaluation and extrinsic evaluation. |
| Outcome: | The proposed models performed best in the three evaluation tasks, while FastText and Glove showed the lowest accuracies. |
A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution. (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for Coreference Resolution rely on word embeddings for word representation, but performance of different embeddables is largely overlooked. |
| Approach: | They frame their study in the context of Event and Entity Coreference Resolution (EvCR & EnCR) they examine whether there is a trade-off between performance and embedding size . |
| Outcome: | The embeddings achieve 86% of the performance of the largest model while being 1.2% of its size. |
Imputing Out-of-Vocabulary Embeddings with LOVE Makes LanguageModels Robust with Little Cost (2022.acl-long)
Copied to clipboard
| Challenge: | State-of-the-art NLP systems are brittle when faced with Out-ofVocabulary words . we present a framework that extends word embeddings and makes them robust to OOV . |
| Approach: | They propose a framework that extends existing word embeddings and makes them robust to OOV. |
| Outcome: | The proposed model performs better on original datasets and corrupted variants than previous competitors. |
IndiSocialFT: Multilingual Word Representation for Indian languages in code-mixed environment (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on word embeddings for Indian languages focus on monolingual corpora with limited reach to social media setups. |
| Approach: | They propose a generalized representation vector for diverse text characteristics . they use a FastText model to gather text from social media and well-formed sources . |
| Outcome: | The proposed representation vector surpasses baselines in most cases and languages, demonstrating suitability for various NLP applications. |
Misspelling Oblivious Word Embeddings (N19-1)
Copied to clipboard
Aleksandra Piktus, Necati Bora Edizel, Piotr Bojanowski, Edouard Grave, Rui Ferreira, Fabrizio Silvestri
| Challenge: | Existing word embeddings have limited applicability to malformed texts . misspellings are frequent and embeddable for words that have not been observed at training time . |
| Approach: | They propose a method to learn word embeddings that are resilient to misspellings . they use FastText with subwords to train embeddables on a new dataset . |
| Outcome: | The proposed method is tested on a publicly available dataset. |
Utilizing Subword Entities in Character-Level Sequence-to-Sequence Lemmatization Models (2020.coling-main)
Copied to clipboard
| Challenge: | a novel character-level sequence-to-sequence lemmatization model uses generic n-gram embeddings to map word/lemma pairs . semitic languages, like Arabic and Hebrew, add other challenges to handle unseen words . |
| Approach: | They propose a character-level sequence-to-sequence lemmatization model . they use generic n-gram embeddings, concatenative (stems) and templatic (roots and patterns) morphological subwords. |
| Outcome: | The proposed model outperforms other linguistically-driven models with generic n-gram embeddings . the best system handles word/lemma pairs that are both unseen in the training data . |
IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages (2020.findings-emnlp)
Copied to clipboard
Divyanshu Kakwani, Anoop Kunchukuttan, Satish Golla, Gokul N.C., Avik Bhattacharyya, Mitesh M. Khapra, Pratyush Kumar
| Challenge: | In this paper, we present NLP resources for 11 major Indian languages . distributional representations are the cornerstone of modern NLP, authors say . |
| Approach: | They introduce NLP resources for 11 major Indian languages from two major language families . monolingual corpora contains 8.8 billion tokens across all 11 languages and Indian English . they also compile a benchmark for Indian language NLU to evaluate their results . |
| Outcome: | The monolingual corpora contains 8.8 billion tokens across all 11 languages and Indian English . the pre-trained language models are based on the compact ALBERT model . |
A Neural Network Model for Part-Of-Speech Tagging of Social Media Texts (L18-1)
Copied to clipboard
| Challenge: | Recent approaches based on end-to-end Deep Neural Networks (DNNs) have shown promising results for Natural Language Processing (NLP). |
| Approach: | They propose a neural network model for part-of-speech (POS) tagging of User-Generated Content (UGC) such as Twitter, Facebook and Web forums that uses character and word representations. |
| Outcome: | The proposed model is end-to-end and uses character and word representations . it is compared with existing models on social media in English, german, french, italian and spanish . |
Give your Text Representation Models some Love: the Case for Basque (2020.lrec-1)
Copied to clipboard
Rodrigo Agerri, Iñaki San Vicente, Jon Ander Campos, Ander Barrena, Xabier Saralegi, Aitor Soroa, Eneko Agirre
| Challenge: | Word embeddings and pre-trained language models are expensive to train and are often used by small companies and research groups to build their own. |
| Approach: | They propose to use word embeddings and pre-trained language models to build rich representations of text and improve NLP tasks. |
| Outcome: | The proposed models perform better than publicly available versions in downstream NLP tasks for Basque. |
Revisiting Tri-training of Dependency Parsers (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained word embeddings and self-training have been used in dependency parsing tasks for years. |
| Approach: | They compare tri-training and pretrained word embeddings in dependency parsing . they use language-specific FastText and ELMo embedds and multilingual BERT embedders . |
| Outcome: | The proposed methods are tri-training and pretrained word embeddings. |