Challenge: a large corpus of newspaper archives has been generated, but historians have struggled to analyze it manually for decades.
Approach: They propose to train word embeddings from three large Lebanese news archives, which collectively consist of 609,386 scanned newspaper images and span 151 years.
Outcome: The embeddings are trained using a Google Tesseract 4.0 OCR engine and a benchmark of analogy tasks to evaluate their accuracy.

Similar Papers

Analyzing the Surprising Variability in Word Embedding Stability Across Languages (2021.emnlp-main)

Copied to clipboard

Challenge: Word embeddings are powerful representations that form the foundation of many natural language processing architectures.
Approach: They explore word embedding stability in a wide range of languages to gain insight into their stability.
Outcome: The proposed results provide insights into word embedding stability in English and other languages.
Diachronic word embeddings and semantic shifts: a survey (C18-1)

Copied to clipboard

Challenge: Existing methods for tracing time-related semantic shifts with word embedding models lack the cohesion, common terminology and shared practices of more established areas of natural language processing.
Approach: They propose several axes along which these methods can be compared and propose a framework for comparison.
Outcome: The proposed methods are compared with existing methods and outline their main challenges and potential applications.
Domain-Specific Word Embeddings with Structure Prediction (2023.tacl-1)

Copied to clipboard

Challenge: Current word embedding methods do not provide a way to use or predict information on structure between sub-corpora, time or domain.
Approach: They propose a word embedding method that provides general word representations for the whole corpus, domain-specific representations and embeddable alignment simultaneously.
Outcome: The proposed method provides better performance than baselines on a dataset of science and philosophy articles.
Dynamic Contextualized Word Embeddings (2021.acl-long)

Copied to clipboard

Challenge: Static word embeddings that represent words by a single vector cannot capture word meaning in different linguistic and extralinguistic contexts.
Approach: They propose dynamic contextualized word embeddings that represent words as a function of linguistic and extralinguistic contexts.
Outcome: The proposed model models time and social space jointly, making them attractive for NLP tasks involving semantic variability.
Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity (2020.acl-main)

Copied to clipboard

Challenge: Existing word embeddings combine complementary strengths of their components to achieve unsupervised semantic similarity (STS).
Approach: They propose to ensemble pre-trained sentence encoders into sentence meta-embeddings to achieve unsupervised Semantic Textual Similarity (STS) they adapt dimensionality reduction, generalized Canonical Correlation Analysis and cross-view auto-encoders to their work.
Outcome: The proposed method achieves 3.7% to 6.4% Pearson’s r over single-source word embeddings on the STS Benchmark and on the StS12-STS16 datasets.
Exploring Word Usage Change with Continuously Evolving Embeddings (2021.acl-demo)

Copied to clipboard

Challenge: a new method to track word usage changes is proposed for text datasets that are collected over a longer period of time.
Approach: They propose a way to track word usage changes via continuously evolving embeddings . they demonstrate an interactive web app that can explore semantic shifts with interactive plots a text .
Outcome: The proposed method can be used to analyze word usage changes with interactive plots.
Relational Word Embeddings (P19-1)

Copied to clipboard

Challenge: Existing approaches to learn word embeddings rely on external knowledge bases . however, they are limited by the amount of available relational knowledge .
Approach: They propose to encode relational knowledge in a separate word embedding . this is complementary to a standard word embedded from co-occurrence statistics .
Outcome: The proposed word embedding is complementary to a standard word embed.
Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment (D18-1)

Copied to clipboard

Challenge: Existing approaches to network embeddings focus on one-hot representations of vertices, which are not able to capture relationships between verti- ces.
Approach: They propose to integrate semantic features into network embeddings by matching important words between text sequences for all pairs of vertices.
Outcome: The proposed framework outperforms state-of-the-art embedding methods on three real-world benchmarks for downstream tasks including link prediction and multi-label vertex classification.
Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings (2021.emnlp-main)

Copied to clipboard

Challenge: Semantic sentence embeddings are usually supervisedly built minimizing distances between pairs of embeddable sentences labelled as semantically similar by annotators.
Approach: They propose a language-independent approach to build large datasets of pairs of informal texts weakly similar, without manual human effort, exploiting Twitter’s powerful signals of relatedness: replies and quotes of tweets.
Outcome: The proposed model learns classical Semantic Textual Similarity, and excels on tasks where pairs of sentences are not exact paraphrases.
Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources (2020.acl-srw)

Copied to clipboard

Challenge: In this paper, we present an effective method for semantic specialization of word vector representations.
Approach: They propose a method for semantic specialization of word vector representations using BabelNet.
Outcome: The proposed method improves on word similarity and dialog state tracking tasks.

What is GenGO?

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

Information

About
Limitations