Papers with lexicon induction
Analytical Methods for Interpretable Ultradense Word Embeddings (D19-1)
Copied to clipboard
| Challenge: | Word embeddings lack interpretability, but rotation of word spaces can help . e.g., lexicon induction, gender bias can be removed by removing interpretable dimensions . |
| Approach: | They propose three methods for making word embeddings interpretable by rotation . they use Densifier, linear SVMs and DensRay to compute word spaces in closed form . |
| Outcome: | The proposed method can be computed in closed form and is more robust than Densifier. |
CSP:Code-Switching Pre-training for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to train neural machine translation models are data-hungry and low-resource . et al., 2018; Radford e.t., 2019; Yang ee.,2019) proposes a new pre-training method for NMT . |
| Approach: | They propose a new pre-training method which randomly replaces some words in the input sentence with their translation words in target language. |
| Outcome: | The proposed method improves on unsupervised and supervised NMT models by making full use of monolingual corpora. |
How Lexical is Bilingual Lexicon Induction? (2024.findings-naacl)
Copied to clipboard
| Challenge: | lexical variation and low-resource settings make it difficult to learn in low-level settings. |
| Approach: | They propose to incorporate additional lexical information into the retrieve-and-rank approach to improve lexicon induction. |
| Outcome: | The proposed approach improves on XLING by an average of 2% across all language pairs. |
Domain Adaptation of Neural Machine Translation by Lexicon Induction (P19-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is sensitive to domain shift, resulting in failure for sentences with large numbers of unknown words and lack of supervision for domain-specific words. |
| Approach: | They propose an unsupervised method which fine-tunes a pre-trained out-of-domain NMT model using a pseudo-in-domain corpus. |
| Outcome: | The proposed method improves in five domains without using in-domain parallel sentences and up to 2 BLEU over strong back-translation baselines. |
TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languages (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Whether politeness phenomena and strategies are universal across languages or not have been controversial among sociologists and linguists. |
| Approach: | They create a dataset containing three-way politeness annotations for 500 examples in each language, totaling 4.5K examples. |
| Outcome: | The proposed model shows a robust zero-shot transfer ability, but falls short of estimated human accuracy significantly. |
Inducing lexicons of in-group language with socio-temporal context (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for lexicon induction do not capture the evolving nature of in-group language, nor the social structure of the community. |
| Approach: | They propose a method for inducing lexicons of in-group language which incorporates its socio-temporal context. |
| Outcome: | The proposed method outperforms existing methods for lexicon induction . it quantifies relevance of each term to a specific sub-community at a given point in time . |