Related papers: Predicting Embedding Reliability in Low-Resource S…
Multilingual acoustic models have been successfully applied to low-resource speech recognition. Most existing works have combined many small corpora together and pretrained a multilingual model by sampling from each corpus uniformly. The…
The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…
This paper experiments with frequency-based corpus similarity measures across 39 languages using a register prediction task. The goal is to quantify (i) the distance between different corpora from the same language and (ii) the homogeneity…
Measuring similarity between training examples is critical for curating high-quality and diverse pretraining datasets for language models. However, similarity is typically computed with a generic off-the-shelf embedding model that has been…
We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e.g. a few hundred sentence pairs). Our method obtains word embeddings via an LSTM encoder-decoder model that…
Cross-lingual transfer is essential for building NLP systems for low-resource African languages, but practitioners lack reliable methods for selecting source languages. We systematically evaluate five embedding similarity metrics across 816…
Word embedding is a key component in many downstream applications in processing natural languages. Existing approaches often assume the existence of a large collection of text for learning effective word embedding. However, such a corpus…
The study of language emergence aims to understand how human languages are shaped by perceptual grounding and communicative intent. Computational approaches to emergent communication (EC) predominantly consider referential games in limited…
We analyze three critical components of word embedding training: the model, the corpus, and the training parameters. We systematize existing neural-network-based word embedding algorithms and compare them using the same corpus. We evaluate…
The rapidly growing ecosystem of Large Language Models (LLMs) makes it increasingly challenging to manage and utilize the vast and dynamic pool of models effectively. We propose LOCUS, a method that produces low-dimensional vector…
Recognizing semantically similar sentences or paragraphs across languages is beneficial for many tasks, ranging from cross-lingual information retrieval and plagiarism detection to machine translation. Recently proposed methods for…
Cross-lingual word embeddings encode the meaning of words from different languages into a shared low-dimensional space. An important requirement for many downstream tasks is that word similarity should be independent of language - i.e.,…
We introduce categorical modularity, a novel low-resource intrinsic metric to evaluate word embedding quality. Categorical modularity is a graph modularity metric based on the $k$-nearest neighbor graph constructed with embedding vectors of…
In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task. Our main approach is based on the LASER toolkit (Language-Agnostic SEntence Representations), which uses an encoder-decoder…
Effective representation of data is crucial in various machine learning tasks, as it captures the underlying structure and context of the data. Embeddings have emerged as a powerful technique for data representation, but evaluating their…
Recently, significant improvements have been achieved in various natural language processing tasks using neural sequence-to-sequence models. While aiming for the best generation quality is important, ultimately it is also necessary to…
Do word embeddings converge to learn similar things over different initializations? How repeatable are experiments with word embeddings? Are all word embedding techniques equally reliable? In this paper we propose evaluating methods for…
Metrics for measuring the comparability of corpora or texts need to be developed and evaluated systematically. Applications based on a corpus, such as training Statistical MT systems in specialised narrow domains, require finding a…
Word embedding spaces are powerful tools for capturing latent semantic relationships between terms in corpora, and have become widely popular for building state-of-the-art natural language processing algorithms. However, studies have shown…
In forensic voice comparison the speaker embedding has become widely popular in the last 10 years. Most of the pretrained speaker embeddings are trained on English corpora, because it is easily accessible. Thus, language dependency can be…