Related papers: Fast and unsupervised methods for multilingual cog…

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

Multilingual Large Language Models (LLMs) exhibit remarkable cross-lingual abilities, yet often exhibit a systematic bias toward the representations from other languages, resulting in semantic interference when generating content in…

We present a cross-linguistic study that aims to quantify vowel harmony using data-driven computational modeling. Concretely, we define an information-theoretic measure of harmonicity based on the predictability of vowels in a natural…

Large language models (LLMs) offer new opportunities for scalable analysis of online discourse. Yet their use in multilingual social science research remains constrained by model size, cost and linguistic bias. We develop a lightweight,…

We present a novel clustering objective that learns a neural network classifier from scratch, given only unlabelled data samples. The model discovers clusters that accurately match semantic classes, achieving state-of-the-art results in…

Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual…

In zero-resource settings where transcribed speech audio is unavailable, unsupervised feature learning is essential for downstream speech processing tasks. Here we compare two recent methods for frame-level acoustic feature learning. For…

Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a novel,…

The availability of highly accurate urban airborne laser scanning (ALS) data will increase rapidly in the future, especially as acquisition costs decrease, for example through the use of drones. Current challenges in data processing are…

Cross-lingual plagiarism (CLP) occurs when texts written in one language are translated into a different language and used without acknowledging the original sources. One of the most common methods for detecting CLP requires online machine…

We introduce new methods for estimating and evaluating embeddings of words in more than fifty languages in a single shared embedding space. Our estimation methods, multiCluster and multiCCA, use dictionaries and monolingual data; they do…

There is an increasing need for more automated system-log analysis tools for large scale online system in a timely manner. However, conventional way to monitor and classify the log output based on keyword list does not scale well for…

This paper investigates an unsupervised approach towards deriving a universal, cross-lingual word embedding space, where words with similar semantics from different languages are close to one another. Previous adversarial approaches have…

Prompt-based tuning has been proven effective for pretrained language models (PLMs). While most of the existing work focuses on the monolingual prompts, we study the multilingual prompts for multilingual PLMs, especially in the zero-shot…

This study introduces a general semiparametric clusterwise index distribution model to analyze how latent clusters affect the covariate-response relationships. By employing sufficient dimension reduction to account for the effects of…

As it has been unveiled that pre-trained language models (PLMs) are to some extent capable of recognizing syntactic concepts in natural language, much effort has been made to develop a method for extracting complete (binary) parses from…

Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems , or to perform quality…

This work presents methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts. We hypothesize that the cross-lingual alignment strategy is transferable, and therefore a model trained to align only…

While pretrained language models (PLMs) primarily serve as general-purpose text encoders that can be fine-tuned for a wide variety of downstream tasks, recent work has shown that they can also be rewired to produce high-quality word…

Translated texts are distinctively different from original ones, to the extent that supervised text classification methods can distinguish between them with high accuracy. These differences were proven useful for statistical machine…