相关论文: How Good is BLI as an Alignment Measure: A Study i…

Existing vision-language methods typically support two languages at a time at most. In this paper, we present a modular approach which can easily be incorporated into existing vision-language methods in order to support many languages. We…

Most existing methods for automatic bilingual dictionary induction rely on prior alignments between the source and target languages, such as parallel corpora or seed dictionaries. For many language pairs, such supervised alignments are not…

We examine the abilities of intrinsic bias metrics of static word embeddings to predict whether Natural Language Processing (NLP) systems exhibit biased behavior. A word embedding is one of the fundamental NLP technologies that represents…

Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…

Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully…

Text embeddings have become an essential part of a variety of language applications. However, methods for interpreting, exploring and reversing embedding spaces are limited, reducing transparency and precluding potentially valuable…

We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples learning the transformation from the source language to the target language into (a)…

Meta-embedding (ME) learning is an emerging approach that attempts to learn more accurate word embeddings given existing (source) word embeddings as the sole input. Due to their ability to incorporate semantics from multiple source…

The long-standing one-to-many problem of gold standard responses in open-domain dialogue systems presents challenges for automatic evaluation metrics. Though prior works have demonstrated some success by applying powerful Large Language…

One of the most important problems in machine translation (MT) evaluation is to evaluate the similarity between translation hypotheses with different surface forms from the reference, especially at the segment level. We propose to use word…

Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world. However, they currently require large pretraining corpora or access to typologically similar languages. In…

Modern generative and vision-language models (VLMs) are increasingly used in scientific and medical decision support, where predicted probabilities must be both accurate and well calibrated. Despite strong empirical results with moderate…

Deep Metric Learning (DML) proposes to learn metric spaces which encode semantic similarities as embedding space distances. These spaces should be transferable to classes beyond those seen during training. Commonly, DML methods task…

Pretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear…

Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability, undermining…

Low-dimensional projections of text embeddings support visual analysis of document collections, but their spatial organization may not reflect the relationships an analyst intends to examine. Existing semantic interaction approaches encode…

The advent of pre-trained language models (PLMs) has enabled significant performance gains in the field of natural language processing. However, recent studies have found PLMs to suffer from miscalibration, indicating a lack of accuracy in…

As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time. Confidence calibration, an effective analysis method for gauging the reliability of…

Development of language proficiency models for non-native learners has been an active area of interest in NLP research for the past few years. Although language proficiency is multidimensional in nature, existing research typically…

Metric learning has the aim to improve classification accuracy by learning a distance measure which brings data points from the same class closer together and pushes data points from different classes further apart. Recent research has…