Related papers: Modeling Bottom-up Information Quality during Lang…

There has been significant interest recently in learning multilingual word embeddings -- in which semantically similar words across languages have similar embeddings. State-of-the-art approaches have relied on expensive labeled data, which…

The detection and normalization of temporal expressions is an important task and preprocessing step for many applications. However, prior work on normalization is rule-based, which severely limits the applicability in real-world…

Neural language models (LMs) are arguably less data-efficient than humans from a language acquisition perspective. One fundamental question is why this human-LM gap arises. This study explores the advantage of grounded language acquisition,…

In recent years, there has been a significant increase in applications of multimodal signal processing and analysis, largely driven by the increased availability of multimodal datasets and the rapid progress in multimodal learning systems.…

Benefiting from large-scale pretrained vision language models (VLMs), the performance of visual question answering (VQA) has approached human oracles. However, finetuning such models on limited data often suffers from overfitting and poor…

Recent psycholinguistic studies have drawn conflicting conclusions about the relationship between the quality of a language model and the ability of its surprisal estimates to predict human reading times, which has been speculated to be due…

Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempts to decode the mappings between utterances and situations.…

Deep neural networks can memorize corrupted labels, making data quality critical for model performance, yet real-world datasets are frequently compromised by both label noise and input noise. This paper proposes a mutual information-based…

Monolingual data, being readily available in large quantities, has been used to upscale the scarcely available parallel data to train better models for automatic translation. Self-learning, where a model is made to learn from its output, is…

Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is…

Masked language modeling (MLM) plays a key role in pretraining large language models. But the MLM objective is often dominated by high-frequency words that are sub-optimal for learning factual knowledge. In this work, we propose an approach…

This paper addresses the problem of simultaneous machine translation (SiMT) by exploring two main concepts: (a) adaptive policies to learn a good trade-off between high translation quality and low latency; and (b) visual information to…

Training conversational question-answering (QA) systems requires a substantial amount of in-domain data, which is often scarce in practice. A common solution to this challenge is to generate synthetic data. Traditional methods typically…

A wide body of evidence shows that human language processing difficulty is predicted by the information-theoretic measure surprisal, a word's negative log probability in context. However, it is still unclear how to best estimate these…

Most studies on word-level Quality Estimation (QE) of machine translation focus on language-specific models. The obvious disadvantages of these approaches are the need for labelled data for each language pair and the high cost required to…

Test-time scaling has emerged as a widely adopted inference-time strategy for boosting reasoning performance. However, its effectiveness has been studied almost exclusively in English, leaving its behavior in other languages largely…

Many computational linguistic methods have been proposed to study the information content of languages. We consider two interesting research questions: 1) how is information distributed over long documents, and 2) how does content…

The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable…

Word embeddings such as ELMo have recently been shown to model word semantics with greater efficacy through contextualized learning on large-scale language corpora, resulting in significant improvement in state of the art across many…

Biased news reporting poses a significant threat to informed decision-making and the functioning of democracies. This study introduces a novel methodology for scalable, minimally biased analysis of media bias in political news. The proposed…