Bilingual Lexicon Induction (BLI), where words are translated between two languages, is an important NLP task. While noticeable progress on BLI in rich resource languages using static word embeddings has been achieved. The word translation performance can be further improved by incorporating information from contextualized word embeddings. In this paper, we introduce ProMap, a novel approach for BLI that leverages the power of prompting pretrained multilingual and multidialectal language models to address these challenges. To overcome the employment of subword tokens in these models, ProMap relies on an effective padded prompting of language models with a seed dictionary that achieves good performance when used independently. We also demonstrate the effectiveness of ProMap in re-ranking results from other BLI methods such as with aligned static word embeddings. When evaluated on both rich-resource and low-resource languages, ProMap consistently achieves state-of-the-art results. Furthermore, ProMap enables strong performance in few-shot scenarios (even with less than 10 training examples), making it a valuable tool for low-resource language translation. Overall, we believe our method offers both exciting and promising direction for BLI in general and low-resource languages in particular. ProMap code and data are available at \url{https://github.com/4mekki4/promap}.

News media is expected to uphold unbiased reporting. Yet they may still affect public opinion by selectively including or omitting events that support or contradict their ideological positions. Prior work in NLP has only studied media bias via linguistic style and word usage. In this paper, we study to which degree media balances news reporting and affects consumers through event inclusion or omission. We first introduce the task of detecting both partisan and counter-partisan events: events that support or oppose the author's political ideology. To conduct our study, we annotate a high-quality dataset, PAC, containing 8,511 (counter-)partisan event annotations in 304 news articles from ideologically diverse media outlets. We benchmark PAC to highlight the challenges of this task. Our findings highlight both the ways in which the news subtly shapes opinion and the need for large language models that better understand events within a broader context. Our dataset can be found at https://github.com/launchnlp/Partisan-Event-Dataset.

Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a decoder, which encourages the network to capture and learn structural information about objects and scenes. The intermediate feature representations obtained from MIM are suitable for fine-tuning on downstream tasks. In this paper, we propose an Image Modeling framework based on random orthogonal projection instead of binary masking as in MIM. Our proposed Random Orthogonal Projection Image Modeling (ROPIM) reduces spatially-wise token information under guaranteed bound on the noise variance and can be considered as masking entire spatial image area under locally varying masking degrees. Since ROPIM uses a random subspace for the projection that realizes the masking step, the readily available complement of the subspace can be used during unmasking to promote recovery of removed information. In this paper, we show that using random orthogonal projection leads to superior performance compared to crop-based masking. We demonstrate state-of-the-art results on several popular benchmarks. ROPIM achieves a higher accuracy (see et al., 2022; Xie et al., 2022) mainly apply also GPL-ROPIM) with a lower training time. The masking in the spatial domain by randomly excluding blue and yellow regions indicate fast methods and image patches. ROPIM has are highly correlated within their spatial neighbourhood, both high accuracy and is fast (the green region). Existing MIM approaches typically replace a random set of input tokens with a special learnable symbol, called MASK, and aim to recover either masked image pixels (He et al., 2022; Xie et al., 2022), masked content features (Wei et al., 2022) or latent representations (Baevski et al., 2022).

For both investors and policymakers, forecasting the stock market is essential as it serves as an indicator of economic well-being. To this end, we harness the power of social media data, a rich source of public sentiment, to enhance the accuracy of stock market predictions. Diverging from conventional methods, we pioneer an approach that integrates sentiment analysis, macroeconomic indicators, search engine data, and historical prices within a multi-attention deep learning model, masterfully decoding the complex patterns inherent in the data. We showcase the state-of-the-art performance of our proposed model using a dataset, specifically curated by us, for predicting stock market movements and volatility.

Large Language Models (LLMs) exhibit impressive performance on a range of NLP tasks, due to the general-purpose linguistic knowledge acquired during pretraining. Existing model interpretability research (Tenney et al., 2019) suggests that a linguistic hierarchy emerges in the LLM layers, with lower layers better suited to solving syntactic tasks and higher layers employed for semantic processing. Yet, little is known about how encodings of different linguistic phenomena interact within the models and to what extent processing of linguistically-related categories relies on the same, shared model representations. In this paper, we propose a framework for testing the joint encoding of linguistic categories in LLMs. Focusing on syntax, we find evidence of joint encoding both at the same (related part-of-speech (POS) classes) and different (POS classes and related syntactic dependency relations) levels of linguistic hierarchy. Our cross-lingual experiments show that the same patterns hold across languages in multilingual LLMs.

Many discriminative natural language understanding (NLU) tasks have large label spaces. Learning such a process of large-space decision making is particularly challenging due to the lack of training instances per label and the difficulty of selection among many fine-grained labels. Inspired by dense retrieval methods for passage finding in open-domain QA, we propose a reformulation of large-space discriminative NLU tasks as a learning-to-retrieve task, leading to a novel solution named Dense Decision Retrieval (DDR ). Instead of predicting fine-grained decisions as logits, DDR adopts a dual-encoder architecture that learns to predict by retrieving from a decision thesaurus. This approach not only leverages rich indirect supervision signals from easy-to-consume learning resources for dense retrieval, it also leads to enhanced prediction generalizability with a semantically meaningful representation of the large decision space. When evaluated on tasks with decision spaces ranging from hundreds to hundred-thousand scales, DDR outperforms strong baselines greatly by 27.54% in P@1 on two extreme multi-label classification tasks, 1.17% in F1 score ultra-fine entity typing, and 1.26% in accuracy on three few-shot intent classification tasks on average. Code and resources are available at https://github.com/luka-group/DDR

Image captioning aims to describe visual content in natural language. As 'a picture is worth a thousand words', there could be various correct descriptions for an image. However, with maximum likelihood estimation as the training objective, the captioning model is penalized whenever its prediction mismatches with the label. For instance, when the model predicts a word expressing richer semantics than the label, it will be penalized and optimized to prefer more concise expressions, referred to as conciseness optimization. In contrast, predictions that are more concise than labels lead to richness optimization. Such conflicting optimization directions could eventually result in the model generating general descriptions. In this work, we introduce Semipermeable MaxImum Likelihood Estimation (SMILE), which allows richness optimization while blocking conciseness optimization, thus encouraging the model to generate longer captions with more details. Extensive experiments on two mainstream image captioning datasets MSCOCO and Flickr30K demonstrate that SMILE significantly enhances the descriptiveness of generated captions. We further provide in-depth investigations to facilitate a better understanding of how SMILE works.

Minimum spanning trees (MSTs) provide a convenient representation of datasets in numerous pattern recognition activities. Moreover, they are relatively fast to compute. In this paper, we quantify the extent to which they can be meaningful in partitional data clustering tasks in low-dimensional spaces. By identifying the upper bounds for the agreement between the best (oracle) algorithm and the expert labels from a large battery of benchmark data, we discover that MST methods are overall very competitive. Next, instead of proposing yet another algorithm that performs well on a limited set of examples, we review, study, extend, and generalise existing, state-of-the-art MST-based partitioning schemes. This leads to a few new and noteworthy approaches. Overall, Genie and the information-theoretic methods often outperform the non-MST algorithms such as k-means, Gaussian mixtures, spectral clustering, Birch, density-based, and classical hierarchical agglomerative procedures. Nevertheless, we identify that there is still some room for improvement, and thus the development of novel algorithms is encouraged.

Continuous optimization based motion planners require deciding on a maneuver homotopy before optimizing the trajectory. Under uncertainty, maneuver intentions of other participants can be unclear, and the vehicle might not be able to decide on the most suitable maneuver. This work introduces a method that incorporates multiple maneuver preferences in planning. It optimizes the trajectory by considering weighted maneuver preferences together with uncertainties ranging from perception to prediction while ensuring the feasibility of a chance-constrained fallback option. Evaluations in both driving experiments and simulation studies show enhanced interaction capabilities and comfort levels compared to conventional planners, which consider only a single maneuver.

Federated Learning (FL) distributes machine learning (ML) training across many edge devices to reduce data transfer overhead and protect data privacy. Since FL model training may span millions of devices and is thus resource-intensive, prior work has focused on improving its resource efficiency to optimize time-to-accuracy. However, prior work generally treats all resources the same, while, in practice, they may incur widely different costs, which instead motivates optimizing cost-to-accuracy. To address the problem, we design CEFL, which uses adaptive cost-aware client selection policies to optimize an arbitrary cost metric when training FL models. Our policies extend and combine prior work on utility-based client selection and critical learning periods by making them cost-aware. We demonstrate CEFL by designing carbon-efficient FL, where energy's carbon-intensity is the cost, and show that it i) reduces carbon emissions by 93\% and reduces training time by 50% compared to random client selection and ii) reduces carbon emissions by 80%, while only increasing training time by 38%, compared to a state-of-the-art approach that optimizes training time.