Related papers: SIGTYP 2020 Shared Task: Prediction of Typological…

Saliency maps can explain a neural model's predictions by identifying important input features. They are difficult to interpret for laypeople, especially for instances with many features. In order to make them more accessible, we formalize…

In this paper, we propose Latent Relation Language Models (LRLMs), a class of language models that parameterizes the joint distribution over the words in a document and the entities that occur therein via knowledge graph relations. This…

There is an increasing amount of evidence that in cases with little or no data in a target language, training on a different language can yield surprisingly good results. However, currently there are no established guidelines for choosing…

This study evaluates the potential of a large language model for aiding in generation of semantic feature norms - a critical tool for evaluating conceptual structure in cognitive science. Building from an existing human-generated dataset,…

Lexical Semantic Change detection, i.e., the task of identifying words that change meaning over time, is a very active research area, with applications in NLP, lexicography, and linguistics. Evaluation is currently the most pressing problem…

Large-scale transformer-based language models (LMs) demonstrate impressive capabilities in open text generation. However, controlling the generated text's properties such as the topic, style, and sentiment is challenging and often requires…

This article reports on a survey carried out across the Natural Language Processing (NLP) community. The survey aimed to capture the opinions of the research community on issues surrounding shared tasks, with respect to both participation…

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Abstract. Cross-lingual knowledge alignment is the cornerstone in building a comprehensive knowledge graph (KG), which can benefit various knowledge-driven applications. As the structures of KGs are usually sparse, attributes of entities…

Challenging problems such as open-domain question answering, fact checking, slot filling and entity linking require access to large, external knowledge sources. While some models do well on individual tasks, developing general models is…

Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process. However, biased datasets can also hurt the generalization…

Semantic communication has emerged as a promising technology for enhancing communication efficiency. However, most existing research emphasizes single-task reconstruction, neglecting model adaptability and generalization across multi-task…

Over the past decade, Knowledge Graphs have received enormous interest both from industry and from academia. Research in this area has been driven, above all, by the Database (DB) community and the Semantic Web (SW) community. However,…

Word embeddings allow natural language processing systems to share statistical information across related words. These embeddings are typically based on distributional statistics, making it difficult for them to generalize to rare or unseen…

Despite the recent popularity of knowledge graph (KG) related tasks and benchmarks such as KG embeddings, link prediction, entity alignment and evaluation of the reasoning abilities of pretrained language models as KGs, the structure and…

Recent advances in NLP demonstrate the effectiveness of training large-scale language models and transferring them to downstream tasks. Can fine-tuning these models on tasks other than language modeling further improve performance? In this…

Modern models for common NLP tasks often employ machine learning techniques and train on journalistic, social media, or other culturally-derived text. These have recently been scrutinized for racial and gender biases, rooting from inherent…

Even for common NLP tasks, sufficient supervision is not available in many languages -- morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent…

In the area of ad-targeting, predicting user responses is essential for many applications such as Real-Time Bidding (RTB). Many of the features available in this domain are sparse categorical features. This presents a challenge especially…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…