Related papers: Linguistic representations for fewer-shot relation…

Representation learning on text-attributed graphs (TAGs) has become a critical research problem in recent years. A typical example of a TAG is a paper citation graph, where the text of each paper serves as node attributes. Initial graph…

Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…

Knowledge graphs (KGs) have been successfully applied to the analysis of complex scientific and technological domains, with automatic KG generation methods typically building upon relation extraction models capturing fine-grained relations…

Cross-lingual summarization (XLS) aims to generate a summary in a target language different from the source language document. While large language models (LLMs) have shown promising zero-shot XLS performance, their few-shot capabilities on…

Neural network language models (NNLMs) have achieved ever-improving accuracy due to more sophisticated architectures and increasing amounts of training data. However, the inductive bias of these models (formed by the distributional…

Transliteration has emerged as a promising means to bridge the gap between various languages in multilingual NLP, showing promising results especially for languages using non-Latin scripts. We investigate the degree to which shared script,…

Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pairs, training only a…

We present a probabilistic model that simultaneously learns alignments and distributed representations for bilingual data. By marginalizing over word alignments the model captures a larger semantic context than prior work relying on hard…

Large language models (LLMs) have achieved state-of-the-art performance in machine translation (MT) and demonstrated the ability to leverage in-context learning through few-shot examples. However, the mechanisms by which LLMs use different…

Despite advances in the multilingual capabilities of Large Language Models (LLMs), their performance varies substantially across different languages and tasks. In multilingual retrieval-augmented generation (RAG)-based systems, knowledge…

Two distinct approaches have been proposed for relational triple extraction - pipeline and joint. Joint models, which capture interactions across triples, are the more recent development, and have been shown to outperform pipeline models…

Existing methods in relation extraction have leveraged the lexical features in the word sequence and the syntactic features in the parse tree. Though effective, the lexical features extracted from the successive word sequence may introduce…

In real-world scenarios, labeled samples for dialogue summarization are usually limited (i.e., few-shot) due to high annotation costs for high-quality dialogue summaries. To efficiently learn from few-shot samples, previous works have…

To leverage machine learning in any decision-making process, one must convert the given knowledge (for example, natural language, unstructured text) into representation vectors that can be understood and processed by machine learning model…

Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings. However, people can grasp new knowledge by learning a few instances. To this end, we…

Recent years have seen rapid development in Information Extraction, as well as its subtask, Relation Extraction. Relation Extraction is able to detect semantic relations between entities in sentences. Currently, many efficient approaches…

Large language models are increasingly deployed across diverse applications. This often includes tasks LLMs have not encountered during training. This implies that enumerating and obtaining the high-quality training data for all tasks is…

Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the…

Linguistic typology aims to capture structural and semantic variation across the world's languages. A large-scale typology could provide excellent guidance for multilingual Natural Language Processing (NLP), particularly for languages that…

Augmenting Transformers with linguistic structures effectively enhances the syntactic generalization performance of language models. Previous work in this direction focuses on syntactic tree structures of languages, in particular…