相关论文: Compositional Generalization in Multilingual Seman…

Compositional generalization is an important ability of language models and has many different manifestations. For data-to-text generation, previous research on this ability is limited to a single manifestation called Systematicity and…

When answering a question, people often draw upon their rich world knowledge in addition to the particular context. Recent work has focused primarily on answering questions given some relevant document or context, and required very little…

Prior work on Data-To-Text Generation, the task of converting knowledge graph (KG) triples into natural text, focused on domain-specific benchmark datasets. In this paper, however, we verbalize the entire English Wikidata KG, and discuss…

Compositionality is a common property in many modalities including natural languages and images, but the compositional generalization of multi-modal models is not well-understood. In this paper, we identify two sources of visual-linguistic…

Text-to-SQL semantic parsing has made significant progress in recent years, with various models demonstrating impressive performance on the challenging Spider benchmark. However, it has also been shown that these models often struggle to…

Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to…

Structured knowledge bases (KBs) are an asset for search engines and other applications, but are inevitably incomplete. Language models (LMs) have been proposed for unsupervised knowledge base completion (KBC), yet, their ability to do this…

Semantic parsing is the process of mapping a natural language sentence into a formal representation of its meaning. In this work we use the neural network approach to transform natural language sentence into a query to an ontology database…

Data originating from the Web, sensor readings and social media result in increasingly huge datasets. The so called Big Data comes with new scientific and technological challenges while creating new opportunities, hence the increasing…

Most semantic parsers that map sentences to graph-based meaning representations are hand-designed for specific graphbanks. We present a compositional neural semantic parser which achieves, for the first time, competitive accuracies across a…

Progress in sentence simplification has been hindered by a lack of labeled parallel simplification data, particularly in languages other than English. We introduce MUSS, a Multilingual Unsupervised Sentence Simplification system that does…

Compositional generalization is a fundamental trait in humans, allowing us to effortlessly combine known phrases to form novel sentences. Recent works have claimed that standard seq-to-seq models severely lack the ability to compositionally…

The web-scale of pretraining data has created an important evaluation challenge: to disentangle linguistic competence on cases well-represented in pretraining data from generalization to out-of-domain language, specifically the dynamic,…

Generating structural query language (SQL) queries from natural language is a long-standing open problem. Answering a natural language question about a database table requires modeling complex interactions between the columns of the table…

This thesis explores challenges in semantic parsing, specifically focusing on scenarios with limited data and computational resources. It offers solutions using techniques like automatic data curation, knowledge transfer, active learning,…

While sequence-to-sequence models have shown remarkable generalization power across several natural language tasks, their construct of solutions are argued to be less compositional than human-like generalization. In this paper, we present…

With the recent explosion in the size and complexity of source codebases and software projects, the need for efficient source code search engines has increased dramatically. Unfortunately, existing information retrieval-based methods fail…

Synthetic data generation has recently emerged as a promising approach for enhancing the capabilities of large language models (LLMs) without the need for expensive human annotations. However, existing methods often generate data that can…

We present a cross-lingual summarisation corpus with long documents in a source language associated with multi-sentence summaries in a target language. The corpus covers twelve language pairs and directions for four European languages,…

Structured knowledge bases (KBs) are a foundation of many intelligent applications, yet are notoriously incomplete. Language models (LMs) have recently been proposed for unsupervised knowledge base completion (KBC), yet, despite encouraging…