Related papers: Temporal expression normalisation in natural langu…

Determining temporal relations (e.g., before or after) between events has been a challenging natural language understanding task, partly due to the difficulty to generate large amounts of high-quality training data. Consequently, neural…

Question answering in temporal knowledge graphs requires retrieval that is both time-consistent and efficient. Existing RAG methods are largely semantic and typically neglect explicit temporal constraints, which leads to time-inconsistent…

Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is…

Literary texts are usually rich in meanings and their interpretation complicates corpus studies and automatic processing. There have been several attempts to create collections of literary texts with annotation of literary elements like the…

Semantic relation extraction is one of the frontiers of biomedical natural language processing research. Gold standards are key tools for advancing this research. It is challenging to generate these standards because of the high cost of…

In this paper, we explore the task of automatically generating natural language descriptions of salient patterns in a time series, such as stock prices of a company over a week. A model for this task should be able to extract high-level…

Historic variations of spelling poses a challenge for full-text search or natural language processing on historical digitized texts. To minimize the gap between the historic orthography and contemporary spelling, usually an automatic…

This paper describes a new system for semi-automatically building, extending and managing a terminological thesaurus---a multilingual terminology dictionary enriched with relationships between the terms themselves to form a thesaurus. The…

Recent research has revealed that neural language models at scale suffer from poor temporal generalization capability, i.e., the language model pre-trained on static data from past years performs worse over time on emerging data. Existing…

Accent normalization converts foreign-accented speech into native-like speech while preserving speaker identity. We propose a novel pipeline using self-supervised discrete tokens and non-parallel training data. The system extracts tokens…

Generative Artificial Intelligence (AI) has rapidly become a powerful tool, capable of generating various types of data, such as images and text. However, despite the significant advancement of generative AI, time series generative AI…

Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such information is often not expressed explicitly in text, and human…

We describe a data-driven approach for automatically explaining new, non-standard English expressions in a given sentence, building on a large dataset that includes 15 years of crowdsourced examples from UrbanDictionary.com. Unlike prior…

We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture…

Existing conversational systems are mostly agent-centric, which assumes the user utterances would closely follow the system ontology (for NLU or dialogue state tracking). However, in real-world scenarios, it is highly desirable that the…

We present hinglishNorm -- a human annotated corpus of Hindi-English code-mixed sentences for text normalization task. Each sentence in the corpus is aligned to its corresponding human annotated normalized form. To the best of our…

Handwritten Mathematical Expression Recognition is foundational for educational technologies, enabling applications like digital note-taking and automated grading. While modern encoder-decoder architectures with large language models excel…

Neural networks have recently achieved human-level performance on various challenging natural language processing (NLP) tasks, but it is notoriously difficult to understand why a neural network produced a particular prediction. In this…

Temporal information extraction (IE) aims to extract structured temporal information from unstructured text, thereby uncovering the implicit timelines within. This technique is applied across domains such as healthcare, newswire, and…

In this paper, we propose a hybrid text normalization system using multi-head self-attention. The system combines the advantages of a rule-based model and a neural model for text preprocessing tasks. Previous studies in Mandarin text…