Related papers: Probing Representations for Document-level Event E…

Expert search aims to find and rank experts based on a user's query. In academia, retrieving experts is an efficient way to navigate through a large amount of academic knowledge. Here, we study how different distributed representations of…

Large language models (LLMs) can perform a new task by merely conditioning on task instructions and a few input-output examples, without optimizing any parameters. This is called In-Context Learning (ICL). In-context Information Extraction…

Neural approaches to learning term embeddings have led to improved computation of similarity and ranking in information retrieval (IR). So far neural representation learning has not been extended to meta-textual information that is readily…

Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or…

The ability to identify and control different kinds of linguistic information encoded in vector representations of words has many use cases, especially for explainability and bias removal. This is usually done via a set of simple…

Language provides speakers with a rich system of modality for expressing thoughts about events, without being committed to their actual occurrence. Modality is commonly used in the political news domain, where both actual and possible…

Deep Learning and Machine Learning based models have become extremely popular in text processing and information retrieval. However, the non-linear structures present inside the networks make these models largely inscrutable. A significant…

Manually labelling large collections of text data is a time-consuming, expensive, and laborious task, but one that is necessary to support machine learning based on text datasets. Active learning has been shown to be an effective way to…

Document-level multi-event extraction aims to extract the structural information from a given document automatically. Most recent approaches usually involve two steps: (1) modeling entity interactions; (2) decoding entity interactions into…

The work presented in this master thesis consists of extracting a set of events from texts written in natural language. For this purpose, we have based ourselves on the basic notions of the information extraction as well as the open…

Text classification is crucial for applications such as sentiment analysis and toxic text filtering, but it still faces challenges due to the complexity and ambiguity of natural language. Recent advancements in deep learning, particularly…

Word embeddings are one of the most useful tools in any modern natural language processing expert's toolkit. They contain various types of information about each word which makes them the best way to represent the terms in any NLP task. But…

This position paper argues that text embedding research should move beyond surface meaning and embrace implicit semantics as a central modeling objective. Text embeddings are a foundational component of modern NLP, underpinning a wide range…

Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods either focus on input-oriented feature extraction, such as supervised…

Large language models (LLMs) based on Transformer have been widely applied in the filed of natural language processing (NLP), demonstrating strong performance, particularly in handling short text tasks. However, when it comes to long…

Vector-based word representations help countless Natural Language Processing (NLP) tasks capture the language's semantic and syntactic regularities. In this paper, we present the characteristics of existing word embedding approaches and…

Large language models (LLMs) are trained on enormous amounts of data and encode knowledge in their parameters. We propose a pipeline to elicit causal relationships from LLMs. Specifically, (i) we sample many documents from LLMs on a given…

Event extraction (EE) is a critical direction in the field of information extraction, laying an important foundation for the construction of structured knowledge bases. EE from text has received ample research and attention for years, yet…

Information extraction (IE) for visually-rich documents (VRDs) has achieved SOTA performance recently thanks to the adaptation of Transformer-based language models, which shows the great potential of pre-training methods. In this paper, we…

While contextualized word representations have improved state-of-the-art benchmarks in many NLP tasks, their potential usefulness for social-oriented tasks remains largely unexplored. We show how contextualized word embeddings can be used…