Related papers: A Zipf's Law-based Text Generation Approach for Ad…
This paper presents a link analysis approach for identifying privileged documents by constructing a network of human entities derived from email header metadata. Entities are classified as either counsel or non-counsel based on a predefined…
Recent neural models for relation extraction with distant supervision alleviate the impact of irrelevant sentences in a bag by learning importance weights for the sentences. Efforts thus far have focused on improving extraction accuracy but…
Table retrieval is essential for accessing information stored in structured tabular formats; however, it remains less explored than text retrieval. The content of the table primarily consists of phrases and words, which include a large…
The main purpose of relation extraction is to extract the semantic relationships between tagged pairs of entities in a sentence, which plays an important role in the semantic understanding of sentences and the construction of knowledge…
We analyze the extent to which internal representations of language models (LMs) identify and distinguish mentions of named entities, focusing on the many-to-many correspondence between entities and their mentions. We first formulate two…
In recent years, the fine-tuned generative models have been proven more powerful than the previous tagging-based or span-based models on named entity recognition (NER) task. It has also been found that the information related to entities,…
Here we present a new class of optimality for coding systems. Members of that class are displaced linearly from optimal coding and thus exhibit Zipf's law, namely a power-law distribution of frequency ranks. Within that class, Zipf's law,…
Beyond generating long and topic-coherent paragraphs in traditional captioning tasks, the medical image report composition task poses more task-oriented challenges by requiring both the highly-accurate medical term diagnosis and multiple…
Knowledge about entities and their interrelations is a crucial factor of success for tasks like question answering or text summarization. Publicly available knowledge graphs like Wikidata or DBpedia are, however, far from being complete. In…
Conditional text generation has been a challenging task that is yet to see human-level performance from state-of-the-art models. In this work, we specifically focus on the Commongen benchmark, wherein the aim is to generate a plausible…
Document subject classification is essential for structuring (digital) libraries and allowing readers to search within a specific field. Currently, the classification is typically made by human domain experts. Semi-supervised Machine…
Named entity linking is to map an ambiguous mention in documents to an entity in a knowledge base. The named entity linking is challenging, given the fact that there are multiple candidate entities for a mention in a document. It is…
The traditional entity extraction problem lies in the ability of extracting named entities from plain text using natural language processing techniques and intensive training from large document collections. Examples of named entities…
We show how generalized Gibbs-Shannon entropies can provide new insights on the statistical properties of texts. The universal distribution of word frequencies (Zipf's law) implies that the generalized entropies, computed at the word level,…
Entities and relationships between entities are vital in the real world. Essentially, we understand the world by understanding entities and relations. For instance, to understand a field, e.g., computer science, we need to understand the…
Entity linking aims to link ambiguous mentions to their corresponding entities in a knowledge base, which is significant and fundamental for various downstream applications, e.g., knowledge base completion, question answering, and…
We study the problem of entity-relation extraction in the presence of symbolic domain knowledge. Such knowledge takes the form of an ontology defining relations and their permissible arguments. Previous approaches set out to integrate such…
The use of methods borrowed from statistics and physics to analyze written texts has allowed the discovery of unprecedent patterns of human behavior and cognition by establishing links between models features and language structure. While…
Zipf's law predicts a power-law relationship between word rank and frequency in language communication systems and has been widely reported in a variety of natural language processing applications. However, the emergence of natural language…
This thesis investigates how natural language understanding and generation with transformer models can benefit from grounding the models with knowledge representations and addresses the following key research questions: (i) Can knowledge of…