相关论文: Towards Analysing Invoices and Receipts with Amazo…
From social networks to P2P systems, network sampling arises in many settings. We present a detailed study on the nature of biases in network sampling strategies to shed light on how best to sample from networks. We investigate connections…
This paper explores the realm of abstractive text summarization through the lens of the SEASON (Salience Allocation as Guidance for Abstractive SummarizatiON) technique, a model designed to enhance summarization by leveraging salience…
Ensuring factual consistency is crucial for natural language generation tasks, particularly in abstractive summarization, where preserving the integrity of information is paramount. Prior works on evaluating factual consistency of…
This project aims to build an elastic web application that can automatically scale out and scale in on-demand and cost-effectively by utilizing cloud resources, specifically from Amazon Web Services (AWS). The application is an image…
To provide a survey on the existing tasks and models in Machine Reading Comprehension (MRC), this report reviews: 1) the dataset collection and performance evaluation of some representative simple-reasoning and complex-reasoning MRC tasks;…
Events of various kinds are mentioned and discussed in text documents, whether they are books, news articles, blogs or microblog feeds. The paper starts by giving an overview of how events are treated in linguistics and philosophy. We…
Speech samples recorded in both indoor and outdoor environments are often contaminated with secondary audio sources. Most end-to-end monaural speech recognition systems either remove these background sounds using speech enhancement or train…
Aspect-based sentiment classification (ASC) is an important task in fine-grained sentiment analysis.~Deep supervised ASC approaches typically model this task as a pair-wise classification task that takes an aspect and a sentence containing…
This document is an evaluation of the original "Rank-N-Contrast" (arXiv:2210.01189v2) paper published in 2023. This evaluation is done for academic purposes. Deep regression models often fail to capture the continuous nature of sample…
The Reception Reader is a web tool for studying text reuse in the Early English Books Online (EEBO-TCP) and Eighteenth Century Collections Online (ECCO) data. Users can: 1) explore a visual overview of the reception of a work, or its…
This project investigates factors that influence the perceived helpfulness of Amazon product reviews through machine learning techniques. After extensive feature analysis and correlation testing, we identified key metadata characteristics…
Dark patterns are ubiquitous in digital systems, impacting users throughout their journeys on many popular apps and websites. While substantial efforts from the research community in the last five years have led to consolidated taxonomies…
We provide a literature review about Automatic Text Summarization (ATS) systems. We consider a citation-based approach. We start with some popular and well-known papers that we have in hand about each topic we want to cover and we have…
For assessing various performance indicators of companies, the focus is shifting from strictly financial (quantitative) publicly disclosed information to qualitative (textual) information. This textual data can provide valuable weak…
Exploratory analysis of a text corpus is essential for assessing data quality and developing meaningful hypotheses. Text analysis relies on understanding documents through structured attributes spanning various granularities of the…
The increasing use of automated translation quality estimation (QE) systems calls for practical, decision-oriented methods for evaluating their performance. We propose that Receiver Operating Characteristic (ROC) analysis is a useful…
We propose an end-to-end trainable network that can simultaneously detect and recognize text of arbitrary shape, making substantial progress on the open problem of reading scene text of irregular shape. We formulate arbitrary shape text…
Reasoning-acting frameworks enhance large language models (LLMs) by interleaving reasoning with actions for dynamic information acquisition. However, extending this paradigm to graph learning remains underexplored. Graph data is inherently…
Web services represent a system with a huge number of units and many various and complex interactions. Complex networks as a tool for modelling and analyzing natural environments seem to be well adapted to such a complex system. To describe…
Reviews of products or services on Internet marketplace websites contain a rich amount of information. Users often wish to survey reviews or review snippets from the perspective of a certain aspect, which has resulted in a large body of…