Searcharxiv⌕ Search

arXiv subjects

Natalia Vanetik

Publications and source records attributed to Natalia Vanetik.

10 recordsLinked to original sources
arXiv2024

Improving Factual Error Correction for Abstractive Summarization via Data Distillation and Conditional-generation Cloze

Improving factual consistency in abstractive summarization has been a focus of current research. One promising approach is the post-editing method. However, previous works have yet to make sufficient use of factual factors in summaries and suffers from the negative effect of the training datasets. In this paper, we first propose a novel factual error correction model FactCloze based on a conditional-generation cloze task. FactCloze can construct the causality among factual factors while being able to determine whether the blank can be answered or not. Then, we propose a data distillation method to generate a more faithful summarization dataset SummDSC via multiple-dimensional evaluation. We experimentally validate the effectiveness of our approach, which leads to an improvement in multiple factual consistency metrics compared to baselines.

cs.CL↗
arXiv2023

Just ClozE! A Novel Framework for Evaluating the Factual Consistency Faster in Abstractive Summarization

The issue of factual consistency in abstractive summarization has received extensive attention in recent years, and the evaluation of factual consistency between summary and document has become an important and urgent task. Most of the current evaluation metrics are adopted from the question answering (QA) or natural language inference (NLI) task. However, the application of QA-based metrics is extremely time-consuming in practice while NLI-based metrics are lack of interpretability. In this paper, we propose a cloze-based evaluation framework called ClozE and show the great potential of the cloze-based metric. It inherits strong interpretability from QA, while maintaining the speed of NLI- level reasoning. We demonstrate that ClozE can reduce the evaluation time by nearly 96% relative to QA-based metrics while retaining their interpretability and performance through experiments on six human-annotated datasets and a meta-evaluation benchmark GO FIGURE (Gabriel et al., 2021). Finally, we discuss three important facets of ClozE in practice, which further shows better overall performance of ClozE compared to other metrics.

cs.CL↗
arXiv2021

Subjective Bias in Abstractive Summarization

Due to the subjectivity of the summarization, it is a good practice to have more than one gold summary for each training document. However, many modern large-scale abstractive summarization datasets have only one-to-one samples written by different human with different styles. The impact of this phenomenon is understudied. We formulate the differences among possible multiple expressions summarizing the same content as subjective bias and examine the role of this bias in the context of abstractive summarization. In this paper a lightweight and effective method to extract the feature embeddings of subjective styles is proposed. Results of summarization models trained on style-clustered datasets show that there are certain types of styles that lead to better convergence, abstraction and generalization. The reproducible code and generated summaries are available online.

cs.CL↗
arXiv2020

Automated Discovery of Mathematical Definitions in Text with Deep Neural Networks

Automatic definition extraction from texts is an important task that has numerous applications in several natural language processing fields such as summarization, analysis of scientific texts, automatic taxonomy generation, ontology generation, concept identification, and question answering. For definitions that are contained within a single sentence, this problem can be viewed as a binary classification of sentences into definitions and non-definitions. In this paper, we focus on automatic detection of one-sentence definitions in mathematical texts, which are difficult to separate from surrounding text. We experiment with several data representations, which include sentence syntactic structure and word embeddings, and apply deep learning methods such as the Convolutional Neural Network (CNN) and the Long Short-Term Memory network (LSTM), in order to identify mathematical definitions. Our experiments demonstrate the superiority of CNN and its combination with LSTM, when applied on the syntactically-enriched input representation. We also present a new dataset for definition extraction from mathematical texts. We demonstrate that this dataset is beneficial for training supervised models aimed at extraction of mathematical definitions. Our experiments with different domains demonstrate that mathematical definitions require special treatment, and that using cross-domain learning is inefficient for that task.

cs.CL↗
arXiv2020

The classification problem for graphs and lattices is wild

We prove that the classification problem for graphs and several types of algebraic lattices (distributive, congruence and modular) up to isomorphism contains the classification problem for pairs of matrices up to simultaneous similarity.

math.CO↗
arXiv2020

In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes

Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently. Despite these models provide high ROUGE scores, they are limited to generate comprehensive summaries with a high level of abstraction due to its degenerated attention distribution. We introduce Diverse Convolutional Seq2Seq Model(DivCNN Seq2Seq) using Determinantal Point Processes methods(Micro DPPs and Macro DPPs) to produce attention distribution considering both quality and diversity. Without breaking the end to end architecture, DivCNN Seq2Seq achieves a higher level of comprehensiveness compared to vanilla models and strong baselines. All the reproducible codes and datasets are available online.

cs.CL↗
arXiv2014

On Borel complexity of the isomorphism problems for graph-related classes of Lie algebras and finite p-groups

We reduce the isomorphism problem for undirected graphs without loops to the isomorphism problems for a class of finite dimensional $2$-step nilpotent Lie algebras over a field and for a class of finite $p$-groups. We show that the isomorphism problem for graphs is harder than the two latter isomorphism problems in the sense of Borel reducibility. A computable analogue of Borel reducibility was introduced by S. Coskey, J.D. Hamkins, and R. Miller. A relation of the isomorphism problem for undirected graphs to the well-known problem of classifying pairs of matrices over a field (up to similarity) is also studied.

math.GR↗
arXiv2010

On connection between division sequences and presentations of a free group

This paper describes a simple method for estimating lower bounds on the number of classes of equivalence for a special kind of integer sequences, called division sequences. The method is based on adding group structure to classes of equivalence and studying properties of resulting groups as presentations of free group.

math.CO↗