Unsupervised opinion summarization aims to generate concise summaries which capture vital opinions from online reviews without any ground truth labels. However, most approaches suffer from the hallucination problem, generating inaccurate content. ...

Display Omitted

• This marks the debut of adversarial framework in unsupervised opinion summarization.
• Retrain the NLI module via unsupervised contrastive learning without annotations.
• M2A outperforms some of SOTA in terms of faithfulness of ...

The abductive natural language inference task (αNLI) is proposed to infer the most plausible explanation between the cause and the event. In the αNLI task, two observations are given, and the most plausible hypothesis is asked to pick out from ...

• For αNLI task, we regroup instead of ranking all hypotheses.
• We design a softmax focal loss for each group and combine them into a joint loss.
• we design an information interaction layer that increases the AUC by about 5%.

With the prevalence of social media platforms, rumors have been a serious social problem. Notably, existing rumor detection methods simply provide detection labels while ignoring their explanation. However, illustrating the reasons why a ...

This paper presents a practical approach to develop an aspect-based opinion mining system for a low-resource language. Our design aims to harness the strengths of rule-based model and transformer-based model to accurately extract fine grained named ...

Recently, research on inference methods has been actively conducted to use language models more effectively for studying natural language understanding. Inference in language models that use bidirectional encoder representations from transformers ...

• Most natural language inference using BERT uses CLS tokens.
• Inference using CLS tokens has proven effective in most NLU tasks.
• Leveraging the knowledge acquired when the language model is pretrained is important.
• The effective ...

Online customer advocacy has developed as a distinctive strategic way to improve organisational performance by fostering favourable reciprocal affinitive customer behaviours between the business and its customers. Intelligent systems that can ...

The recent advance of large language models (LLMs) demonstrates that these large-scale foundation models achieve remarkable capabilities across a wide range of language tasks and domains. The success of the statistical learning approach challenges ...

Precise semantic representation is important for allowing machines to truly comprehend the meaning of natural language text, especially biomedical literature. Although the semantic relations among words in a single sentence may be accurately ...

• A graph-based framework for structured semantic representation is proposed.
• FSSR uses Constructs and six types rules to model semantics and semantic relations.
• FSSR connects Constructs by rules to build a directed graph.
• FSSR ...

Fact verification is a challenging task that requires retrieving evidence from a corpus and verifying claims. This paper proposes Co-attention Networks with Graph Transformer (CNGT), a novel end-to-end reasoning framework for fact verification. ...

In this paper, we examine several methods of acquiring Czech data for automated fact-checking, which is a task commonly modeled as a classification of textual claim veracity w.r.t. a corpus of trusted ground truths. We attempt to collect sets of ...

Effective learning schemes such as fine-tuning, zero-shot, and few-shot learning, have been widely used to obtain considerable performance with only a handful of annotated training data. In this paper, we presented a unified benchmark ...

• A unified benchmark for zero-shot Turkish text classification task.
• Monolingual ...

SOPalign is a tool designed for hospitals and other healthcare providers in the Netherlands to automatically estimate the compliance of internal standard operating procedures (SOPs) for employees with the national guidelines. In this tool, users ...

The goal of aspect-category sentiment analysis (ACSA) is to predict the sentiment polarity toward a specific aspect category from reviewers’ expressed opinions in a sentence. With the boom of pretrained language models, various ...

Natural language inference (NLI) is an increasingly important task of natural language processing, and the explainable NLI generates natural language explanations (NLEs) in addition to label prediction, to make NLI explainable and acceptable. ...

Aspect category detection (ACD) aims to identify the aspect categories from reviewers’ expressed opinions in a given sentence, where one or multiple predefined aspect categories are mentioned explicitly or implicitly. With the boom of the ...

Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and model interpretability. Adversarial training (AT) for attention ...

The goal of natural language inference (NLI) is to judge the logical relationship between sentence pairs, including entailment, contradiction, and neutral. At present, many researchers have shown that the introduction of external ...

Sentence pair modeling is a fundamental yet challenging issue for feature mining in natural language processing (NLP) tasks. Recently, most works have generated feature and sentence representation based on the interactive attention ...

Our society produces and shares overwhelming amounts of information through Online Social Networks (OSNs). Within this environment, misinformation and disinformation have proliferated, becoming a public safety concern in most ...

Fake news detection is a challenging problem in online social media, with considerable social and political impacts. Several methods have already been proposed for the automatic detection of fake news, which are often based on the statistical ...