With the rapid growth of social network services, misinformation has spread uncontrollably. Most recent approaches to fake news detection use neural network models to predict whether the input text is fake or real. Some of them even provide explanations, in addition to veracity, generated by Large Language Models (LLMs). However, they do not utilize factual evidence, nor do they allude to it or provide evidence/justification, thereby making their predictions less credible. This paper proposes a new fake news detection method that predicts the truth or false-hood of a claim based on relevant factual evidence (if exists) or LLM’s inference mechanisms (such as common-sense reasoning) otherwise. Our method produces the final synthesized prediction, along with well-founded facts or reasoning. Experimental results on several large COVID-19 fake news datasets show that our method achieves state-of-the-art (SOTA) detection and evidence explanation performance. Our source codes are available online.

We present an AI dietitian chatbot that generates factually accurate and empathetic responses. The system employs an agentic AI architecture and incorporates a nutrition database and two Large Language Models (LLMs), one of which is fine-tuned with natural doctor-patient conversations. A preliminary evaluation is performed using an LLM-as-a-judge approach, where the system’s responses are evaluated against a baseline model with regard to factual consistency and empathy. Preliminary results show much improved retrieval consistency and empathy in our responses compared to the baseline model.

Aspect-category-based sentiment analysis (ACSA), which aims to identify aspect categories and predict their sentiments has been intensively studied due to its wide range of NLP applications. Most approaches mainly utilize intrasentential features. However, a review often includes multiple different aspect categories, and some of them do not explicitly appear in the review. Even in a sentence, there is more than one aspect category with its sentiments, and they are entangled intra-sentence, which makes the model fail to discriminately preserve all sentiment characteristics. In this paper, we propose an enhanced coherence-aware network with hierarchical disentanglement (ECAN) for ACSA tasks. Specifically, we explore coherence modeling to capture the contexts across the whole review and to help the implicit aspect and sentiment identification. To address the issue of multiple aspect categories and sentiment entanglement, we propose a hierarchical disentanglement module to extract distinct categories and sentiment features. Extensive experimental and visualization results show that our ECAN effectively decouples multiple categories and sentiments entangled in the coherence representations and achieves state-of-the-art (SOTA) performance. Our codes and data are available online: https://github.com/cuijin-23/ECAN.

When customers purchase a product or sign up for service from a company, they often are required to agree to a Privacy Policy or Terms of Service agreement. Many of these policies are lengthy, and a typical customer agrees to them without reading them carefully if at all. To address this problem, we have developed a prototype automatic text summarization system which is specifically designed for privacy policies. Our system generates a summary of a policy statement by identifying important sentences from the statement, categorizing these sentences by which of 5 "statement categories" the sentence addresses, and displaying to a user a list of the sentences which match each category. Our system incorporates keywords identified by a human domain expert and rules that were obtained by machine learning, and they are combined in an ensemble architecture. We have tested our system on a sample corpus of privacy statements, and preliminary results are promising.

Information in visually rich formats such as PDF and HTML is often conveyed by a combination of textual and visual features. In particular, genres such as marketing flyers and info-graphics often augment textual information by its color, size, positioning, etc. As a result, tradi-tional text-based approaches to informa-tion extraction (IE) could underperform. In this study, we present a supervised ma-chine learning approach to IE from on-line commercial real estate flyers. We evaluated the performance of SVM clas-sifiers on the task of identifying 12 types

Shieber's abstract parsing algorithm (Shieber 1992) for unification grammars is an extension of Earley's algorithm (Earley 1970) for context-free grammars to feature structures. In this paper, we show that, under certain conditions, Shieber's algorithm produces what we call a nonminimal derivation: a parse tree which contains additional features that are not in the licensing productions. While Shieber's definition of parse tree allows for such nonminimal derivations, we claim that they should be viewed as invalid. We describe the sources of the nonminimal derivation problem, and propose a precise definition of minimal parse tree, as well as a modification to Shieber's algorithm which ensures minimality, although at some computational cost.

A left-corner parsing algorithm with topdown filtering has been reported to show very efficient performance for unification-based systems. However, due to the nontermination of parsing with left-recursive grammars, top-down constraints must be weakened. In this paper, a general method of maximizng top-down constraints is proposed. The method provides a procedure to dynamically compute restrictor, a minimum set of features involved in an infinite loop for every propagation path; thus top-down constraints are maximally propagated.