In this work, we explore the relevance of textual semantics to Large Language Models (LLMs), extending previous insights into the connection between distributional semantics and structural semantics. We investigate whether LLM-generated texts preserve semantic isotopies. We design a story continuation experiment using 10,000 ROCStories prompts completed by five LLMs. We first validate GPT-4o's ability to extract isotopies from a linguistic benchmark, then apply it to the generated stories. We then analyze structural (coverage, density, spread) and semantic properties of isotopies to assess how they are affected by completion. Results show that LLM completion within a given token horizon preserves semantic isotopies across multiple properties.

Existing cross-document event coreference resolution models, which either compute mention similarity directly or enhance mention representation by extracting event arguments (such as location, time, agent, and patient), lacking the ability to utilize document-level information. As a result, they struggle to capture long-distance dependencies. This shortcoming leads to their underwhelming performance in determining coreference for the events where their argument information relies on long-distance dependencies. In light of these limitations, we propose the construction of document-level Rhetorical Structure Theory (RST) trees and cross-document Lexical Chains to model the structural and semantic information of documents. Subsequently, cross-document heterogeneous graphs are constructed and GAT is utilized to learn the representations of events. Finally, a pair scorer calculates the similarity between each pair of events and co-referred events can be recognized using standard clustering algorithm. Additionally, as the existing cross-document event coreference datasets are limited to English, we have developed a large-scale Chinese cross-document event coreference dataset to fill this gap, which comprises 53,066 event mentions and 4,476 clusters. After applying our model on the English and Chinese datasets respectively, it outperforms all baselines by large margins.

The relationship between words in a sentence often tells us more about the underlying semantic content of a document than its actual words, individually. In this work, we propose two novel algorithms, called Flexible Lexical Chain II and Fixed Lexical Chain II. These algorithms combine the semantic relations derived from lexical chains, prior knowledge from lexical databases, and the robustness of the distributional hypothesis in word embeddings as building blocks forming a single system. In short, our approach has three main contributions: (i) a set of techniques that fully integrate word embeddings and lexical chains; (ii) a more robust semantic representation that considers the latent relation between words in a document; and (iii) lightweight word embeddings models that can be extended to any natural language task. We intend to assess the knowledge of pre-trained models to evaluate their robustness in the document classification task. The proposed techniques are tested against seven word embeddings algorithms using five different machine learning classifiers over six scenarios in the document classification task. Our results show the integration between lexical chains and word embeddings representations sustain state-of-the-art results, even against more complex systems.

This paper presents a new approach of automatic text summarization which combines domain oriented text analysis (DoTA) and rhetorical structure theory (RST) in a grammar form: the attributed rhetorical structure grammar (ARSG), where the non-terminal symbols are domain keywords, called domain relations, while the rhetorical relations serve as attributes. We developed machine learning algorithms for learning such a grammar from a corpus of sample domain texts, as well as parsing algorithms for the learned grammar, together with adjustable text summarization algorithms for generating domain specific summaries. Our practical experiments have shown that with support of domain knowledge the drawback of missing very large training data set can be effectively compensated. We have also shown that the knowledge based approach may be made more powerful by introducing grammar parsing and RST as inference engine. For checking the feasibility of model transfer, we introduced a technique for mapping a grammar from one domain to others with acceptable cost. We have also made a comprehensive comparison of our approach with some others.

Lexical chains between two concepts are sequences of semantically related words interconnected via semantic relations. This paper presents a new approach for the automatic construction of lexical chains on knowledge bases. Experiments were performed building lexical chains on WordNet, Extended WordNet, and Extended WordNet Knowledge Base. The research addresses the problems of lexical chains ranking and labeling them with appropriate semantic names.

Associations between people and other concepts are common in text and range from distant to close connections. This paper discusses and justifies the need to consider subtypes of the generic relation ASSOCIATION. Semantic primitives are used as a concise and formal way of specifying the key semantic differences between subtypes. A taxonomy of association relations is proposed, and a method based on composing previously extracted relations is used to extract subtypes. Experimental results show high precision and moderate recall.