Dissecting The Analects: an NLP-based exploration of semantic similarities and differences across English translations Humanities and Social Sciences Communications

By far the most common event types were the first four, all of which involved some sort of change to one or more participants in the event. We developed a basic first-order-logic representation that was consistent with the GL theory of subevent structure and that could be adapted for the various types of change events. We preserved existing semantic predicates where possible, but more fully defined them and their arguments and applied them consistently across classes. In this first stage, we decided on our system of subevent sequencing and developed new predicates to relate them. We also defined our event variable e and the variations that expressed aspect and temporal sequencing.

The data displayed in Table 5 and Attachment 3 underscore significant discrepancies in semantic similarity (values ≤ 80%) among specific sentence pairs across the five translations, with a particular emphasis on variances in word choice. As mentioned earlier, the factors contributing to these differences can be multi-faceted and are worth exploring further. In Table 3, “NO.” refers to the specific sentence identifiers assigned to individual English translations of The Analects from the corpus referenced above. “Translator 1” and “Translator 2” correspond to the respective translators, and their translations undergo a comparative analysis to ascertain semantic concordance. The columns labeled “Word2Vec,” “GloVe,” and “BERT” present outcomes derived from their respective semantic similarity algorithms.

Statistical approach

This study ingeniously integrates natural language processing technology into translation research. The semantic similarity calculation model utilized in this study can also be applied to other types of translated texts. Translators can employ this model to compare their translations degree of similarity with previous translations, an approach that does not necessarily mandate a higher similarity to predecessors. This allows them to better realize the purpose and function of translation while assessing translation quality.

• At first glance, it is hard to understand most terms in the reading materials.
• These tasks require the detection of subtle interactions between participants in events, of sequencing of subevents that are often not explicitly mentioned, and of changes to various participants across an event.
• Like the classic VerbNet representations, we use E to indicate a state that holds throughout an event.
• Second, we followed GL’s principle of using states, processes and transitions, in various combinations, to represent different Aktionsarten.

This visualization aids in identifying the most critical and recurrent themes or concepts within the translations. “Integrating generative lexicon event structures into verbnet,” in Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (Miyazaki), 56–61. Question answering is an NLU task that is increasingly implemented into search, especially search engines that expect natural language searches. Most search engines only have a single content type on which to search at a time. It takes messy data (and natural language can be very messy) and processes it into something that computers can work with.

Research involving human and animal rights

In this post, we’ll cover the basics of natural language processing, dive into some of its techniques and also learn how NLP has benefited from recent advances in deep learning. In addition to substantially revising the representation of subevents, we increased the informativeness of the semantic predicates themselves and improved their consistency across classes. This effort included defining each predicate and its arguments and, where possible, relating them hierarchically in order for users to chose the appropriate level of meaning granularity for their needs. We also strove to connect classes that shared semantic aspects by reusing predicates wherever possible.

All these models aim to provide numerical representations of words that capture their meanings. This study obtains high-resolution PDF versions of the five English translations of The Analects through purchase and download. The first step entailed establishing preprocessing parameters, which included eliminating special symbols, converting capitalized words to lowercase, and sequentially reading the PDF file whilst preserving the English text. Subsequently, this study aligned the cleaned texts of the translations by Lau, Legge, Jennings, Slingerland, and Watson at the sentence level to construct a parallel corpus.

From readers cognitive enhancement perspective, this approach can significantly improve readers’ understanding and reading fluency, thus enhancing reading efficiency. As discussed above, as a broad coverage verb lexicon with detailed syntactic and semantic information, VerbNet has already been used in various NLP tasks, primarily as an aid to semantic role labeling or ensuring broad syntactic coverage for a parser. The richer and more coherent representations described in this article offer opportunities for additional types of downstream applications that focus more on the semantic consequences of an event. However, the clearest demonstration of the coverage and accuracy of the revised semantic representations can be found in the Lexis system (Kazeminejad et al., 2021) described in more detail below.

The brittleness of deep learning systems is revealed in their inability to generalize to new domains and their reliance on massive amounts of data—much more than human beings need—to become fluent in a language. The idea of directly incorporating linguistic knowledge into these systems is being explored in several ways. Our effort to contribute to this goal has been to supply a large repository of semantic representations linked to the syntactic structures and classes of verbs in VerbNet. Although VerbNet has been successfully used in NLP in many ways, its original semantic representations had rarely been incorporated into NLP systems (Zaenen et al., 2008; Narayan-Chen et al., 2017). We have described here our extensive revisions of those representations using the Dynamic Event Model of the Generative Lexicon, which we believe has made them more expressive and potentially more useful for natural language understanding. Another significant change to the semantic representations in GL-VerbNet was overhauling the predicates themselves, including their definitions and argument slots.

search

This representation follows the GL model by breaking down the transition into a process and several states that trace the phases of the event. • Subevents related within a representation for causality, nlp semantics temporal sequence and, where appropriate, aspect. In Classic VerbNet, the semantic form implied that the entire atomic event is caused by an Agent, i.e., cause(Agent, E), as seen in 4.