Advanced Integration of Discrete Line Segments in Digitized P&ID for Continuous Instrument Connectivity

Piping and Instrumentation Diagrams (P&IDs) constitute the foundational blueprint of a plant, depicting the interconnections among process equipment, instrumentation for process control, and the flow of fluids and control signals. In their existing setup, the manual mapping of information from P&ID sheets holds a significant challenge. This is a time-consuming process, taking around 3-6 months, and is susceptible to errors. It also depends on the expertise of the domain experts and often requires multiple rounds of review. The digitization of P&IDs entails merging detected line segments, which is essential for linking various detected instruments, thereby creating a comprehensive digitized P&ID. This paper focuses on explaining how line segments which are detected using a computer vision model are merged and eventually building the connection between equipment and merged lines. Hence presenting a digitized form of information stating the interconnection between process equipment, instrumentation, flow of fluids and control signals. Eventually, which can be stored in a knowledge graph and that information along with the help of advanced algorithms can be leveraged for tasks like finding optimal routes, detecting system cycles, computing transitive closures, and more.

Named Entity Recognition in Indian court judgments

Identification of named entities from legal texts is an essential building block for developing other legal Artificial Intelligence applications. Named Entities in legal texts are slightly different and more fine-grained than commonly used named entities like Person, Organization, Location etc. In this paper, we introduce a new corpus of 46545 annotated legal named entities mapped to 14 legal entity types. The Baseline model for extracting legal named entities from judgment text is also developed.

Corpus for Automatic Structuring of Legal Documents

In populous countries, pending legal cases have been growing exponentially. There is a need for developing techniques for processing and organizing legal documents. In this paper, we introduce a new corpus for structuring legal documents. In particular, we introduce a corpus of legal judgment documents in English that are segmented into topical and coherent parts. Each of these parts is annotated with a label coming from a list of pre-defined Rhetorical Roles. We develop baseline models for automatically predicting rhetorical roles in a legal document based on the annotated corpus. Further, we show the application of rhetorical roles to improve performance on the tasks of summarization and legal judgment prediction. We release the corpus and baseline model code along with the paper.