2021/07/29 by Ankush Chopra, Chopra, Ankush, Sohom Ghosh +1 · 1 citation
Computer Science · Mathematics · #Advanced Text Analysis Techniques #Artificial intelligence #Computation and Language (cs.CL) #Computer science #FOS: Computer and information sciences #Finance #Information retrieval #Mathematics #Natural Language Processing Techniques #Natural language processing #Noun #Noun phrase #Prospectus #Rank (graph theory) #Ranking (information retrieval) #Semantic similarity #Similarity (geometry) #Synonym (taxonomy) #Task (project management) #Topic Modeling #Transformer #cs.CL
paper · pdf · doi:10.48550/arxiv.2107.13764
published in arXiv (Cornell University) (Cornell University) · Accepted at 3rd Workshop on Financial Technology and Natural Language Processing (FinNLP) in conjunction with 30th International Joint Conference on Artificial Intelligence (IJCAI) 2021
arxiv created 2021/07/29 · openalex publication_date 2021/07/29 · arxiv updated 2021/07/30 · openalex created_date 2021/08/02 · openalex updated_date 2026/07/28
Hypernym and synonym matching are one of the mainstream Natural Language Processing (NLP) tasks. In this paper, we present systems that attempt to solve this problem. We designed these systems to participate in the FinSim-3, a shared task of FinNLP workshop at IJCAI-2021. The shared task is focused on solving this problem for the financial domain. We experimented with various transformer based pre-trained embeddings by fine-tuning these for either classification or phrase similarity tasks. We also augmented the provided dataset with abbreviations derived from prospectus provided by the organizers and definitions of the financial terms from DBpedia [Auer et al., 2007], Investopedia, and the Financial Industry Business Ontology (FIBO). Our best performing system uses both FinBERT [Araci, 2019] and data augmentation from the afore-mentioned sources. We observed that term expansion using data augmentation in conjunction with semantic similarity is beneficial for this task and could be useful for the other tasks that deal with short phrases. Our best performing model (Accuracy: 0.917, Rank: 1.156) was developed by fine-tuning SentenceBERT [Reimers et al., 2019] (with FinBERT at the backend) over an extended labelled set created using the hierarchy of labels present in FIBO.