NLP

Evaluating Extrapolation Ability of Large Language Model in Chemical Domain
Solving a problem outside the training space, i.e. extrapolation, has been a long problem in the machine learning community. The …
PDF Cite URL
Exploring Hallucination Types in Question-Answering Generation and Limitation of Text Evaluation Metrics
대형 언어 모델의 생성 텍스트는 환각 현상 때문에 신뢰성 및 안정성 문제가 있다. 질의응답에서의 환각을 판별하기 위해 생성 텍스트 환각을 총 5가지로 분류하는 방식을 제안하고 BLEU, METEOR 그리고 ROUGE …
PDF Cite URL
SentenceLDA: Discriminative and Robust Document Representation with Sentence Level Topic Model
A subtle difference in context results in totally different nuances even for lexically identical words. On the other hand, two words …
PDF Cite URL
SentenceLDA: Discriminative and Robust Document Representation with Sentence Level Topic Model
Aspect-based Dense Passage Retrieval
In information retrieval, traditional models like TF-IDF and BM25 have been used for search engine queries. However, with the rise of …
Cite URL
Aspect-based Dense Passage Retrieval
Predicting U.S. Treasury Yield Curve Shifts with FOMC Statements Using BERT
Cite URL
Predicting U.S. Treasury Yield Curve Shifts with FOMC Statements Using BERT
Noun-MWP: Math Word Problems Meet Noun Answers
We introduce a new type of problems for math word problem (MWP) solvers, named Noun-MWPs, whose answer is a non-numerical string …
PDF Cite URL
Noun-MWP: Math Word Problems Meet Noun Answers