Related papers: LSBert: A Simple Framework for Lexical Simplificat…
The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…
As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in context of the document. Recent successful…
Text simplification systems generate versions of texts that are easier to understand for a broader audience. The quality of simplified texts is generally estimated using metrics that compare to human references, which can be difficult to…
Reverse dictionary is the task to find the proper target word given the word description. In this paper, we tried to incorporate BERT into this task. However, since BERT is based on the byte-pair-encoding (BPE) subword encoding, it is…
In this paper, we present our approach for the CLEF 2025 SimpleText Task 1, which addresses both sentence-level and document-level scientific text simplification. For sentence-level simplification, our methodology employs large language…
Long document classification poses challenges due to the computational limitations of transformer-based models, particularly BERT, which are constrained by fixed input lengths and quadratic attention complexity. Moreover, using the full…
Multi-level sentence simplification generates simplified sentences with varying language proficiency levels. We propose Label Confidence Weighted Learning (LCWL), a novel approach that incorporates a label confidence weighting scheme in the…
Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…
Estimation of semantic similarity is an important research problem both in natural language processing and the natural language understanding, and that has tremendous application on various downstream tasks such as question answering,…
We aim to highlight an interesting trend to contribute to the ongoing debate around advances within legal Natural Language Processing. Recently, the focus for most legal text classification tasks has shifted towards large pre-trained deep…
Existing search engines use keyword matching or tf-idf based matching to map the query to the web-documents and rank them. They also consider other factors such as page rank, hubs-and-authority scores, knowledge graphs to make the results…
BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks. However, a major blocking issue of applying BERT to online services is…
Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…
We propose edit operation based lexically constrained decoding for sentence simplification. In sentence simplification, lexical paraphrasing is one of the primary procedures for rewriting complex sentences into simpler correspondences.…
Sememes are minimum semantic units of concepts in human languages, such that each word sense is composed of one or multiple sememes. Words are usually manually annotated with their sememes by linguists, and form linguistic common-sense…
We propose a new uniform framework for text classification and ranking that can automate the process of identifying check-worthy sentences in political debates and speech transcripts. Our framework combines the semantic analysis of the…
Training learnable metrics using modern language models has recently emerged as a promising method for the automatic evaluation of machine translation. However, existing human evaluation datasets for text simplification have limited…
Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However,…
Lexicon information and pre-trained models, such as BERT, have been combined to explore Chinese sequence labelling tasks due to their respective strengths. However, existing methods solely fuse lexicon features via a shallow and random…
Recent advances in natural language processing (NLP) have been driven bypretrained language models like BERT, RoBERTa, T5, and GPT. Thesemodels excel at understanding complex texts, but biomedical literature, withits domain-specific…