Zobrazeno 1 - 10
of 670
pro vyhledávání: '"Verspoor Karin"'
Autor:
Shehzad, Ahsan, Xia, Feng, Abid, Shagufta, Peng, Ciyuan, Yu, Shuo, Zhang, Dongyu, Verspoor, Karin
Graph transformers are a recent advancement in machine learning, offering a new class of neural network models for graph-structured data. The synergy between transformers and graph learning demonstrates strong performance and versatility across vario
Externí odkaz:
http://arxiv.org/abs/2407.09777
In this work, we measure the impact of affixal negation on modern English large language models (LLMs). In affixal negation, the negated meaning is expressed through a negative morpheme, which is potentially challenging for LLMs as their tokenizers a
Externí odkaz:
http://arxiv.org/abs/2404.02421
Publikováno v:
2023 IEEE International Conference on Data Mining Workshops (ICDMW), December 1-4, 2023, Shanghai, China
Knowledge graphs (KGs) have garnered significant attention for their vast potential across diverse domains. However, the issue of outdated facts poses a challenge to KGs, affecting their overall quality as real-world information evolves. Existing sol
Externí odkaz:
http://arxiv.org/abs/2402.03732
The NLP community typically relies on performance of a model on a held-out test set to assess generalization. Performance drops observed in datasets outside of official test sets are generally attributed to "out-of-distribution" effects. Here, we exp
Externí odkaz:
http://arxiv.org/abs/2311.03663
BERT-based models have had strong performance on leaderboards, yet have been demonstrably worse in real-world settings requiring generalization. Limited quantities of training data is considered a key impediment to achieving generalizability in machi
Externí odkaz:
http://arxiv.org/abs/2310.08008
Publikováno v:
TACL Submission batch: 7/2022; Revision batch: 1/2023; Published 2023
Despite the subjective nature of semantic textual similarity (STS) and pervasive disagreements in STS annotation, existing benchmarks have used averaged human ratings as the gold standard. Averaging masks the true distribution of human opinions on ex
Externí odkaz:
http://arxiv.org/abs/2308.04114
Negation has been shown to be a major bottleneck for masked language models, such as BERT. However, whether this finding still holds for larger-sized auto-regressive language models (``LLMs'') has not been studied comprehensively. With the ever-incre
Externí odkaz:
http://arxiv.org/abs/2306.08189
Modeling text-based time-series to make prediction about a future event or outcome is an important task with a wide range of applications. The standard approach is to train and test the model using the same input window, but this approach neglects th
Externí odkaz:
http://arxiv.org/abs/2301.10887
Autor:
Truong, Thinh Hung, Otmakhova, Yulia, Baldwin, Timothy, Cohn, Trevor, Lau, Jey Han, Verspoor, Karin
Negation is poorly captured by current language models, although the extent of this problem is not widely understood. We introduce a natural language inference (NLI) test suite to enable probing the capabilities of NLP methods, with the aim of unders
Externí odkaz:
http://arxiv.org/abs/2210.03256
Autor:
Otmakhova, Yulia, Truong, Hung Thinh, Baldwin, Timothy, Cohn, Trevor, Verspoor, Karin, Lau, Jey Han
In this paper we report on our submission to the Multidocument Summarisation for Literature Review (MSLR) shared task. Specifically, we adapt PRIMERA (Xiao et al., 2022) to the biomedical domain by placing global attention on important biomedical ent
Externí odkaz:
http://arxiv.org/abs/2209.08698