Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Nicholas Monath"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:7788-7796
Clustering algorithms are often evaluated using metrics which compare with ground-truth cluster assignments, such as Rand index and NMI. Algorithm performance may vary widely for different hyperparameters, however, and thus model selection based on o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::73707f246cb17bbf41b0fc03d00eeccb
https://doi.org/10.1609/aaai.v36i7.20747
https://doi.org/10.1609/aaai.v36i7.20747
Publikováno v:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1f7ee357d42407b13c93d93f2cfac8d
https://doi.org/10.18653/v1/2022.naacl-main.343
https://doi.org/10.18653/v1/2022.naacl-main.343
We study algorithms for approximating pairwise similarity matrices that arise in natural language processing. Generally, computing a similarity matrix for $n$ data points requires $\Omega(n^2)$ similarity computations. This quadratic scaling is a sig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2423772c85ca3d5a5953388e240662d9
http://arxiv.org/abs/2112.09631
http://arxiv.org/abs/2112.09631
Autor:
Mert Terzihan, Yuan Wang, Bryon Tjanaka, Manzil Zaheer, Avinava Dubey, Gokhan Mergen, Marc Najork, Yuchen Wu, Amr Ahmed, Andrew McCallum, Guru Guruganesh, Nicholas Monath
Publikováno v:
Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.
The applicability of agglomerative clustering, for inferring both hierarchical and flat clustering, is limited by its scalability. Existing scalable hierarchical clustering methods sacrifice quality for speed and often lead to over-merging of cluster
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ebbe6956e11da592de2d62449f1730ff
https://doi.org/10.1145/3447548.3467404
https://doi.org/10.1145/3447548.3467404
Publikováno v:
BCB
Tools to explore scientific literature are essential for scientists, especially in biomedicine, where about a million new papers are published every year. Many such tools provide users the ability to search for specific entities (e.g. proteins, disea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ea472abfe636fcb478dc3307feccc82c
https://doi.org/10.1145/3459930.3469524
https://doi.org/10.1145/3459930.3469524
Autor:
Manzil Zaheer, Andrew McCallum, Kumar Shridhar, Mrinmaya Sachan, Nicholas Monath, Raghuveer Thirukovalluru
Publikováno v:
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
ACL/IJCNLP (Findings)
ACL/IJCNLP (Findings)
State of the art end-to-end coreference resolution models use expensive span representations and antecedent prediction mechanisms. These approaches are expensive both in terms of their memory requirements as well as compute time, and are particularly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::56ebb625c54183deaf993c1bab1c20b1
Autor:
Shruti Chanumolu, Dung Thai, Sankaranarayanan Ananthakrishnan, Mukund Sridhar, Nicholas Monath, Andrew McCallum, Raghuveer Thirukovalluru
Publikováno v:
Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021).
Smart assistants are tasked to answer various questions regarding world knowledge. These questions range from retrieval of simple facts to retrieval of complex, multi-hops question followed by various operators (i.e., filter, argmax). Semantic parsin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd6d9f13a39c44eb6e283e8ffc328276
https://doi.org/10.18653/v1/2021.repl4nlp-1.24
https://doi.org/10.18653/v1/2021.repl4nlp-1.24
Publikováno v:
NAACL-HLT
Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates entity linking models which are able to link mentions of unseen entities using learned repre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c402048b3307bc095bbc4bef72e4c0f
https://doi.org/10.18653/v1/2021.naacl-main.205
https://doi.org/10.18653/v1/2021.naacl-main.205
Publikováno v:
Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9bc147b295b66480f8f8538f4b7b7316
https://doi.org/10.18653/v1/2021.crac-1.11
https://doi.org/10.18653/v1/2021.crac-1.11
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2020.
A case-based reasoning (CBR) system solves a new problem by retrieving `cases' that are similar to the given problem. If such a system can achieve high accuracy, it is appealing owing to its simplicity, interpretability, and scalability. In this pape
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::615bb8c993f518c828dacd78a426fb49
https://doi.org/10.18653/v1/2020.findings-emnlp.427
https://doi.org/10.18653/v1/2020.findings-emnlp.427