Zobrazeno 1 - 10
of 45
pro vyhledávání: '"ROSS, HAYLEY"'
Inferences from adjective-noun combinations like "Is artificial intelligence still intelligence?" provide a good test bed for LLMs' understanding of meaning and compositional generalization capability, since there are many combinations which are nove
Externí odkaz:
http://arxiv.org/abs/2410.17482
Autor:
Sreenivas, Sharath Turuvekere, Muralidharan, Saurav, Joshi, Raviraj, Chochowski, Marcin, Mahabaleshwarkar, Ameya Sunil, Shen, Gerald, Zeng, Jiaqi, Chen, Zijia, Suhara, Yoshi, Diao, Shizhe, Yu, Chenhan, Chen, Wei-Chun, Ross, Hayley, Olabiyi, Oluwatobi, Aithal, Ashwath, Kuchaiev, Oleksii, Korzekwa, Daniel, Molchanov, Pavlo, Patwary, Mostofa, Shoeybi, Mohammad, Kautz, Jan, Catanzaro, Bryan
We present a comprehensive report on compressing the Llama 3.1 8B and Mistral NeMo 12B models to 4B and 8B parameters, respectively, using pruning and distillation. We explore two distinct pruning strategies: (1) depth pruning and (2) joint hidden/at
Externí odkaz:
http://arxiv.org/abs/2408.11796
Autor:
Min, Bonan, Ross, Hayley, Sulem, Elior, Veyseh, Amir Pouran Ben, Nguyen, Thien Huu, Sainz, Oscar, Agirre, Eneko, Heinz, Ilana, Roth, Dan
Large, pre-trained transformer-based language models such as BERT have drastically changed the Natural Language Processing (NLP) field. We present a survey of recent work that uses these large language models to solve NLP tasks via pre-training then
Externí odkaz:
http://arxiv.org/abs/2111.01243
Extracting temporal relations between events and time expressions has many applications such as constructing event timelines and time-related question answering. It is a challenging problem which requires syntactic and semantic information at sentenc
Externí odkaz:
http://arxiv.org/abs/2004.14577
Autor:
MIN, BONAN1 bonanmin@amazon.com, ROSS, HAYLEY2 hayleyross@g.harvard.edu, SULEM, ELIOR3 eliors@seas.upenn.edu, BEN VEYSEH, AMIR POURAN4 apouran@cs.uoregon.edu, THIEN HUU NGUYEN4 thien@cs.uoregon.edu, SAINZ, OSCAR5 oscar.sainz@ehu.eus, AGIRRE, ENEKO5 e.agirre@ehu.eus, HEINTZ, ILANA6 ilana@synopticengineering.com, ROTH, DAN3 danroth@seas.upenn.edu
Publikováno v:
ACM Computing Surveys. Feb2024, Vol. 56 Issue 2, p1-40. 40p.
Publikováno v:
Healthcare Management Forum; Jul2024, Vol. 37 Issue 4, p237-243, 7p
Autor:
Ross, Hayley1 hayleyross@g.harvard.edu
Publikováno v:
Annual Review of the Faculty of Philosophy / Godisnjak Filozofskog Fakulteta. 2022, Vol. 47 Issue 3, p15-41. 27p.
This experiment is intended to confirm two hypotheses following a pilot study on weak and strong crossover. (1) Each of two experimental designs shows a clear effect between crossover and non-crossover (coreference) readings of the same sentences, an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae5efe749b54a37e26f634ced33ca5e4
This experiment addresses a number of shortcomings in our previous study on weak and strong crossover. In brief, we substantially improve the quality of the stimuli, control for a range of pronouns (singular they vs. masculine vs. feminine) and test
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e60b4c315a048132c9c2f0ca91a028dd
This experiment follows our previous experiments on WH-crossover and tests whether a similar effect occurs when proper names follow pronouns. This 2x2(x2) design crosses linear order (forward/backward anaphora, if anaphora is possible) of the proper
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::199892f1eacaafbe53b463e2d88be4da