1 code implementation • NeurIPS 2021 • Petar Stojanov, Zijian Li, Mingming Gong, Ruichu Cai, Jaime Carbonell, Kun Zhang
We provide reasoning why when the supports of the source and target data from overlap, any map of $X$ that is fixed across domains may not be suitable for domain adaptation via invariant features.
no code implementations • EMNLP 2020 • ZiRui Wang, Sanket Vaibhav Mehta, Barnabás Póczos, Jaime Carbonell
State-of-the-art lifelong language learning methods store past examples in episodic memory and replay them at both training and inference time.
1 code implementation • ACL 2020 • Shruti Rijhwani, Shuyan Zhou, Graham Neubig, Jaime Carbonell
However, designing such features for low-resource languages is challenging, because exhaustive entity gazetteers do not exist in these languages.
1 code implementation • TACL 2020 • Shuyan Zhou, Shruti Rijhawani, John Wieting, Jaime Carbonell, Graham Neubig
Cross-lingual entity linking (XEL) is the task of finding referents in a target-language knowledge base (KB) for mentions extracted from source-language texts.
1 code implementation • EACL 2021 • Vidhisha Balachandran, Artidoro Pagnoni, Jay Yoon Lee, Dheeraj Rajagopal, Jaime Carbonell, Yulia Tsvetkov
To this end, we propose incorporating latent and explicit dependencies across sentences in the source document into end-to-end single-document summarization models.
1 code implementation • ICML 2020 • Xinyi Wang, Hieu Pham, Paul Michel, Antonios Anastasopoulos, Jaime Carbonell, Graham Neubig
To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems.
2 code implementations • ICLR 2020 • Zirui Wang, Jiateng Xie, Ruochen Xu, Yiming Yang, Graham Neubig, Jaime Carbonell
Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks.
1 code implementation • IJCNLP 2019 • Harsh Jhamtani, Sanket Vaibhav Mehta, Jaime Carbonell, Taylor Berg-Kirkpatrick
Existing recurrent neural language models often fail to capture higher-level structure present in text: for example, rhyming patterns present in poetry.
26 code implementations • NeurIPS 2019 • Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling.
Ranked #1 on Question Answering on SQuAD2.0 dev
2 code implementations • ACL 2019 • Junjie Hu, Mengzhou Xia, Graham Neubig, Jaime Carbonell
It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift.
no code implementations • ICLR 2019 • Zihang Dai*, Zhilin Yang*, Yiming Yang, William W. Cohen, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov
Moreover, Transformer-XL is up to 1, 800+ times faster than vanilla Transformer during evaluation.
no code implementations • 24 Feb 2019 • Aditi Chaudhary, Siddharth Dalmia, Junjie Hu, Xinjian Li, Austin Matthews, Aldrian Obaja Muis, Naoki Otani, Shruti Rijhwani, Zaid Sheikh, Nidhi Vyas, Xinyi Wang, Jiateng Xie, Ruochen Xu, Chunting Zhou, Peter J. Jansen, Yiming Yang, Lori Levin, Florian Metze, Teruko Mitamura, David R. Mortensen, Graham Neubig, Eduard Hovy, Alan W. black, Jaime Carbonell, Graham V. Horwood, Shabnam Tafreshi, Mona Diab, Efsun S. Kayi, Noura Farra, Kathleen McKeown
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).
37 code implementations • ACL 2019 • Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov
Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling.
Ranked #4 on Language Modelling on One Billion Word
no code implementations • CVPR 2019 • Zirui Wang, Zihang Dai, Barnabás Póczos, Jaime Carbonell
When labeled data is scarce for a specific target task, transfer learning often offers an effective solution by utilizing data from a related source task.
1 code implementation • 9 Nov 2018 • Shruti Rijhwani, Jiateng Xie, Graham Neubig, Jaime Carbonell
To address this problem, we investigate zero-shot cross-lingual entity linking, in which we assume no bilingual lexical resources are available in the source low-resource language.
no code implementations • EMNLP 2018 • Jesse Dunietz, Jaime Carbonell, Lori Levin
This paper introduces the surface construction labeling (SCL) task, which expands the coverage of Shallow Semantic Parsing (SSP) to include frames triggered by complex constructions.
1 code implementation • EMNLP 2018 • Jiateng Xie, Zhilin Yang, Graham Neubig, Noah A. Smith, Jaime Carbonell
To improve robustness to word order differences, we propose to use self-attention, which allows for a degree of flexibility with respect to word order.
no code implementations • EMNLP 2018 • Sanket Vaibhav Mehta, Jay Yoon Lee, Jaime Carbonell
The paper proposes a semi-supervised semantic role labeling method that outperforms the state-of-the-art in limited SRL training corpora.
no code implementations • 6 Jul 2018 • Zirui Wang, Jaime Carbonell
Multi-source transfer learning has been proven effective when within-target labeled data is scarce.
no code implementations • ICLR 2018 • Keerthiram Murugesan, Jaime Carbonell
Lifelong learning poses considerable challenges in terms of effectiveness (minimizing prediction errors for all tasks) and overall computational tractability for real-time performance.
no code implementations • NeurIPS 2017 • Keerthiram Murugesan, Jaime Carbonell
This paper addresses the challenge of learning from peers in an online multitask setting.
1 code implementation • 20 Nov 2017 • Guoqing Zheng, Yiming Yang, Jaime Carbonell
However, freely enriching the family of variational distribution is challenging since the ELBO requires variational likelihood evaluations of the latent variables.
1 code implementation • ICLR 2018 • Guoqing Zheng, Yiming Yang, Jaime Carbonell
Variational inference provides one way to approximate the posterior distribution, however its expressive power is limited and so is the accuracy of resulting approximation.
no code implementations • 26 Jul 2017 • Jay Yoon Lee, Sanket Vaibhav Mehta, Michael Wick, Jean-Baptiste Tristan, Jaime Carbonell
Practitioners apply neural networks to increasingly complex problems in natural language processing, such as syntactic parsing and semantic role labeling that have rich output structures.
2 code implementations • ICLR 2018 • Adams Wei Yu, Lei Huang, Qihang Lin, Ruslan Salakhutdinov, Jaime Carbonell
In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization.
1 code implementation • WS 2017 • Jesse Dunietz, Lori Levin, Jaime Carbonell
Language of cause and effect captures an essential component of the semantics of a text.
no code implementations • 3 Mar 2017 • Keerthiram Murugesan, Jaime Carbonell, Yiming Yang
This paper presents a new multitask learning framework that learns a shared representation among the tasks, incorporating both task and feature clusters.
no code implementations • 2 Mar 2017 • Keerthiram Murugesan, Jaime Carbonell
This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning.
no code implementations • TACL 2017 • Jesse Dunietz, Lori Levin, Jaime Carbonell
Semantic parsing becomes difficult in the face of the wide variety of linguistic realizations that causation can take on.
no code implementations • NeurIPS 2016 • Keerthiram Murugesan, Hanxiao Liu, Jaime Carbonell, Yiming Yang
This paper addresses the challenge of jointly learning both the per-task model parameters and the inter-task relationships in a multi-task online learning setting.
no code implementations • COLING 2016 • Andrew Hsi, Yiming Yang, Jaime Carbonell, Ruochen Xu
Event extraction has become one of the most important topics in information extraction, but to date, there is very limited work on leveraging cross-lingual training to boost performance.
no code implementations • 10 Nov 2016 • Keerthiram Murugesan, Jaime Carbonell
The problem is formulated as a regularization-based approach called \textit{Multi-Task Multiple Kernel Relationship Learning} (\textit{MK-MTRL}), which models the task relationship matrix from the weights learned from latent feature spaces of task-specific base kernels.
no code implementations • 6 Aug 2015 • Luís Marujo, José Portêlo, Wang Ling, David Martins de Matos, João P. Neto, Anatole Gershman, Jaime Carbonell, Isabel Trancoso, Bhiksha Raj
State-of-the-art extractive multi-document summarization systems are usually designed without any concern about privacy issues, meaning that all documents are open to third parties.
no code implementations • SEMEVAL 2015 • Luís Marujo, Ricardo Ribeiro, David Martins de Matos, João P. Neto, Anatole Gershman, Jaime Carbonell
The increasing amount of online content motivated the development of multi-document summarization methods.
no code implementations • 20 May 2015 • Liu Yang, Steve Hanneke, Jaime Carbonell
We study the optimal rates of convergence for estimating a prior distribution over a VC class from a sequence of independent data sets respectively labeled by independent target functions sampled from the prior.
no code implementations • NeurIPS 2014 • Adams Wei Yu, Wanli Ma, YaoLiang Yu, Jaime Carbonell, Suvrit Sra
We study the problem of finding structured low-rank matrices using nuclear norm regularization where the structure is encoded by a linear map.
no code implementations • LREC 2014 • Lori Levin, Teruko Mitamura, Brian MacWhinney, Davida Fromm, Jaime Carbonell, Weston Feely, Robert Frederking, Anatole Gershman, Carlos Ramirez
The extraction rules operate on the output of a dependency parser and identify the grammatical configurations (such as a verb with a prepositional phrase complement) that are likely to contain conventional metaphors.
no code implementations • 24 Mar 2014 • Luís Marujo, Anatole Gershman, Jaime Carbonell, João P. Neto, David Martins de Matos
Event classification at sentence level is an important Information Extraction task with applications in several NLP, IR, and personalization systems.
no code implementations • 23 Dec 2013 • Luis Marujo, Anatole Gershman, Jaime Carbonell, David Martins de Matos, João P. Neto
In this work, we propose two stochastic architectural models (CMC and CMC-M) with two layers of classifiers applicable to datasets with one and multiple skewed classes.
no code implementations • NeurIPS 2013 • Liu Yang, Jaime Carbonell
We additionally study the total cost sufficient for learning, for an abstract notion of the cost of requesting the labels of a given number of examples at once.
no code implementations • COLING 2012 • Luis Marujo, Wang Ling, Anatole Gershman, Jaime Carbonell, João P. Neto, David Matos
We extend the concept of Named Entities to Named Events - commonly occurring events such as battles and earthquakes.
no code implementations • 20 Jun 2013 • Luis Marujo, Ricardo Ribeiro, David Martins de Matos, João P. Neto, Anatole Gershman, Jaime Carbonell
Key phrases are often used to index the document or as features in further processing.
1 code implementation • LREC 2012 • Luis Marujo, Anatole Gershman, Jaime Carbonell, Robert Frederking, João P. Neto
We also experimented with 2 forms of document pre-processing that we call light filtering and co-reference normalization.