Search Results for author:
Found 53 papers, 17 papers with code
Domain Adaptation with Invariant Representation Learning: What Transformations to Learn?
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.
Efficient Meta Lifelong-Learning with Limited Memory
State-of-the-art lifelong language learning methods store past examples in episodic memory and replay them at both training and inference time.
Soft Gazetteers for Low-Resource Named Entity Recognition
However, designing such features for low-resource languages is challenging, because exhaustive entity gazetteers do not exist in these languages.
Improving Candidate Generation for Low-resource Cross-lingual Entity Linking
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.
StructSum: Summarization via Structured Representations
To this end, we propose incorporating latent and explicit dependencies across sentences in the source document into end-to-end single-document summarization models.
Optimizing Data Usage via Differentiable Rewards
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.
Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework
Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks.
Learning Rhyming Constraints using Structured Adversaries
Existing recurrent neural language models often fail to capture higher-level structure present in text: for example, rhyming patterns present in poetry.
XLNet: Generalized Autoregressive Pretraining for Language Understanding
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
Domain Adaptation of Neural Machine Translation by Lexicon Induction
It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift.
Transformer-XL: Language Modeling with Longer-Term Dependency
Moreover, Transformer-XL is up to 1, 800+ times faster than vanilla Transformer during evaluation.
The ARIEL-CMU Systems for LoReHLT18
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).
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling.
Ranked #3 on
Language Modelling
on One Billion Word
Characterizing and Avoiding Negative Transfer
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.
Zero-shot Neural Transfer for Cross-lingual Entity Linking
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.
DeepCx: A transition-based approach for shallow semantic parsing with complex constructional triggers
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.
Neural Cross-Lingual Named Entity Recognition with Minimal Resources
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.
Towards Semi-Supervised Learning for Deep Semantic Role Labeling
The paper proposes a semi-supervised semantic role labeling method that outperforms the state-of-the-art in limited SRL training corpora.
Towards more Reliable Transfer Learning
Multi-source transfer learning has been proven effective when within-target labeled data is scarce.
Lifelong Learning with Output Kernels
Lifelong learning poses considerable challenges in terms of effectiveness (minimizing prediction errors for all tasks) and overall computational tractability for real-time performance.
Active Learning from Peers
This paper addresses the challenge of learning from peers in an online multitask setting.
Asymmetric Variational Autoencoders
However, freely enriching the family of variational distribution is challenging since the ELBO requires variational likelihood evaluations of the latent variables.
Convolutional Normalizing Flows
Variational inference provides one way to approximate the posterior distribution, however its expressive power is limited and so is the accuracy of resulting approximation.
Gradient-based Inference for Networks with Output Constraints
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.
Block-Normalized Gradient Method: An Empirical Study for Training Deep Neural Network
In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization.
The BECauSE Corpus 2.0: Annotating Causality and Overlapping Relations
Language of cause and effect captures an essential component of the semantics of a text.
Co-Clustering for Multitask Learning
This paper presents a new multitask learning framework that learns a shared representation among the tasks, incorporating both task and feature clusters.
Self-Paced Multitask Learning with Shared Knowledge
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.
Automatically Tagging Constructions of Causation and Their Slot-Fillers
Semantic parsing becomes difficult in the face of the wide variety of linguistic realizations that causation can take on.
Adaptive Smoothed Online Multi-Task Learning
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.
Leveraging Multilingual Training for Limited Resource Event Extraction
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.
Multi-Task Multiple Kernel Relationship Learning
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.
Privacy-Preserving Multi-Document Summarization
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.
Extending a Single-Document Summarizer to Multi-Document: a Hierarchical Approach
The increasing amount of online content motivated the development of multi-document summarization methods.
Bounds on the Minimax Rate for Estimating a Prior over a VC Class from Independent Learning Tasks
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.
Efficient Structured Matrix Rank Minimization
We study the problem of finding structured low-rank matrices using nuclear norm regularization where the structure is encoded by a linear map.
Resources for the Detection of Conventionalized Metaphors in Four Languages
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.
Ensemble Detection of Single & Multiple Events at Sentence-Level
Event classification at sentence level is an important Information Extraction task with applications in several NLP, IR, and personalization systems.
Co-Multistage of Multiple Classifiers for Imbalanced Multiclass Learning
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.
Buy-in-Bulk Active Learning
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.
Supervised Topical Key Phrase Extraction of News Stories using Crowdsourcing, Light Filtering and Co-reference Normalization
We also experimented with 2 forms of document pre-processing that we call light filtering and co-reference normalization.
Key Phrase Extraction of Lightly Filtered Broadcast News
Key phrases are often used to index the document or as features in further processing.
Recognition of Named-Event Passages in News Articles
We extend the concept of Named Entities to Named Events - commonly occurring events such as battles and earthquakes.
