Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths
This paper presents SDP-LSTM, a novel neural network to classify the relation of two entities in a sentence, which leverages the shortest dependency path (SDP) between two entities; multichannel recurrent neural networks, with long short term memory (L STM) units, pick up heterogeneous information along the SDP.
A Convolutional Attention Network for Extreme Summarization of Source Code
An attentional neural network that employs convolution on the input tokens to detect local time-invariant and long-range topical attention features in a context-dependent way to solve the problem of extreme summarization of source code snippets into short, descriptive function name-like summaries is introduced.
Deep Multitask Learning for Semantic Dependency Parsing
We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a…
Discriminative Neural Sentence Modeling by Tree-Based Convolution
This paper proposes a tree-based convolutional neural network (TBCNN) for discriminative sentence modeling that outperforms previous state-of-the-art results, including existing neural networks and dedicated feature/rule engineering.
Random Feature Attention
- Hao Peng, Nikolaos Pappas, Dani Yogatama, Roy Schwartz, Noah A. Smith, Lingpeng Kong
- Computer ScienceICLR
- 3 March 2021
RFA, a linear time and space attention that uses random feature methods to approximate the softmax function, is proposed and explored, showing that RFA is competitive in terms of both accuracy and efficiency on three long text classification datasets.
Contextualized Perturbation for Textual Adversarial Attack
CLARE is a ContextuaLized AdversaRial Example generation model that produces fluent and grammatical outputs through a mask-then-infill procedure that can flexibly combine and apply perturbations at any position in the inputs, and is thus able to attack the victim model more effectively with fewer edits.
Learning Joint Semantic Parsers from Disjoint Data
A new approach to learning a semantic parser from multiple datasets, even when the target semantic formalisms are drastically different and the underlying corpora do not overlap is presented, by treating annotations for unobserved formalisms as latent structured variables.
Text Generation with Exemplar-based Adaptive Decoding
- Hao Peng, Ankur P. Parikh, Manaal Faruqui, Bhuwan Dhingra, Dipanjan Das
- Computer ScienceNAACL
- 9 April 2019
A novel conditioned text generation model that retrieves exemplar text from the training data as “soft templates,” which are then used to construct an exemplar-specific decoder, which achieves strong performance and outperforms comparable baselines.
Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation
The findings suggest that the latency disadvantage for autoregressive translation has been overestimated due to a suboptimal choice of layer allocation, and a new speed-quality baseline for future research toward fast, accurate translation is provided.
Backpropagating through Structured Argmax using a SPIGOT
It is shown that training with SPIGOT leads to a larger improvement on the downstream task than a modularly-trained pipeline, the straight-through estimator, and structured attention, reaching a new state of the art on semantic dependency parsing.