• Publications
  • Influence
ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars
TLDR
This work explores an in-situ processing approach, where memristor crossbar arrays not only store input weights, but are also used to perform dot-product operations in an analog manner. Expand
DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning
TLDR
DeepLog, a deep neural network model utilizing Long Short-Term Memory (LSTM), is proposed, to model a system log as a natural language sequence, which allows DeepLog to automatically learn log patterns from normal execution, and detect anomalies when log patterns deviate from the model trained from log data under normal execution. Expand
Importance of Semantic Representation: Dataless Classification
TLDR
This paper introduces Dataless Classification, a learning protocol that uses world knowledge to induce classifiers without the need for any labeled data, and proposes a model for dataless classification and shows that the label name alone is often sufficient to induceclassifiers. Expand
Modeling Biological Processes for Reading Comprehension
TLDR
This paper focuses on a new reading comprehension task that requires complex reasoning over a single document, and demonstrates that answering questions via predicted structures substantially improves accuracy over baselines that use shallower representations. Expand
Discriminative Learning over Constrained Latent Representations
TLDR
A novel joint learning algorithm for both NLP decision problems, that uses the final prediction to guide the selection of the best intermediate representation, is developed. Expand
An NLP Curator (or: How I Learned to Stop Worrying and Love NLP Pipelines)
TLDR
Curator, an NLP management framework designed to address some common problems and inefficiencies associated with building NLP process pipelines; and Edison, a NLP data structure library in Java that provides streamlined interactions with Curator and offers a range of useful supporting functionality. Expand
Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension
TLDR
A flexible visualization library for creating customized visual analytic environments, in which the user can investigate and interrogate the relationships among the input, the model internals, and the output predictions, which in turn shed light on the model decision-making process. Expand
A Hierarchy with, of, and for Preposition Supersenses
TLDR
This paper proposes a general-purpose, broadcoverage taxonomy of preposition functions that they are called supersenses: these are coarse and unlexicalized so as to be tractable for efficient manual annotation, yet capture crucial semantic distinctions. Expand
A Logic-Driven Framework for Consistency of Neural Models
TLDR
This paper proposes a learning framework for constraining models using logic rules to regularize them away from inconsistency, and instantiate it on natural language inference, where experiments show that enforcing invariants stated in logic can help make the predictions of neural models both accurate and consistent. Expand
Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes
TLDR
This paper addresses the problem of providing real-time guidance to therapists with a dialogue observer that categorizes therapist and client MI behavioral codes and forecasts codes for upcoming utterances to help guide the conversation and potentially alert the therapist. Expand
...
1
2
3
4
5
...