Search Results for author:
Found 57 papers, 32 papers with code
Boundary-Seeking Generative Adversarial Networks
We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
Twin Networks: Matching the Future for Sequence Generation
We propose a simple technique for encouraging generative RNNs to plan ahead.
Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
In this work, we present a simple, effective multi-task learning framework for sentence representations that combines the inductive biases of diverse training objectives in a single model.
Ranked #1 on
Semantic Textual Similarity
on SentEval
Learning deep representations by mutual information estimation and maximization
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder.
Iterative Alternating Neural Attention for Machine Reading
We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document.
Ranked #3 on
Question Answering
on Children's Book Test
(Accuracy-NE metric)
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions.
Machine Comprehension by Text-to-Text Neural Question Generation
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers.
One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases
With both previous and new evaluation metrics, our model outperforms strong baselines on all datasets.
Does Order Matter? An Empirical Study on Generating Multiple Keyphrases as a Sequence
Recently, concatenating multiple keyphrases as a target sequence has been proposed as a new learning paradigm for keyphrase generation.
An Empirical Study on Neural Keyphrase Generation
Recent years have seen a flourishing of neural keyphrase generation (KPG) works, including the release of several large-scale datasets and a host of new models to tackle them.
Plan, Attend, Generate: Planning for Sequence-to-Sequence Models
We investigate the integration of a planning mechanism into sequence-to-sequence models using attention.
Plan, Attend, Generate: Character-level Neural Machine Translation with Planning in the Decoder
We investigate the integration of a planning mechanism into an encoder-decoder architecture with an explicit alignment for character-level machine translation.
An Empirical Study of Example Forgetting during Deep Neural Network Learning
Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks.
Joint Prompt Optimization of Stacked LLMs using Variational Inference
Thus, they can be seen as stochastic language layers in a language network, where the learnable parameters are the natural language prompts at each layer.
NewsQA: A Machine Comprehension Dataset
We present NewsQA, a challenging machine comprehension dataset of over 100, 000 human-generated question-answer pairs.
Exploring and Predicting Transferability across NLP Tasks
We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task, and we validate their effectiveness in experiments controlled for source and target data size.
Interactive Language Learning by Question Answering
In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions.
FigureQA: An Annotated Figure Dataset for Visual Reasoning
To resolve, such questions often require reference to multiple plot elements and synthesis of information distributed spatially throughout a figure.
Ranked #3 on
Visual Question Answering (VQA)
on FigureQA - test 1
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Playing text-based games requires skills in processing natural language and sequential decision making.
Counting to Explore and Generalize in Text-based Games
We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments.
A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data
The parallel hierarchy enables our model to compare the passage, question, and answer from a variety of trainable perspectives, as opposed to using a manually designed, rigid feature set.
Ranked #1 on
Question Answering
on MCTest-160
Interactive Machine Comprehension with Information Seeking Agents
Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA).
Role-Wise Data Augmentation for Knowledge Distillation
To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated.
Think Before You Act: Decision Transformers with Internal Working Memory
We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training.
Building Dynamic Knowledge Graphs from Text-based Games
We are interested in learning how to update Knowledge Graphs (KG) from text.
Modeling Event Plausibility with Consistent Conceptual Abstraction
Understanding natural language requires common sense, one aspect of which is the ability to discern the plausibility of events.
The Knowref Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution
To explain this performance gap, we show empirically that state-of-the art models often fail to capture context, instead relying on the gender or number of candidate antecedents to make a decision.
How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG
Recent studies have significantly improved the state-of-the-art on common-sense reasoning (CSR) benchmarks like the Winograd Schema Challenge (WSC) and SWAG.
Ranked #36 on
Coreference Resolution
on Winograd Schema Challenge
On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT
In particular, we demonstrate through a simple consistency probe that the ability to correctly retrieve hypernyms in cloze tasks, as used in prior work, does not correspond to systematic knowledge in BERT.
TextWorld: A Learning Environment for Text-based Games
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games.
The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources in Natural Language Understanding Systems
In this work, we propose a test suite of coreference resolution subtasks that require reasoning over multiple facts.
Focused Hierarchical RNNs for Conditional Sequence Processing
We evaluate this method on several types of tasks with different attributes.
Ranked #3 on
Open-Domain Question Answering
on SearchQA
(Unigram Acc metric)
Neural Models for Key Phrase Detection and Question Generation
We propose a two-stage neural model to tackle question generation from documents.
Rapid Adaptation with Conditionally Shifted Neurons
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons.
Variational Bi-LSTMs
Bidirectional LSTMs (Bi-LSTMs) on the other hand model sequences along both forward and backward directions and are generally known to perform better at such tasks because they capture a richer representation of the data.
Learning Algorithms for Active Learning
We introduce a model that learns active learning algorithms via metalearning.
A Joint Model for Question Answering and Question Generation
We propose a generative machine comprehension model that learns jointly to ask and answer questions based on documents.
Towards Information-Seeking Agents
We develop a general problem setting for training and testing the ability of agents to gather information efficiently.
Natural Language Comprehension with the EpiReader
We present the EpiReader, a novel model for machine comprehension of text.
Ranked #7 on
Question Answering
on Children's Book Test
Synthesis of recurrent neural networks for dynamical system simulation
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task.
Metalearning with Hebbian Fast Weights
We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning.
A Knowledge Hunting Framework for Common Sense Reasoning
We introduce an automatic system that achieves state-of-the-art results on the Winograd Schema Challenge (WSC), a common sense reasoning task that requires diverse, complex forms of inference and knowledge.
Ranked #65 on
Coreference Resolution
on Winograd Schema Challenge
Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
We harness and extend a recently proposed machine reading comprehension (MRC) model to query for entity states, since these states are generally communicated in spans of text and MRC models perform well in extracting entity-centric spans.
Ranked #3 on
Procedural Text Understanding
on ProPara
A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge
We introduce an automatic system that performs well on two common-sense reasoning tasks, the Winograd Schema Challenge (WSC) and the Choice of Plausible Alternatives (COPA).
Neural Models for Key Phrase Extraction and Question Generation
We propose a two-stage neural model to tackle question generation from documents.
Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning
We investigate the integration of a planning mechanism into an encoder-decoder architecture with attention.
Towards Text Generation with Adversarially Learned Neural Outlines
We generate outlines with an adversarial model trained to approximate the distribution of sentences in a latent space induced by general-purpose sentence encoders.
Boundary Seeking GANs
We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
A Study of State Aliasing in Structured Prediction with RNNs
We show through extensive experiments and analysis that, when trained with policy gradient, recurrent neural networks often fail to learn a state representation that leads to an optimal policy in settings where the same action should be taken at different states.
Metalearned Neural Memory
We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning.
Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning
In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training, to inject language models with structured knowledge via learning from raw text.
BUTLER: Building Understanding in TextWorld via Language for Embodied Reasoning
ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions.
An Analysis of Dataset Overlap on Winograd-Style Tasks
The Winograd Schema Challenge (WSC) and variants inspired by it have become important benchmarks for common-sense reasoning (CSR).
ADEPT: An Adjective-Dependent Plausibility Task
A false contract is more likely to be rejected than a contract is, yet a false key is less likely than a key to open doors.
Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications
There are many ways to express similar things in text, which makes evaluating natural language generation (NLG) systems difficult.
Investigating Failures to Generalize for Coreference Resolution Models
We investigate the extent to which errors of current coreference resolution models are associated with existing differences in operationalization across datasets (OntoNotes, PreCo, and Winogrande).
Responsible AI Considerations in Text Summarization Research: A Review of Current Practices
We focus on how, which, and when responsible AI issues are covered, which relevant stakeholders are considered, and mismatches between stated and realized research goals.
