Search Results for author:
Found 22 papers, 8 papers with code
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
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
Policy Networks with Two-Stage Training for Dialogue Systems
Indeed, with only a few hundred dialogues collected with a handcrafted policy, the actor-critic deep learner is considerably bootstrapped from a combination of supervised and batch RL.
Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data
Natural language generation plays a critical role in spoken dialogue systems.
A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems
The model takes as input a sequence of dialogue contexts and outputs a sequence of dialogue acts corresponding to user intentions.
NewsQA: A Machine Comprehension Dataset
We present NewsQA, a challenging machine comprehension dataset of over 100, 000 human-generated question-answer pairs.
Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems
We developed this dataset to study the role of memory in goal-oriented dialogue systems.
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).
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
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
Playing log(N)-Questions over Sentences
We propose a two-agent game wherein a questioner must be able to conjure discerning questions between sentences, incorporate responses from an answerer, and keep track of a hypothesis state.
Improving Neural Question Generation using World Knowledge
In this paper, we propose a method for incorporating world knowledge (linked entities and fine-grained entity types) into a neural question generation model.
Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text
Previous work has focused specifically on modeling physical plausibility and shown that distributional methods fail when tested in a supervised setting.
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).
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.
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.
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.
TopiOCQA: Open-domain Conversational Question Answering with Topic Switching
On average, a conversation in our dataset spans 13 question-answer turns and involves four topics (documents).
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.
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.
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).
