
-
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
A key limitation in current datasets for multi-hop reasoning is that the...
read it
-
Few-Shot Question Answering by Pretraining Span Selection
In a number of question answering (QA) benchmarks, pretrained models hav...
read it
-
Transformer Feed-Forward Layers Are Key-Value Memories
Feed-forward layers constitute two-thirds of a transformer model's param...
read it
-
SmBoP: Semi-autoregressive Bottom-up Semantic Parsing
The de-facto standard decoding method for semantic parsing in recent yea...
read it
-
Improving Compositional Generalization in Semantic Parsing
Generalization of models to out-of-distribution (OOD) data has captured ...
read it
-
Learning Object Detection from Captions via Textual Scene Attributes
Object detection is a fundamental task in computer vision, requiring lar...
read it
-
Scene Graph to Image Generation with Contextualized Object Layout Refinement
Generating high-quality images from scene graphs, that is, graphs that d...
read it
-
Span-based Semantic Parsing for Compositional Generalization
Despite the success of sequence-to-sequence (seq2seq) models in semantic...
read it
-
A Simple Global Neural Discourse Parser
Discourse parsing is largely dominated by greedy parsers with manually-d...
read it
-
Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering
Answering questions that involve multi-step reasoning requires decomposi...
read it
-
Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge
To what extent can a neural network systematically reason over symbolic ...
read it
-
GMAT: Global Memory Augmentation for Transformers
Transformer-based models have become ubiquitous in natural language proc...
read it
-
Obtaining Faithful Interpretations from Compositional Neural Networks
Neural module networks (NMNs) are a popular approach for modeling compos...
read it
-
Explaining Question Answering Models through Text Generation
Large pre-trained language models (LMs) have been shown to perform surpr...
read it
-
Injecting Numerical Reasoning Skills into Language Models
Large pre-trained language models (LMs) are known to encode substantial ...
read it
-
Evaluating the Evaluation of Diversity in Natural Language Generation
Despite growing interest in natural language generation (NLG) models tha...
read it
-
Evaluating NLP Models via Contrast Sets
Standard test sets for supervised learning evaluate in-distribution gene...
read it
-
Break It Down: A Question Understanding Benchmark
Understanding natural language questions entails the ability to break do...
read it
-
oLMpics – On what Language Model Pre-training Captures
Recent success of pre-trained language models (LMs) has spurred widespre...
read it
-
On the Limits of Learning to Actively Learn Semantic Representations
One of the goals of natural language understanding is to develop models ...
read it
-
Question Answering is a Format; When is it Useful?
Recent years have seen a dramatic expansion of tasks and datasets posed ...
read it
-
Global Reasoning over Database Structures for Text-to-SQL Parsing
State-of-the-art semantic parsers rely on auto-regressive decoding, emit...
read it
-
Don't paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsing
A major hurdle on the road to conversational interfaces is the difficult...
read it
-
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets
Crowdsourcing has been the prevalent paradigm for creating natural langu...
read it
-
MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension
A large number of reading comprehension (RC) datasets has been created r...
read it
-
Grammar-based Neural Text-to-SQL Generation
The sequence-to-sequence paradigm employed by neural text-to-SQL models ...
read it
-
Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
Research on parsing language to SQL has largely ignored the structure of...
read it
-
White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks
Adversarial examples are important for understanding the behavior of neu...
read it
-
DiscoFuse: A Large-Scale Dataset for Discourse-based Sentence Fusion
Sentence fusion is the task of joining several independent sentences int...
read it
-
Learning Latent Scene-Graph Representations for Referring Relationships
Understanding the semantics of complex visual scenes often requires anal...
read it
-
Neural network gradient-based learning of black-box function interfaces
Deep neural networks work well at approximating complicated functions wh...
read it
-
Value-based Search in Execution Space for Mapping Instructions to Programs
Training models to map natural language instructions to programs given t...
read it
-
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
When answering a question, people often draw upon their rich world knowl...
read it
-
Evaluating Text GANs as Language Models
Generative Adversarial Networks (GANs) are a promising approach for text...
read it
-
Emergence of Communication in an Interactive World with Consistent Speakers
Training agents to communicate with one another given task-based supervi...
read it
-
Explaining Queries over Web Tables to Non-Experts
Designing a reliable natural language (NL) interface for querying tables...
read it
-
Repartitioning of the ComplexWebQuestions Dataset
Recently, Talmor and Berant (2018) introduced ComplexWebQuestions - a da...
read it
-
Memory Augmented Policy Optimization for Program Synthesis with Generalization
This paper presents Memory Augmented Policy Optimization (MAPO): a novel...
read it
-
Learning to Search in Long Documents Using Document Structure
Reading comprehension models are based on recurrent neural networks that...
read it
-
Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing
Building a semantic parser quickly in a new domain is a fundamental chal...
read it
-
Text Segmentation as a Supervised Learning Task
Text segmentation, the task of dividing a document into contiguous segme...
read it
-
Polyglot Semantic Parsing in APIs
Traditional approaches to semantic parsing (SP) work by training individ...
read it
-
The Web as a Knowledge-base for Answering Complex Questions
Answering complex questions is a time-consuming activity for humans that...
read it
-
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
Structured prediction is concerned with predicting multiple inter-depend...
read it
-
Contextualized Word Representations for Reading Comprehension
Reading a document and extracting an answer to a question about its cont...
read it
-
Weakly-supervised Semantic Parsing with Abstract Examples
Semantic parsers translate language utterances to programs, but are ofte...
read it
-
Inducing Regular Grammars Using Recurrent Neural Networks
Grammar induction is the task of learning a grammar from a set of exampl...
read it
-
Evaluating Semantic Parsing against a Simple Web-based Question Answering Model
Semantic parsing shines at analyzing complex natural language that invol...
read it
-
Language Generation with Recurrent Generative Adversarial Networks without Pre-training
Generative Adversarial Networks (GANs) have shown great promise recently...
read it
-
Neural Semantic Parsing over Multiple Knowledge-bases
A fundamental challenge in developing semantic parsers is the paucity of...
read it