Search Results for author:
Found 14 papers, 3 papers with code
Team Papelo at FEVEROUS: Multi-hop Evidence Pursuit
We develop a system for the FEVEROUS fact extraction and verification task that ranks an initial set of potential evidence and then pursues missing evidence in subsequent hops by trying to generate it, with a “next hop prediction module” whose output is matched against page elements in a predicted article.
Analyzing Coreference and Bridging in Product Reviews
Product reviews may have complex discourse including coreference and bridging relations to a main product, competing products, and interacting products.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training.
Self-Consistent Decoding for More Factual Open Responses
We compare this "Sample & Select" method to greedy decoding, beam search, nucleus sampling, and the recently introduced hallucination avoiding decoders of DoLA, P-CRR, and S-CRR.
Automatically Evaluating Opinion Prevalence in Opinion Summarization
Finally, we show that preprocessing source reviews by simplification can raise the opinion prevalence achieved by existing abstractive opinion summarization systems to the level of human performance.
KGxBoard: Explainable and Interactive Leaderboard for Evaluation of Knowledge Graph Completion Models
Knowledge Graphs (KGs) store information in the form of (head, predicate, tail)-triples.
Fast Few-shot Debugging for NLU Test Suites
We study few-shot debugging of transformer based natural language understanding models, using recently popularized test suites to not just diagnose but correct a problem.
Overcoming Poor Word Embeddings with Word Definitions
Modern natural language understanding models depend on pretrained subword embeddings, but applications may need to reason about words that were never or rarely seen during pretraining.
Natural Language Inference
Natural Language Understanding
+1
Improving Neural Network Robustness through Neighborhood Preserving Layers
Finally, we empirically show that our designed network architecture is more robust against state-of-art gradient descent based attacks, such as a PGD attack on the benchmark datasets MNIST and CIFAR10.
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance
Learning disentangled representations of natural language is essential for many NLP tasks, e. g., conditional text generation, style transfer, personalized dialogue systems, etc.
Generating Followup Questions for Interpretable Multi-hop Question Answering
As a first instantiation of this framework, we train a pointer-generator network to predict followup questions based on the question and partial information.
Team Papelo: Transformer Networks at FEVER
We develop a system for the FEVER fact extraction and verification challenge that uses a high precision entailment classifier based on transformer networks pretrained with language modeling, to classify a broad set of potential evidence.
Teaching Syntax by Adversarial Distraction
Existing entailment datasets mainly pose problems which can be answered without attention to grammar or word order.
