Search Results for author:
Found 46 papers, 19 papers with code
Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and Texture
Current state-of-the-art methods fail to generate realistic animation from any speech on unknown faces due to their poor gen-eralization over different facial characteristics, languages, and accents.
Exploiting Unfair Advantages: Investigating Opportunistic Trading in the NFT Market
Yet, there are sophisticated actors who turn their domain knowledge and market inefficiencies to their strategic advantage; thus extracting value from trades not accessible to others.
SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation
In this work, we introduce SEAHORSE, a dataset for multilingual, multifaceted summarization evaluation.
Text-Blueprint: An Interactive Platform for Plan-based Conditional Generation
While conditional generation models can now generate natural language well enough to create fluent text, it is still difficult to control the generation process, leading to irrelevant, repetitive, and hallucinated content.
Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models
We take human annotations as a gold standard and show that a correlated automatic metric is suitable for development.
QAmeleon: Multilingual QA with Only 5 Examples
The availability of large, high-quality datasets has been one of the main drivers of recent progress in question answering (QA).
Query Refinement Prompts for Closed-Book Long-Form Question Answering
Large language models (LLMs) have been shown to perform well in answering questions and in producing long-form texts, both in few-shot closed-book settings.
Language Models are Multilingual Chain-of-Thought Reasoners
Finally, we show that the multilingual reasoning abilities of language models extend to other tasks such as commonsense reasoning and word-in-context semantic judgment.
Conditional Generation with a Question-Answering Blueprint
The ability to convey relevant and faithful information is critical for many tasks in conditional generation and yet remains elusive for neural seq-to-seq models whose outputs often reveal hallucinations and fail to correctly cover important details.
A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation
We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies.
Measuring Attribution in Natural Language Generation Models
With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world.
Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features
At training time, additional inputs based on these evaluation measures are given to the dialogue model.
The MultiBERTs: BERT Reproductions for Robustness Analysis
Experiments with pre-trained models such as BERT are often based on a single checkpoint.
Decontextualization: Making Sentences Stand-Alone
Models for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context and use that meaning in a new context.
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics.
Ranked #1 on
Extreme Summarization
on GEM-XSum
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+5
Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task
The quality of machine translation systems has dramatically improved over the last decade, and as a result, evaluation has become an increasingly challenging problem.
Variational Clustering: Leveraging Variational Autoencoders for Image Clustering
Since we wish to efficiently discriminate between different clusters in the data, we propose a method based on VAEs where we use a Gaussian Mixture prior to help cluster the images accurately.
ToTTo: A Controlled Table-To-Text Generation Dataset
We present ToTTo, an open-domain English table-to-text dataset with over 120, 000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description.
Ranked #3 on
Data-to-Text Generation
on ToTTo
Syntactic Data Augmentation Increases Robustness to Inference Heuristics
Pretrained neural models such as BERT, when fine-tuned to perform natural language inference (NLI), often show high accuracy on standard datasets, but display a surprising lack of sensitivity to word order on controlled challenge sets.
BLEURT: Learning Robust Metrics for Text Generation
We propose BLEURT, a learned evaluation metric based on BERT that can model human judgments with a few thousand possibly biased training examples.
Handling Divergent Reference Texts when Evaluating Table-to-Text Generation
Automatically constructed datasets for generating text from semi-structured data (tables), such as WikiBio, often contain reference texts that diverge from the information in the corresponding semi-structured data.
What do you learn from context? Probing for sentence structure in contextualized word representations
The jiant toolkit for general-purpose text understanding models
BERT Rediscovers the Classical NLP Pipeline
Pre-trained text encoders have rapidly advanced the state of the art on many NLP tasks.
Text Generation with Exemplar-based Adaptive Decoding
We propose a novel conditioned text generation model.
Deep Representation Learning Characterized by Inter-class Separation for Image Clustering
Despite significant advances in clustering methods in recent years, the outcome of clustering of a natural image dataset is still unsatisfactory due to two important drawbacks.
Epipolar Geometry based Learning of Multi-view Depth and Ego-Motion from Monocular Sequences
The proposed method results in better depth images and pose estimates, which capture the scene structure and motion in a better way.
Identifying Well-formed Natural Language Questions
Understanding search queries is a hard problem as it involves dealing with "word salad" text ubiquitously issued by users.
Ranked #1 on
Query Wellformedness
on Query Wellformedness
Learning To Split and Rephrase From Wikipedia Edit History
Split and rephrase is the task of breaking down a sentence into shorter ones that together convey the same meaning.
WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse
We release a corpus of 43 million atomic edits across 8 languages.
Neural Paraphrase Identification of Questions with Noisy Pretraining
We present a solution to the problem of paraphrase identification of questions.
Learning Recurrent Span Representations for Extractive Question Answering
In this paper, we focus on this answer extraction task, presenting a novel model architecture that efficiently builds fixed length representations of all spans in the evidence document with a recurrent network.
Ranked #43 on
Question Answering
on SQuAD1.1 dev
A Decomposable Attention Model for Natural Language Inference
We propose a simple neural architecture for natural language inference.
Ranked #48 on
Natural Language Inference
on SNLI
Transforming Dependency Structures to Logical Forms for Semantic Parsing
In contrast{---}partly due to the lack of a strong type system{---}dependency structures are easy to annotate and have become a widely used form of syntactic analysis for many languages.
Efficient Inference and Structured Learning for Semantic Role Labeling
We present a dynamic programming algorithm for efficient constrained inference in semantic role labeling.
Token and Type Constraints for Cross-Lingual Part-of-Speech Tagging
We consider the construction of part-of-speech taggers for resource-poor languages.
A Universal Part-of-Speech Tagset
To facilitate future research in unsupervised induction of syntactic structure and to standardize best-practices, we propose a tagset that consists of twelve universal part-of-speech categories.
