Search Results for author:
Found 61 papers, 19 papers with code
Unsupervised Cross-Lingual Part-of-Speech Tagging for Truly Low-Resource Scenarios
Our approach innovates in three ways: 1) a robust approach of selecting training instances via cross-lingual annotation projection that exploits best practices of unsupervised type and token constraints, word-alignment confidence and density of projected POS, 2) a Bi-LSTM architecture that uses contextualized word embeddings, affix embeddings and hierarchical Brown clusters, and 3) an evaluation on 12 diverse languages in terms of language family and morphological typology.
Investigating the Effect of Background Knowledge on Natural Questions
We create a subset of the NQ data, Factual Questions (FQ), where the questions have evidence in the KB in the form of paths that link question entities to answer entities but still must be answered using text, to facilitate further research into KB integration methods.
A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains
REVEAL includes comprehensive labels for the relevance, attribution to evidence passages, and logical correctness of each reasoning step in a language model's answer, across a variety of datasets and state-of-the-art language models.
Controlled Decoding from Language Models
KL-regularized reinforcement learning (RL) is a popular alignment framework to control the language model responses towards high reward outcomes.
Language Modelling
Multi-Objective Reinforcement Learning
+1
Learning to Reject with a Fixed Predictor: Application to Decontextualization
We study the problem of classification with a reject option for a fixed predictor, applicable in natural language processing.
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.
Coreference Resolution through a seq2seq Transition-Based System
We obtain state-of-the-art accuracy on the CoNLL-2012 datasets with 83. 3 F1-score for English (a 2. 3 higher F1-score than previous work (Dobrovolskii, 2021)) using only CoNLL data for training, 68. 5 F1-score for Arabic (+4. 1 higher than previous work) and 74. 3 F1-score for Chinese (+5. 3).
Ranked #1 on
Coreference Resolution
on OntoNotes
Towards Computationally Verifiable Semantic Grounding for Language Models
Compared to a baseline that generates text using greedy search, we demonstrate two techniques that improve the fluency and semantic accuracy of the generated text: The first technique samples multiple candidate text sequences from which the semantic parser chooses.
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.
Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization
We present Expected Statistic Regularization (ESR), a novel regularization technique that utilizes low-order multi-task structural statistics to shape model distributions for semi-supervised learning on low-resource datasets.
Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model
But what sorts of rationales are useful and how can we train systems to produce them?
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.
Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss
We study learning named entity recognizers in the presence of missing entity annotations.
On planetary systems as ordered sequences
A planetary system consists of a host star and one or more planets, arranged into a particular configuration.
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.
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
We review the EfficientQA competition from NeurIPS 2020.
Evaluating Explanations: How much do explanations from the teacher aid students?
While many methods purport to explain predictions by highlighting salient features, what aims these explanations serve and how they ought to be evaluated often go unstated.
QED: A Framework and Dataset for Explanations in Question Answering
A question answering system that in addition to providing an answer provides an explanation of the reasoning that leads to that answer has potential advantages in terms of debuggability, extensibility and trust.
Sparse, Dense, and Attentional Representations for Text Retrieval
Dual encoders perform retrieval by encoding documents and queries into dense lowdimensional vectors, scoring each document by its inner product with the query.
TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages
Confidently making progress on multilingual modeling requires challenging, trustworthy evaluations.
Fusion of Detected Objects in Text for Visual Question Answering
To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language.
Synthetic QA Corpora Generation with Roundtrip Consistency
We introduce a novel method of generating synthetic question answering corpora by combining models of question generation and answer extraction, and by filtering the results to ensure roundtrip consistency.
Natural Questions: a Benchmark for Question Answering Research
The public release consists of 307, 373 training examples with single annotations, 7, 830 examples with 5-way annotations for development data, and a further 7, 842 examples 5-way annotated sequestered as test data.
Ranked #7 on
Question Answering
on Natural Questions (long)
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
In this paper we study yes/no questions that are naturally occurring --- meaning that they are generated in unprompted and unconstrained settings.
Ranked #26 on
Question Answering
on BoolQ
Low-Resource Syntactic Transfer with Unsupervised Source Reordering
We describe a cross-lingual transfer method for dependency parsing that takes into account the problem of word order differences between source and target languages.
A BERT Baseline for the Natural Questions
This technical note describes a new baseline for the Natural Questions.
Ranked #6 on
Question Answering
on Natural Questions (long)
Improving Span-based Question Answering Systems with Coarsely Labeled Data
We study approaches to improve fine-grained short answer Question Answering models by integrating coarse-grained data annotated for paragraph-level relevance and show that coarsely annotated data can bring significant performance gains.
Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency
Noise Contrastive Estimation (NCE) is a powerful parameter estimation method for log-linear models, which avoids calculation of the partition function or its derivatives at each training step, a computationally demanding step in many cases.
Ranked #14 on
Question Answering
on WikiQA
Source-Side Left-to-Right or Target-Side Left-to-Right? An Empirical Comparison of Two Phrase-Based Decoding Algorithms
The algorithm produces a translation by processing the source-language sentence in strictly left-to-right order, differing from commonly used approaches that build the target-language sentence in left-to-right order.
SyntaxNet Models for the CoNLL 2017 Shared Task
We describe a baseline dependency parsing system for the CoNLL2017 Shared Task.
Kernel Approximation Methods for Speech Recognition
First, in order to reduce the number of random features required by kernel models, we propose a simple but effective method for feature selection.
A Polynomial-Time Dynamic Programming Algorithm for Phrase-Based Decoding with a Fixed Distortion Limit
Decoding of phrase-based translation models in the general case is known to be NP-complete, by a reduction from the traveling salesman problem (Knight, 1999).
Cross-Lingual Syntactic Transfer with Limited Resources
We describe a simple but effective method for cross-lingual syntactic transfer of dependency parsers, in the scenario where a large amount of translation data is not available.
Globally Normalized Transition-Based Neural Networks
Our model is a simple feed-forward neural network that operates on a task-specific transition system, yet achieves comparable or better accuracies than recurrent models.
Ranked #16 on
Dependency Parsing
on Penn Treebank
A Comparison between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition
We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition.
Unsupervised Part-Of-Speech Tagging with Anchor Hidden Markov Models
We tackle unsupervised part-of-speech (POS) tagging by learning hidden Markov models (HMMs) that are particularly well-suited for the problem.
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.
Structured Training for Neural Network Transition-Based Parsing
We present structured perceptron training for neural network transition-based dependency parsing.
Ranked #17 on
Dependency Parsing
on Penn Treebank
Learning Dictionaries for Named Entity Recognition using Minimal Supervision
This paper describes an approach for automatic construction of dictionaries for Named Entity Recognition (NER) using large amounts of unlabeled data and a few seed examples.
How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets
The computational complexity of kernel methods has often been a major barrier for applying them to large-scale learning problems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
A Tutorial on Dual Decomposition and Lagrangian Relaxation for Inference in Natural Language Processing
Dual decomposition, and more generally Lagrangian relaxation, is a classical method for combinatorial optimization; it has recently been applied to several inference problems in natural language processing (NLP).
Tensor Decomposition for Fast Parsing with Latent-Variable PCFGs
We describe an approach to speed-up inference with latent variable PCFGs, which have been shown to be highly effective for natural language parsing.
Learning Label Embeddings for Nearest-Neighbor Multi-class Classification with an Application to Speech Recognition
We consider the problem of using nearest neighbor methods to provide a conditional probability estimate, P(y|a), when the number of labels y is large and the labels share some underlying structure.
