Papers by Regina Barzilay

15 papers
Nutri-bullets Hybrid: Consensual Multi-document Summarization (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for generating comparative summaries that highlight similarities and contradictions in input documents are lacking large parallel training data for their training.
Approach: They propose a method for generating comparative summaries that highlight similarities and contradictions in input documents by using a neural interpretation of traditional concept-to-text generation systems.
Outcome: The proposed model is compared with conventional methods in the domain of nutrition and health, where the existing models lack large parallel training data.
Consistent Accelerated Inference via Confident Adaptive Transformers (2021.emnlp-main)

Copied to clipboard

Challenge: Amortized or approximate computational methods increase efficiency, but can result in unpredictable performance costs.
Approach: They propose a method that increases computational efficiency while guaranteeing a specifiable degree of consistency with the original model with high confidence.
Outcome: The proposed method improves on four classification and regression tasks and can be used to predict the performance of the proposed model.
Towards Debiasing Fact Verification Models (D19-1)

Copied to clipboard

Challenge: Prior research has shown that data collection methods that use crowdsourcing introduce idiosyncratic biases that impact performance in unexpected ways.
Approach: They propose a method to regularize the training data to avoid idiosyncrasies in the datasets that are used for fact verification.
Outcome: The proposed model outperforms the existing model on the FEVER dataset, achieving 61.7% of the baseline.
Multi-Source Domain Adaptation with Mixture of Experts (D18-1)

Copied to clipboard

Challenge: Existing methods for domain adaptation from multiple sources are designed to transfer supervision from a single source domain.
Approach: They propose to capture the relationship between a target example and different source domains by a point-to-set metric.
Outcome: The proposed method outperforms baselines and can handle negative transfer.
Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing (N19-1)

Copied to clipboard

Challenge: Existing methods for multilingual transfer are limited by their dynamic nature.
Approach: They propose a method that utilizes deep contextual embeddings, pretrained in an unsupervised fashion.
Outcome: The proposed method outperforms the state-of-the-art on 6 languages, yielding an improvement of 6.8 LAS points on average.
Blank Language Models (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches focus on adapting left-to-right language models for text infilling.
Approach: They propose a model that generates sequences by dynamically creating and filling in blanks.
Outcome: Experiments on style transfer and damaged ancient text restoration show that the proposed model outperforms baseline models in terms of accuracy and fluency.
CapWAP: Image Captioning with a Purpose (2020.emnlp-main)

Copied to clipboard

Challenge: a traditional image captioning task uses generic reference captions to provide textual information about images.
Approach: They propose a task that uses question-answer pairs to provide visual information instead of generic reference captions.
Outcome: The proposed captioning with a purpose task can be tailored to meet user needs . question-answer pairs are used as a source of supervision for learning visual information needs a new task is proposed .
Inferring Which Medical Treatments Work from Reports of Clinical Trials (N19-1)

Copied to clipboard

Challenge: Ideally, one would consult all available evidence from relevant clinical trials. however, these results are primarily disseminated in natural language scientific articles.
Approach: They propose a task that involves inferring results from a full-text article describing randomized controlled trials with respect to a given intervention, comparator, and outcome of interest.
Outcome: The proposed task consists of 10,000+ prompts coupled with full-text articles describing randomized controlled trials.
Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence (2021.naacl-main)

Copied to clipboard

Challenge: Typical fact verification models use retrieved written evidence to verify claims . evidence sources change over time as more information is gathered and revised . a new benchmark for fact verification is VitaminC, which is contrastive in nature .
Approach: They propose a benchmark that uses Wikipedia revisions to train models to discern and adjust to slight factual changes.
Outcome: The proposed model improves accuracy by 10% on adversarial fact verification and 6% on adversary natural language inference.
Predictive Chemistry Augmented with Text Retrieval (2023.emnlp-main)

Copied to clipboard

Challenge: TextReact is a new method to augment predictive chemistry with text descriptions retrieved from the literature.
Approach: They propose a method that directly augments predictive chemistry with texts retrieved from the literature.
Outcome: The proposed method outperforms existing models trained on molecular data.
Deriving Machine Attention from Human Rationales (D18-1)

Copied to clipboard

Challenge: Attention-based models are successful when trained on large amounts of data.
Approach: They propose an approach to map human-annotated rationales to high-performing attention and use this to guide models trained in low-resource scenarios.
Outcome: The proposed model yields over 15% error reduction on benchmark datasets.
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior (2021.tacl-1)

Copied to clipboard

Challenge: a number of undeciphered languages are still undecipherated, igniting fierce scientific debate . a recent study shows that NLP methods can successfully decipher lost languages .
Approach: They propose a decipherment model that incorporates phonetic geometry into word segmentation and cognate alignment . they use the International Phonetic Alphabet to learn character embeddings based on historical sound change .
Outcome: The proposed model shows that it can decipher both deciphered and undeciphered languages.
GraphIE: A Graph-Based Framework for Information Extraction (N19-1)

Copied to clipboard

Challenge: Most modern Information Extraction (IE) systems are implemented as sequential taggers and model local dependencies.
Approach: They propose a framework that operates over a graph representing a broad set of dependencies between textual units.
Outcome: The proposed framework outperforms the state-of-the-art sequence tagging model on three different tasks.
Working Hard or Hardly Working: Challenges of Integrating Typology into Neural Dependency Parsers (D19-1)

Copied to clipboard

Challenge: linguistic typology has shown great promise in pre-neural parsing, but results for neural architectures have been mixed.
Approach: They explore the task of leveraging typology in the context of cross-lingual dependency parsing.
Outcome: The proposed approach improves performance in the context of cross-lingual dependency parsing.
Neural Decipherment via Minimum-Cost Flow: From Ugaritic to Linear B (P19-1)

Copied to clipboard

Challenge: Existing methods for decipherment of lost languages are limited by limited data and scarce quantities of ancient text.
Approach: They propose a neural approach for automatic decipherment of lost languages . they use an expressive sequence-to-sequence model to capture character-level correspondences between cognates .
Outcome: The proposed approach improves on the decipherment of Ugaritic and Linear B in ancient Greek . the proposed approach is highly customized for a given language pair and does not generalize to other lost languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations