Papers by Regina Barzilay
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
Tal Schuster, Darsh Shah, Yun Jie Serene Yeo, Daniel Roberto Filizzola Ortiz, Enrico Santus, Regina Barzilay
| 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. |