Papers by Manzil Zaheer

16 papers
Analysis of Plan-based Retrieval for Grounded Text Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Large, parametric language models (LLMs) produce fluent text for many applications . hallucinations are generation of text that is factually correct and semantically plausible .
Approach: They propose to use learning-tuned LLMs to infuse models with retrieval mechanisms to reduce hallucinations.
Outcome: The proposed approach reduces the frequency of hallucinations by reducing the coverage of relevant facts and generating more informative responses while providing higher attribution rates.
Investigating the Working of Text Classifiers (C18-1)

Copied to clipboard

Challenge: Text classification is one of the most widely studied tasks in natural language processing.
Approach: They propose to use large multilayer neural network models to compose meaning of sentences . they propose to disincentivize focusing on key lexicons to improve classification accuracy .
Outcome: The proposed models learn to compose the meaning of the sentences or focus on key lexicons for classifying the document.
Questions Are All You Need to Train a Dense Passage Retriever (2023.tacl-1)

Copied to clipboard

Challenge: Existing methods for dense retrieval require large supervised datasets with custom hard-negative mining and denoising of positive examples.
Approach: They propose a new corpus-level autoencoding approach for training dense retrieval models that does not require labeled training data.
Outcome: The proposed method matches or surpasses strong supervised performance levels on multiple QA benchmarks with no labeled training data or task-specific losses.
Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition (2023.findings-emnlp)

Copied to clipboard

Challenge: ANNCUR uses a cross-encoder only to perform k-NN search, but the approximation of the distances is often detrimental to the retrieval of top-k items.
Approach: They propose a method that minimizes approximation error for k-nearest neighbor searches . they propose to use a cross-encoder only to perform k NN search .
Outcome: The proposed method reduces approximation error for top-k neighbors by up to 70% . iteratively performs k-NN search using the available anchors, then adds them to the next set .
Can Public Large Language Models Help Private Cross-device Federated Learning? (2024.findings-naacl)

Copied to clipboard

Challenge: Recent studies have shown that public data can be used to improve privacy-utility trade-offs for large and small language models.
Approach: They propose to use large-scale public data to help differentially private FL training . they propose a distribution matching algorithm with theoretical grounding to sample public data close to private data distribution .
Outcome: The proposed method is efficient and effective for training private models by taking advantage of public data.
Differentiable Open-Ended Commonsense Reasoning (2021.naacl-main)

Copied to clipboard

Challenge: Existing commonsense reasoning models work by scoring a question-candidate pair, but new approaches are needed to answer multiple-choice questions.
Approach: They propose to use a corpus of commonsense facts to answer a commonsensical question without any pre-defined choices as a resource.
Outcome: The proposed model outperforms baseline methods by a large margin in the open-ended commonsense reasoning task.
Scaling Within Document Coreference to Long Texts (2021.findings-acl)

Copied to clipboard

Challenge: Existing end-to-end coreference resolution models use expensive span representations and antecedent prediction mechanisms.
Approach: They propose an approximation to end-to-end coreference resolution models which scales gracefully to documents of any length.
Outcome: The proposed model reduces training and inference time and memory costs compared to current models with minimal loss in accuracy.
Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (D19-58)

Copied to clipboard

Challenge: Multi-hop question answering (QA) requires an information retrieval system that can find multiple supporting evidence needed to answer the question.
Approach: They propose a technique that uses information of entities present in the initial retrieved evidence to learn to ‘hop’ onto other relevant evidence.
Outcome: The proposed method boosts retrieval performance on a multi-hop question answering dataset with 5 million Wikipedia paragraphs and a model without training increases its performance by 10.59 F1.
Longtonotes: OntoNotes with Longer Coreference Chains (2023.findings-eacl)

Copied to clipboard

Challenge: Using Ontonotes, documents in certain genres were split into smaller parts for ease of annotation.
Approach: They propose to merge annotations from documents split into smaller parts in Ontonotes for ease of annotation.
Outcome: The proposed corpus restores documents to their original form, revealing dramatic increases in length in certain genres.
Case-based Reasoning for Natural Language Queries over Knowledge Bases (2021.emnlp-main)

Copied to clipboard

Challenge: Using human-labeled examples, case-based reasoning can solve complex problems from scratch . case-Based reasoning is a paradigm that is used to solve complex problem .
Approach: They propose a neuro-symbolic CBR approach for question answering over large knowledge bases.
Outcome: The proposed approach outperforms the current state of the art on a CWQ dataset by 11% on accuracy.
Machine Reading Comprehension using Case-based Reasoning (2023.findings-emnlp)

Copied to clipboard

Challenge: Current state-of-the-art machine readers do not support case-based reasoning .
Approach: They propose a method that extracts a set of similar cases from a nonparametric memory and then predicts an answer by selecting the span in the test context that is most similar to the contextualized representations of answers.
Outcome: The proposed method outperforms baselines on NaturalQuestions and NewsQA by 11.5 and 8.4 EM.
Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization (2022.emnlp-main)

Copied to clipboard

Challenge: Efficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP.
Approach: They propose an approach that avoids the use of a dual-encoder for retrieval, relying solely on the cross-encoding model.
Outcome: Empirically, for k > 10, our approach provides test-time recall-vs-computational cost trade-offs superior to the current widely-used methods that re-rank items retrieved using a dual-encoder or TF-IDF.
Large Language Models with Controllable Working Memory (2023.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have led to a series of breakthroughs in natural language processing due to the massive amounts of world knowledge they memorize during pretraining.
Approach: They propose a method to inject counterfactual and irrelevant contexts into standard supervised datasets to strengthen both controllability and robustness.
Outcome: The proposed method improves controllability and robustness across model architectures and sizes.
Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for learning non-parametric representations of entities and relations are based on tensor factorization or sophisticated neural approaches.
Approach: They propose a case-based reasoning system that retrieves ‘cases’ that are similar to the given problem and then stores them in its parameters.
Outcome: The proposed model outperforms state-of-the-art methods on several benchmark datasets and is non-parametric and grows dynamically as new entities and relations arrive in the KB.
Chains-of-Reasoning at TextGraphs 2019 Shared Task: Reasoning over Chains of Facts for Explainable Multi-hop Inference (D19-53)

Copied to clipboard

Challenge: EMNLP 2019 shared task on 'Multi-hop Inference Explanation Regeneration' identifies chains of facts relevant to explain an answer to an elementary science examination question.
Approach: They propose a system that identifies chains of facts relevant to explain an answer to an elementary science examination question.
Outcome: The proposed system outperforms the second best system by 14.95 points on the mean average precision (MAP) metric.
Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text (D18-1)

Copied to clipboard

Challenge: Specialized neural models have been developed for extracting answers from text alone or Knowledge Bases (KBs) alone.
Approach: They propose a novel model for extracting answers from a question-specific subgraph containing text and KB entities and relations.
Outcome: The proposed model outperforms existing methods in a combination of a KB and entity-linked text in QA over a large text corpus.

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