Search Results for author:
Found 47 papers, 14 papers with code
Towards Robust Neural Retrieval with Source Domain Synthetic Pre-Finetuning
Research on neural IR has so far been focused primarily on standard supervised learning settings, where it outperforms traditional term matching baselines.
Transforming the Hybrid Cloud for Emerging AI Workloads
This white paper, developed through close collaboration between IBM Research and UIUC researchers within the IIDAI Institute, envisions transforming hybrid cloud systems to meet the growing complexity of AI workloads through innovative, full-stack co-design approaches, emphasizing usability, manageability, affordability, adaptability, efficiency, and scalability.
FIRST: Faster Improved Listwise Reranking with Single Token Decoding
Further, we incorporate a learning-to-rank loss during training, prioritizing ranking accuracy for the more relevant passages.
Prompts as Auto-Optimized Training Hyperparameters: Training Best-in-Class IR Models from Scratch with 10 Gold Labels
We develop a method for training small-scale (under 100M parameter) neural information retrieval models with as few as 10 gold relevance labels.
CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems
We present ClapNQ, a benchmark Long-form Question Answering dataset for the full RAG pipeline.
An Empirical Investigation into the Effect of Parameter Choices in Knowledge Distillation
We present a large-scale empirical study of how choices of configuration parameters affect performance in knowledge distillation (KD).
Muted: Multilingual Targeted Offensive Speech Identification and Visualization
Offensive language such as hate, abuse, and profanity (HAP) occurs in various content on the web.
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Our framework trains a single arbitrary LM that adaptively retrieves passages on-demand, and generates and reflects on retrieved passages and its own generations using special tokens, called reflection tokens.
Ranked #1 on
Question Answering
on PopQA
ReFIT: Relevance Feedback from a Reranker during Inference
Retrieve-and-rerank is a prevalent framework in neural information retrieval, wherein a bi-encoder network initially retrieves a pre-defined number of candidates (e. g., K=100), which are then reranked by a more powerful cross-encoder model.
UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers
Many information retrieval tasks require large labeled datasets for fine-tuning.
PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Development
The field of Question Answering (QA) has made remarkable progress in recent years, thanks to the advent of large pre-trained language models, newer realistic benchmark datasets with leaderboards, and novel algorithms for key components such as retrievers and readers.
Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking
Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks.
SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers
Fine-tuning pre-trained language models (PLMs) achieves impressive performance on a range of downstream tasks, and their sizes have consequently been getting bigger.
Zero-Shot Dynamic Quantization for Transformer Inference
We introduce a novel run-time method for significantly reducing the accuracy loss associated with quantizing BERT-like models to 8-bit integers.
GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questions
Recent machine reading comprehension datasets include extractive and boolean questions but current approaches do not offer integrated support for answering both question types.
Task Transfer and Domain Adaptation for Zero-Shot Question Answering
Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks.
Not to Overfit or Underfit the Source Domains? An Empirical Study of Domain Generalization in Question Answering
Machine learning models are prone to overfitting their training (source) domains, which is commonly believed to be the reason why they falter in novel target domains.
Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrieval
On two public IR benchmarks, we empirically show that the proposed method helps improve both the model's attention patterns and retrieval performance, including in zero-shot settings.
Synthetic Target Domain Supervision for Open Retrieval QA
Neural passage retrieval is a new and promising approach in open retrieval question answering.
MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding
Specifically, the task involves multi-hop questions that require reasoning over image-caption pairs to identify the grounded visual object being referred to and then predicting a span from the news body text to answer the question.
Learning Cross-Lingual IR from an English Retriever
We present DR. DECR (Dense Retrieval with Distillation-Enhanced Cross-Lingual Representation), a new cross-lingual information retrieval (CLIR) system trained using multi-stage knowledge distillation (KD).
Cross-Lingual Information Retrieval
Knowledge Distillation
+3
Do Answers to Boolean Questions Need Explanations? Yes
Existing datasets that contain boolean questions, such as BoolQ and TYDI QA , provide the user with a YES/NO response to the question.
On The Ingredients of an Effective Zero-shot Semantic Parser
Semantic parsers map natural language utterances into meaning representations (e. g., programs).
Improved Text Classification via Contrastive Adversarial Training
We propose a simple and general method to regularize the fine-tuning of Transformer-based encoders for text classification tasks.
VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension
Existing models on Machine Reading Comprehension (MRC) require complex model architecture for effectively modeling long texts with paragraph representation and classification, thereby making inference computationally inefficient for production use.
Towards Robust Neural Retrieval Models with Synthetic Pre-Training
Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems.
Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering
Recent approaches have exploited weaknesses in monolingual question answering (QA) models by adding adversarial statements to the passage.
Towards Confident Machine Reading Comprehension
Performance prediction is particularly important in cases of domain shift (as measured by training RC models on SQUAD 2. 0 and evaluating on NQ), where Mr. C not only improves AUC, but also traditional answerability prediction (as measured by a 5 point improvement in F1).
Multilingual Transfer Learning for QA Using Translation as Data Augmentation
Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a QA model on English and test on other languages.
Answer Span Correction in Machine Reading Comprehension
Answer validation in machine reading comprehension (MRC) consists of verifying an extracted answer against an input context and question pair.
Multi-Stage Pre-training for Low-Resource Domain Adaptation
Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain.
The TechQA Dataset
We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain.
Cross-lingual Structure Transfer for Relation and Event Extraction
The identification of complex semantic structures such as events and entity relations, already a challenging Information Extraction task, is doubly difficult from sources written in under-resourced and under-annotated languages.
Ensembling Strategies for Answering Natural Questions
Many of the top question answering systems today utilize ensembling to improve their performance on tasks such as the Stanford Question Answering Dataset (SQuAD) and Natural Questions (NQ) challenges.
Structured Pruning of a BERT-based Question Answering Model
The recent trend in industry-setting Natural Language Processing (NLP) research has been to operate large %scale pretrained language models like BERT under strict computational limits.
Frustratingly Easy Natural Question Answering
Existing literature on Question Answering (QA) mostly focuses on algorithmic novelty, data augmentation, or increasingly large pre-trained language models like XLNet and RoBERTa.
Ranked #5 on
Question Answering
on Natural Questions (long)
Span Selection Pre-training for Question Answering
BERT (Bidirectional Encoder Representations from Transformers) and related pre-trained Transformers have provided large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA).
CFO: A Framework for Building Production NLP Systems
This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments.
Neural Cross-Lingual Coreference Resolution and its Application to Entity Linking
We propose an entity-centric neural cross-lingual coreference model that builds on multi-lingual embeddings and language-independent features.
Neural Cross-Lingual Entity Linking
A major challenge in Entity Linking (EL) is making effective use of contextual information to disambiguate mentions to Wikipedia that might refer to different entities in different contexts.
Ranked #3 on
Entity Disambiguation
on TAC2010
One for All: Towards Language Independent Named Entity Linking
Entity linking (EL) is the task of disambiguating mentions in text by associating them with entries in a predefined database of mentions (persons, organizations, etc).
Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structures
Slot Filling (SF) aims to extract the values of certain types of attributes (or slots, such as person:cities\_of\_residence) for a given entity from a large collection of source documents.
Toward Mention Detection Robustness with Recurrent Neural Networks
One of the key challenges in natural language processing (NLP) is to yield good performance across application domains and languages.
