Research on neural IR has so far been focused primarily on standard supervised learning settings, where it outperforms traditional term matching baselines.
Neural information retrieval often adopts a retrieve-and-rerank framework: a bi-encoder network first retrieves K (e. g., 100) candidates that are then re-ranked using a more powerful cross-encoder model to rank the better candidates higher.
After that, a much less expensive one is used to create large numbers of synthetic queries, which are used to fine-tune a family of reranker models.
1 code implementation • 23 Jan 2023 • Avirup Sil, Jaydeep Sen, Bhavani Iyer, Martin Franz, Kshitij Fadnis, Mihaela Bornea, Sara Rosenthal, Scott McCarley, Rong Zhang, Vishwajeet Kumar, Yulong Li, Md Arafat Sultan, Riyaz Bhat, Radu Florian, Salim Roukos
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.
Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks.
Fine-tuning pre-trained language models (PLMs) achieves impressive performance on a range of downstream tasks, and their sizes have consequently been getting bigger.
We introduce a novel run-time method for significantly reducing the accuracy loss associated with quantizing BERT-like models to 8-bit integers.
Recent machine reading comprehension datasets include extractive and boolean questions but current approaches do not offer integrated support for answering both question types.
Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks.
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.
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.
Neural passage retrieval is a new and promising approach in open retrieval question answering.
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.
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).
Existing datasets that contain boolean questions, such as BoolQ and TYDI QA , provide the user with a YES/NO response to the question.
We propose a simple and general method to regularize the fine-tuning of Transformer-based encoders for text classification tasks.
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.
Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems.
Recent approaches have exploited weaknesses in monolingual question answering (QA) models by adding adversarial statements to the passage.
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).
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 validation in machine reading comprehension (MRC) consists of verifying an extracted answer against an input context and question pair.
Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain.
2 code implementations • • Vittorio Castelli, Rishav Chakravarti, Saswati Dana, Anthony Ferritto, Radu Florian, Martin Franz, Dinesh Garg, Dinesh Khandelwal, Scott McCarley, Mike McCawley, Mohamed Nasr, Lin Pan, Cezar Pendus, John Pitrelli, Saurabh Pujar, Salim Roukos, Andrzej Sakrajda, Avirup Sil, Rosario Uceda-Sosa, Todd Ward, Rong Zhang
We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain.
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.
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.
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.
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)
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).
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.
We propose an entity-centric neural cross-lingual coreference model that builds on multi-lingual embeddings and language-independent features.
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).
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
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.
One of the key challenges in natural language processing (NLP) is to yield good performance across application domains and languages.