Search Results for author:
Found 17 papers, 11 papers with code
Fine-tuning Strategies for Domain Specific Question Answering under Low Annotation Budget Constraints
In this work, we demonstrate that this strategy is sub-optimal for fine-tuning QA models, especially under a low QA annotation budget, which is a usual setting in practice due to the extractive QA labeling cost.
QAnswer: Towards Question Answering Search over Websites
Question Answering (QA) is increasingly used by search engines to provide results to their end-users, yet very few websites currently use QA technologies for their search functionality.
Wikidata as a seed for Web Extraction
On the other side, most of the information on the Web is not published in highly structured data repositories like Wikidata, but rather as unstructured and semi-structured content, more concretely in HTML pages containing text and tables.
An investigation of structures responsible for gender bias in BERT and DistilBERT
In this paper, we propose an empirical exploration of this problem by formalizing two questions: (1) Can we identify the neural mechanism(s) responsible for gender bias in BERT (and by extension DistilBERT)?
ProtAugment: Intent Detection Meta-Learning through Unsupervised Diverse Paraphrasing
It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode.
ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning
It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode.
A Neural Few-Shot Text Classification Reality Check
Additionally, some models used in Computer Vision are yet to be tested in NLP applications.
Few-shot Pseudo-Labeling for Intent Detection
This performance is achieved on multiple intent detection datasets, even in more challenging situations where the number of classes is large or when the dataset is highly imbalanced.
Near-lossless Binarization of Word Embeddings
Word embeddings are commonly used as a starting point in many NLP models to achieve state-of-the-art performances.
Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
While Wikipedia exists in 287 languages, its content is unevenly distributed among them.
Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types
We present a neural model for question generation from knowledge base triples in a "Zero-Shot" setup, that is generating questions for triples containing predicates, subject types or object types that were not seen at training time.
Ranked #14 on
Zero-shot Text Search
on BEIR
Unsupervised Open Relation Extraction
We explore methods to extract relations between named entities from free text in an unsupervised setting.
High Recall Open IE for Relation Discovery
Relation Discovery discovers predicates (relation types) from a text corpus relying on the co-occurrence of two named entities in the same sentence.
Dict2vec : Learning Word Embeddings using Lexical Dictionaries
Learning word embeddings on large unlabeled corpus has been shown to be successful in improving many natural language tasks.
