Weakly-supervised table question-answering(TableQA) models have achieved state-of-art performance by using pre-trained BERT transformer to jointly encoding a question and a table to produce structured query for the question.
Automatically inducing high quality knowledge graphs from a given collection of documents still remains a challenging problem in AI.
Ranked #1 on Zero-shot Slot Filling on T-REx
Relation linking is essential to enable question answering over knowledge bases.
Ranked #1 on Relation Linking on QALD-9
Relation linking is a crucial component of Knowledge Base Question Answering systems.
We present the first end-to-end, transformer-based table question answering (QA) system that takes natural language questions and massive table corpora as inputs to retrieve the most relevant tables and locate the correct table cells to answer the question.
1 code implementation • 24 Jun 2021 • Yannis Katsis, Saneem Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Mustafa Canim, Michael Glass, Alfio Gliozzo, Feifei Pan, Jaydeep Sen, Karthik Sankaranarayanan, Soumen Chakrabarti
Recent advances in transformers have enabled Table Question Answering (Table QA) systems to achieve high accuracy and SOTA results on open domain datasets like WikiTableQuestions and WikiSQL.
We present the first end-to-end, transformer-based table question answering (QA) system that takes natural language questions and massive table corpus as inputs to retrieve the most relevant tables and locate the correct table cells to answer the question.
Recently, there has been a promising direction in evaluating language models in the same way we would evaluate knowledge bases, and the task of slot filling is the most suitable to this intent.
While this model yields extremely high accuracy at finding cell values on recent benchmarks, a second model we propose, called RCI representation, provides a significant efficiency advantage for online QA systems over tables by materializing embeddings for existing tables.
Inferring semantic types for entity mentions within text documents is an important asset for many downstream NLP tasks, such as Semantic Role Labelling, Entity Disambiguation, Knowledge Base Question Answering, etc.
In this work, we propose Canonicalizing Using Variational Autoencoders (CUVA), a joint model to learn both embeddings and cluster assignments in an end-to-end approach, which leads to a better vector representation for the noun and relation phrases.
1 code implementation • 3 Dec 2020 • Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramon Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue, Dinesh Garg, Alfio Gliozzo, Sairam Gurajada, Hima Karanam, Naweed Khan, Dinesh Khandelwal, Young-suk Lee, Yunyao Li, Francois Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G P Shrivatsa Bhargav, Mo Yu
Knowledge base question answering (KBQA)is an important task in Natural Language Processing.
Each year the International Semantic Web Conference accepts a set of Semantic Web Challenges to establish competitions that will advance the state of the art solutions in any given problem domain.
Knowledgebase question answering systems are heavily dependent on relation extraction and linking modules.
Ranked #1 on Relation Linking on QALD-7
However, there has been no attempt to exploit GNN to create taxonomies.
This paper introduces Strict Partial Order Networks (SPON), a novel neural network architecture designed to enforce asymmetry and transitive properties as soft constraints.
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 #1 on Question Answering on Natural Questions (short)
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).
In addition to that, the system uses a deep learning approach for knowledge base completion by utilizing the global structure information of the induced KG to further refine the confidence of the newly discovered relations.
State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken from the knowledge base, whereas negative ones are generated by random sampling of entities.
We address relation extraction as an analogy problem by proposing a novel approach to learn representations of relations expressed by their textual mentions.
State-of-the-art relation extraction approaches are only able to recognize relationships between mentions of entity arguments stated explicitly in the text and typically localized to the same sentence.