Neural passage retrieval is a new and promising approach in open retrieval question answering.
Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems.
End-to-end question answering (QA) requires both information retrieval (IR) over a large document collection and machine reading comprehension (MRC) on the retrieved passages.
We present scalable Universal Dependency (UD) treebank synthesis techniques that exploit advances in language representation modeling which leverage vast amounts of unlabeled general-purpose multilingual text.
Answer validation in machine reading comprehension (MRC) consists of verifying an extracted answer against an input context and question pair.
Automatically generated synthetic training examples have been shown to improve performance in machine reading comprehension (MRC).
Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain.
Automatic question generation (QG) has shown promise as a source of synthetic training data for question answering (QA).
1 code implementation • • 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.
We demonstrate the viability of knowledge transfer between two related tasks: machine reading comprehension (MRC) and query-based text summarization.
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.
This paper presents the IBM Research AI submission to the CoNLL 2018 Shared Task on Parsing Universal Dependencies.
We consider the problem of using sentence compression techniques to facilitate query-focused multi-document summarization.
Answer sentence ranking and answer extraction are two key challenges in question answering that have traditionally been treated in isolation, i. e., as independent tasks.