Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading

By Martin Raison, Pierre-Emmanuel Mazaré, Rajarshi Das, Antoine Bordes. 2018

20 citations recorded by the source corpus.

This paper aims at improving how machines can answer questions directly from text, with the focus of having models that can answer correctly multiple types of questions and from various types of texts, documents or even from large collections of them. To that end, we introduce the Weaver model that uses a new way to relate a question to a textual context by weaving layers of recurrent networks, with the goal of making as few assumptions as possible as to how the information from both question and context should be combined to form the answer. We show empirically on six datasets that Weaver performs well in multiple conditions. For instance, it produces solid results on the very popular SQuAD dataset (Rajpurkar et al., 2016), solves almost all bAbI tasks (Weston et al., 2015) and greatly outperforms state-of-the-art methods for open domain question answering from text (Chen et al., 2017).

Subfields: Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (2019, methodology): “As mentioned in Section 6.1, the difference between ours and Weaver can be considered as the decomposability gap arising from the constraint of query-agnostic phrase representations.”
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language (2019, methodology): “Furthermore on MEDHOP, we equip the models with word embeddings that were pretrained on a large biomedical corpus (Pyysalo et al., 2013).”
Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text (2018, background): “Recently, the paradigm has shifted towards training end-to-end deep neural network models for the task (Chen et al., 2017; Liang et al., 2017; Raison et al., 2018; Talmor and Berant, 2018; Iyyer et al., 2017).”
Question Answering by Reasoning Across Documents with Graph Convolutional Networks (2018, background): “, 2018), and Weaver / Jenga (Raison et al., 2018) have been applied to multi-document question answering.”
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension (2019, result): “For a fair comparison to recent works (De Cao et al., 2018; Song et al., 2018a; Raison et al., 2018), we report our “EPAr” with Next, in Table 2, we further evaluate our EPAr system (and its smaller-sized and ablated versions) on the “follows + multiple”, “follows + single”, and the full…”