Constituent centric architecture for reading comprehension
AssigneePetuum Inc.
InventorsPengtao Xie, Eric Xing
Life of this patent
Estimating the term…
Abstract
A constituent-centric neural architecture for reading comprehension is disclosed. One embodiment provides a method that performs reading comprehension comprising encoding individual constituents from a text passage using a chain of trees long short-term encoding, encodes question related to the text passage using a tree long short-term memory encoding, generates a question-aware representation for each constituent in the passage using a tree-guided attention mechanism, generates a plurality of candidate answers from the question-aware representation using hierarchical relations among constituents, and predicts an answer to the question in relation to the text passage using a feed-forward network. Other embodiments are disclosed herein.
Claims16
A method for performing reading comprehension (RC), comprising:
- encoding individual constituents from a text passage using a chain of trees long short-term encoding, wherein encoding individual constituents from the text passage using a chain of trees long short-term encoding further comprises:
- building a bi-directional tree long short-term memory encoding for each sentence;
- and
- gluing together the bi-directional tree long short-term memory encoding with a bi-directional chain long short-term memory;
- encoding a question related to the text passage using a tree long short-term memory encoding;
- generating a question-aware representation for each constituent in the passage using a tree-guided attention mechanism;
- generating a plurality of candidate answers from the question-aware representation using hierarchical relations among constituents;
- and
- predicting an answer to the question in relation to the text passage using a feed-forward network.
A reading comprehension (RC) system with memory and a processor, the reading comprehension system comprising:
- a parsing module;
- and
- a Constituent-Centric Neural Network (CCNN) module stored in memory and comprising an encoding module to encode constituents in a text passage and one or more text questions, a tree-guided attention module to learn question-aware representations, a candidate answer generation module, the candidate answer generation module to produce candidate answers based on a constituent expansion, and an answer prediction module to select the best answer from the candidate answers using a feed-forward network, wherein the encoding module encodes individual constituents from the text passage using a chain of trees long short-term encoding by building a bi-directional tree long short-term memory encoding for each sentence and gluing together the bi-directional tree long short-term memory encoding with a bi-directional chain long short-term memory.
A method for performing reading comprehension (RC), comprising:
- parsing a text passage and one or more text questions into constituents;
- encoding said constituents in an encoding sub-module and sending encoded constituents to a tree guided attention sub-module to learn question-aware representations;
- receiving said question-aware representations in a candidate answer generation sub-module to generate candidate answers;
- and
- selecting the best answer from said candidate answers in an answer prediction sub-module, wherein the encoding sub-module encodes the constituents from the text passage using a chain of trees long short-term encoding by building a bi-directional tree long short-term memory encoding for each sentence and gluing together the bi-directional tree long short-term memory encoding with a bi-directional chain long short-term memory.
Dependencies are inferred from the claim text.