Modeling Biological Processes for Reading Comprehension

By Jonathan Berant, Vivek Srikumar, Pei-Chun Chen, Abby Vander Linden, Brittany Harding, Brad Huang, Peter Clark, Christopher D. Manning. 2014

240 citations recorded by the source corpus.

Machine reading calls for programs that read and understand text, but most current work only attempts to extract facts from redundant web-scale corpora. In this paper, we focus on a new reading comprehension task that requires complex reasoning over a single document. The input is a paragraph describing a biological process, and the goal is to answer questions that require an understanding of the relations between entities and events in the process. To answer the questions, we first predict a rich structure representing the process in the paragraph. Then, we map the question to a formal query, which is executed against the predicted structure. We demonstrate that answering questions via predicted structures substantially improves accuracy over baselines that use shallower representations.

Subfields: Artificial Intelligence, Molecular Biology, 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 Artificial Intelligence

In Molecular Biology

In Natural Language Processing

Citations in the corpus

The Effect of Natural Distribution Shift on Question Answering Models (2020, background): “Beyond SQuAD, a number of works have proposed datasets for question answering (Richardson et al., 2013; Berant et al., 2014; Joshi et al., 2017; Trischler et al., 2017; Dunn et al., 2017; Yang et al., 2018; Kwiatkowski et al., 2019).”
Solving General Arithmetic Word Problems (2016, background): “The system described in (Berant et al., 2014) attempts to automatically answer biology questions, by extracting the structure of biological processes from text.”
Parsing Algebraic Word Problems into Equations (2015, methodology): “…discriminative models trained from a small number of word problems and their solutions – without any manual annotation; and (3) We demonstrate empirically that ALGES has broader scope than the system of Hosseini et al. (2014), and overcomes the brittleness of the method of Kushman et al. (2014).”
A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task (2016, methodology): “In recent years, there have been several strands of work which attempt to collect human-labeled data for this task – in the form of document, question and answer triples – and to learn machine learning models directly from it (Richardson et al., 2013; Berant et al., 2014; Wang et al., 2015).”
Gated Self-Matching Networks for Reading Comprehension and Question Answering (2017, background): “Those that are labeled by humans are always in high quality (Richardson et al., 2013; Berant et al., 2014; Yang et al., 2015), but are too small for training modern data-intensive models.”
Dynamic Coattention Networks For Question Answering (2016, background): “Previous QA datasets tend to be high in quality due to human annotation, but small in size (Berant et al., 2014; Richardson et al., 2013).”
Learning Disentangled Representations with Semi-Supervised Deep Generative Models (2017, background): “Unfortunately, deﬁning a good probabilistic model is hard: in complex perceptual domains such as vision, extensive feature engineering (e.g. Siddharth et al. [30], Berant et al. [1]) may be necessary to deﬁne a suitable likelihood function.”
MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension (2019, background): “BioProcess (Berant et al., 2014) Paragraphs are sourced from a biology textbook, and question and answer pairs about those paragraphs are then created by domain experts.”
Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering (2017, background): “…to understand given documents and answer questions about their content has recently attracted intensive interest, including but not limited to the efforts as in [Richardson et al., 2013, Hermann et al., 2015, Hill et al., 2015, Rajpurkar et al., 2016, Nguyen et al., 2016, Berant et al., 2014].”
Learning Knowledge Graphs for Question Answering through Conversational Dialog (2015, methodology): “, 2014) and biology reading comprehension questions (Berant et al., 2014).”
MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension (2019, background): “Reading comprehension (RC) is concerned with reading a piece of text and answering questions about it (Richardson et al., 2013; Berant et al., 2014; Hermann et al., 2015; Rajpurkar et al., 2016).”
Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph (2018, background): “…et al. 2016; Nguyen et al. 2016), (iv) cloze style QA (Mostafazadeh et al. 2016; Onishi et al. 2016) (v) multiple choice QA (Richardson, Burges, and Renshaw 2013; Berant et al. 2014) Of the above QA tasks, factoid QA is most relevant to us as the questions in our CSQA dataset are factoid questions.”
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension (2018, methodology): “Global constraints were found useful in the earlier ProRead system (Berant et al., 2014).”
DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension (2018, background): “There are also some datasets for RC with multiple choice questions (Richardson et al., 2013; Berant et al., 2014; Lai et al., 2017) where the task is to select one among k given candidate answers.”
Question Answering as Global Reasoning Over Semantic Abstractions (2018, methodology): “It also gen-1 eralizes well, as demonstrated by its strong performance on biology questions in the P ROCESS B ANK dataset (Berant et al. 2014).”