Machine Comprehension with Syntax, Frames, and Semantics

By Hai Wang, Mohit Bansal, Kevin Gimpel, David A. McAllester. 2015

103 citations recorded by the source corpus.

We demonstrate significant improvement on the MCTest question answering task (Richardson et al., 2013) by augmenting baseline features with features based on syntax, frame semantics, coreference, and word embeddings, and combining them in a max-margin learning framework. We achieve the best results we are aware of on this dataset, outperforming concurrentlypublished results. These results demonstrate a significant performance gradient for the use of linguistic structure in machine comprehension.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension (2017, methodology): “ous work (Wang et al., 2015; Chen et al., 2016), and compare these to BiDAF (Seo et al.”
SQuAD: 100,000+ Questions for Machine Comprehension of Text (2016, background): “Because many of the questions require commonsense reasoning and reasoning across multiple sentences, the dataset remains quite challenging, though there has been noticeable progress (Narasimhan and Barzilay, 2015; Sachan et al., 2015; Wang et al., 2015).”
NewsQA: A Machine Comprehension Dataset (2016, methodology): “Nevertheless, recent comprehension models have performed well on MCTest (Sachan et al., 2015; Wang et al., 2015), including a highly structured neural model (Trischler et al., 2016a).”
A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task (2016, background): “This is similar in spirit to (Wang et al., 2015), which at present has very competitive performance on the MCTest RC dataset (Richardson et al., 2013).”
Dynamic Coattention Networks For Question Answering (2016, methodology): “Wang et al. (2015) described a statistical model using frame semantic features as well as syntactic features such as part of speech tags and dependency parses.”
Multi-Perspective Context Matching for Machine Comprehension (2016, methodology): “…dataset prevents researchers from building end-to-end deep neural network models, and the state-of-the-art performances are still dominated by the methods highly relying on hand-crafted features (Sachan et al., 2015; Wang and McAllester, 2015) or employing additional knowledge (Wang et al., 2016a).”
Who did What: A Large-Scale Person-Centered Cloze Dataset (2016, background): “• Semantic features: NLP feature based system from Wang et al. (2015).”
Linguistically-Informed Self-Attention for Semantic Role Labeling (2018, positive): “Our approach may be interpreted as an extension of teacher forcing (Williams and Zipser, 1989) to MTL.”
A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset (2018, methodology): “Recent techniques such as Wang et al. (2015) and Yin et al. (2016) have performed well on this dataset.”
Answering Science Exam Questions Using Query Rewriting with Background Knowledge (2018, methodology): “f of the questions required the answer to be derived from two sentences, with the motivation being to encourage research in multi-hop (one-hop) reasoning. Recent techniques such as those presented by Wang et al. (2015) and Yin, Ebert, and Schutze (2016) have performed well on this dataset.¨ Currentl”
Controlled Crowdsourcing for High-Quality QA-SRL Annotation (2019, background): “, 2013), machine comprehension (Wang et al., 2015) and cross-document coreference (Barhom et al.”
Hierarchical Attention Flow for Multiple-Choice Reading Comprehension (2018, methodology): “Existing models (Richardson, Burges, and Renshaw 2013; Sachan et al. 2015; Narasimhan and Barzilay 2015; Wang et al. 2015; Smith et al. 2015; Trischler et al. 2016; Yin, Ebert, and Schütze 2016; Lai et al. 2017) for multiple-choice reading comprehension score each candidate option independently.”
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain (2018, methodology): “2018), the latest entailment model that has shown promise on the SciTail dataset10; (4) match-LSTM (Wang et al. 2015), which has shown good performance on the SNLI dataset; (5) match-LSTM with GRU, which replaces LSTMs with GRUs for its encoding, since GRUs are better than LSTMs for text classificat”
Evidence Sentence Extraction for Machine Reading Comprehension (2019, background): “Linguistic knowledge such as coreference resolution, frame semantics, and discourse relations is widely used to improve machine comprehension (Wang et al., 2015; Sachan et al., 2015; Narasimhan and Barzilay, 2015; Sun et al., 2018) especially when there are only hundreds of documents available in a…”
Evidence Extraction for Machine Reading Comprehension with Deep Probabilistic Logic (2018, background): “Wang et al. (2015); Sun et al. (2018); Sachan et al. (2015); Narasimhan and Barzilay (2015) use linguistical knowledge such as coreference, frame semantics and discourse relation to solve the machine comprehension on relatively small dataset where deep learning is difficult to apply.”
WorldTree V2: A Corpus of Science-Domain Structured Explanations and Inference Patterns supporting Multi-Hop Inference (2020, background): “…animals, all possible substances) to generate slight variations of questions. reasoning mechanisms similar to scripts or semantic frames (Minsky, 1974; Schank and Abelson, 1977; Wang et al., 2015; Ostermann et al., 2017), and that acquiring domain expertise is critical for multi-hop reasoning.”
Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures (2020, methodology): “Training Data with Biases (MultiNLI).”