Challenge: Existing methods for reading comprehension tasks ignore semantic relations between sentences or use sliding window scanning over the words of the passage without sentence breaks.
Approach: They propose a method to integrate information from multiple sentences to answer complex questions.
Outcome: Experiments on RACE and MCTest show that the proposed approach improves state-of-the-art methods on simple factoid questions.

Similar Papers

TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions (2020.emnlp-main)

Copied to clipboard

Challenge: Current machine reading comprehension benchmarks have no questions that test temporal phenomena . a new study studies reading comprehension for temporal relations .
Approach: They propose a reading comprehension benchmark built on news snippets and 21k human-generated questions querying temporal relationships.
Outcome: The new reading comprehension benchmark TORQUE achieves an exact-match score of 51% on the test set . the benchmark is built on 3.2k news snippets with 21k human-generated questions .
Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for extracting temporal information from text are not suitable for time-sensitive questions.
Approach: They propose to use existing temporal information extraction systems to construct temporal graphs of events, times, and temporal relations in questions and documents.
Outcome: The proposed method outperforms graph convolution-based approaches on SituatedQA and TimeQA.
Understand before Answer: Improve Temporal Reading Comprehension via Precise Question Understanding (2022.naacl-main)

Copied to clipboard

Challenge: Temporal reading comprehension (TRC) is a natural way to study temporal relations since natural language questions are flexible to capture divergent temporal relationships.
Approach: They propose a reading comprehension approach that uses precise question understanding . they embed a temporal ordering question into two vectors and evaluate the temporal relation based on that .
Outcome: The proposed approach outperforms strong baselines and achieves state-of-the-art performance on the TORQUE dataset.
ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations (2021.emnlp-main)

Copied to clipboard

Challenge: Recent event-centric reading comprehension datasets focus mostly on event arguments or temporal relations.
Approach: They propose a machine reading comprehension dataset that leverages natural language queries to reason about the five most common event semantic relations.
Outcome: The proposed dataset shows that current SOTA systems achieve 22.1%, 63.3% and 83.5% for token-based exact-match, **F1** and event-based **HIT@1** scores.
Extracting Temporal Event Relation with Syntax-guided Graph Transformer (2022.findings-naacl)

Copied to clipboard

Challenge: Temporal relationship extraction is crucial for understanding complex events and reasoning over them.
Approach: They propose a Syntax-guided Graph Transformer network to extract temporal relations between events by explicitly exploiting the connection between two events based on their dependency parsing trees.
Outcome: The proposed approach outperforms state-of-the-art methods on MATRES and TB-DENSE with up to 7.9% absolute F-score gain.
Intra-Event and Inter-Event Dependency-Aware Graph Network for Event Argument Extraction (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing models do not build dependency information among event argument roles . Existing methods do not learn the interactions between different roles based on event structure .
Approach: They propose an intra-event and inter-e event dependency-aware graph network to model dependencies between roles . they use event structure as the fundamental unit to construct role dependencies within events .
Outcome: The proposed model improves on the ACE05, RAMS, and WikiEvents datasets.
Once Upon a Time in Graph: Relative-Time Pretraining for Complex Temporal Reasoning (2023.emnlp-main)

Copied to clipboard

Challenge: Existing work focuses on strengthening the knowledge-time association between text and time-stamps, but this is insufficient for downstream tasks.
Approach: They propose a model that explicitly connects all temporally-scoped facts by modeling the time relations between any two sentences.
Outcome: The proposed model outperforms baseline T5 on multiple temporal question answering datasets . it is especially good at modeling long-range complex temporal dependencies, the authors say .
Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs (2020.coling-main)

Copied to clipboard

Challenge: Using conceptual graphs, we can embed a sentence into a knowledge embedding in a graph to solve slot-filling challenges in question answering and capture neighbouring connections of reference concept nodes.
Approach: They propose a miscellaneous-context-based method to embed a sentence into a directed graph and a task-agnostic semantics module which integrates the syntactic-semantic information.
Outcome: The proposed method can accommodate slot-filling challenges in typical question answering and capture the neighbouring connections of reference concept nodes.
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13) (D19-53)

Copied to clipboard

Challenge: TextGraphs is a workshop on graph-based methods for natural language processing . the workshop is being organized in conjunction with the 9th International Joint Conference on Natural Language Processing .
Approach: TextGraphs is the 13th edition of the Workshop on Graph-Based Methods for Natural Language Processing . the workshop promotes synergy between GT and natural language processing .
Outcome: the 2013 edition of TextGraphs is being held in conjunction with the 9th International Joint Conference on Natural Language Processing in Hong Kong.
Annotating Temporal Dependency Graphs via Crowdsourcing (2020.emnlp-main)

Copied to clipboard

Challenge: Existing temporal annotation schemes have been limited due to the complexity of temporal relations between events.
Approach: They propose to build a corpus of Wikinews articles annotated with temporal dependency graphs . they also propose a crowdsourcing strategy to annotate TDGs based on the corpus .
Outcome: The proposed method achieves a good trade-off between completeness and practicality in temporal annotation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations