Relation/Entity-Centric Reading Comprehension
- URL: http://arxiv.org/abs/2008.11940v1
- Date: Thu, 27 Aug 2020 06:42:18 GMT
- Title: Relation/Entity-Centric Reading Comprehension
- Authors: Takeshi Onishi
- Abstract summary: We study reading comprehension with a focus on understanding entities and their relationships.
We focus on entities and relations because they are typically used to represent the semantics of natural language.
- Score: 1.0965065178451106
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Constructing a machine that understands human language is one of the most
elusive and long-standing challenges in artificial intelligence. This thesis
addresses this challenge through studies of reading comprehension with a focus
on understanding entities and their relationships. More specifically, we focus
on question answering tasks designed to measure reading comprehension. We focus
on entities and relations because they are typically used to represent the
semantics of natural language.
Related papers
- Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models [69.79709804046325]
We introduce R-Bench, a novel benchmark for evaluating Vision Relationship Hallucination.
R-Bench features image-level questions that focus on the existence of relationships and instance-level questions that assess local visual comprehension.
We identify three types of relationship co-occurrences that lead to hallucinations: relationship-relationship, subject-relationship, and relationship-object.
arXiv Detail & Related papers (2024-06-24T08:42:42Z) - Identifying Semantic Induction Heads to Understand In-Context Learning [103.00463655766066]
We investigate whether attention heads encode two types of relationships between tokens present in natural languages.
We find that certain attention heads exhibit a pattern where, when attending to head tokens, they recall tail tokens and increase the output logits of those tail tokens.
arXiv Detail & Related papers (2024-02-20T14:43:39Z) - tagE: Enabling an Embodied Agent to Understand Human Instructions [3.943519623674811]
We introduce a novel system known as task and argument grounding for Embodied agents (tagE)
At its core, our system employs an inventive neural network model designed to extract a series of tasks from complex task instructions expressed in natural language.
Our proposed model adopts an encoder-decoder framework enriched with nested decoding to effectively extract tasks and their corresponding arguments from these intricate instructions.
arXiv Detail & Related papers (2023-10-24T08:17:48Z) - SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language
Representations [51.08119762844217]
SenteCon is a method for introducing human interpretability in deep language representations.
We show that SenteCon provides high-level interpretability at little to no cost to predictive performance on downstream tasks.
arXiv Detail & Related papers (2023-05-24T05:06:28Z) - Neural Approaches to Entity-Centric Information Extraction [2.8935588665357077]
We introduce a radically different, entity-centric view of the information in text.
We argue that instead of using individual mentions in text to understand their meaning, we should build applications that would work in terms of entity concepts.
In our work, we show that this task can be improved by considering performing entity linking at the coreference cluster level rather than each of the mentions individually.
arXiv Detail & Related papers (2023-04-15T20:07:37Z) - DALL-E 2 Fails to Reliably Capture Common Syntactic Processes [0.0]
We analyze the ability of DALL-E 2 to capture 8 grammatical phenomena pertaining to compositionality.
We show that DALL-E 2 is unable to reliably infer meanings that are consistent with the syntax.
arXiv Detail & Related papers (2022-10-23T23:56:54Z) - A Linguistic Investigation of Machine Learning based Contradiction
Detection Models: An Empirical Analysis and Future Perspectives [0.34998703934432673]
We analyze two Natural Language Inference data sets with respect to their linguistic features.
The goal is to identify those syntactic and semantic properties that are particularly hard to comprehend for a machine learning model.
arXiv Detail & Related papers (2022-10-19T10:06:03Z) - Compositional Processing Emerges in Neural Networks Solving Math
Problems [100.80518350845668]
Recent progress in artificial neural networks has shown that when large models are trained on enough linguistic data, grammatical structure emerges in their representations.
We extend this work to the domain of mathematical reasoning, where it is possible to formulate precise hypotheses about how meanings should be composed.
Our work shows that neural networks are not only able to infer something about the structured relationships implicit in their training data, but can also deploy this knowledge to guide the composition of individual meanings into composite wholes.
arXiv Detail & Related papers (2021-05-19T07:24:42Z) - ERICA: Improving Entity and Relation Understanding for Pre-trained
Language Models via Contrastive Learning [97.10875695679499]
We propose a novel contrastive learning framework named ERICA in pre-training phase to obtain a deeper understanding of the entities and their relations in text.
Experimental results demonstrate that our proposed ERICA framework achieves consistent improvements on several document-level language understanding tasks.
arXiv Detail & Related papers (2020-12-30T03:35:22Z) - Semantics-Aware Inferential Network for Natural Language Understanding [79.70497178043368]
We propose a Semantics-Aware Inferential Network (SAIN) to meet such a motivation.
Taking explicit contextualized semantics as a complementary input, the inferential module of SAIN enables a series of reasoning steps over semantic clues.
Our model achieves significant improvement on 11 tasks including machine reading comprehension and natural language inference.
arXiv Detail & Related papers (2020-04-28T07:24:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.