Do you want to publish a course? Click here

BiQuAD: Towards QA based on deeper text understanding

BIQUAD: نحو QA بناء على فهم النص الأعمق

287   0   0   0.0 ( 0 )
 Publication date 2021
and research's language is English
 Created by Shamra Editor




Ask ChatGPT about the research

Recent question answering and machine reading benchmarks frequently reduce the task to one of pinpointing spans within a certain text passage that answers the given question. Typically, these systems are not required to actually understand the text on a deeper level that allows for more complex reasoning on the information contained. We introduce a new dataset called BiQuAD that requires deeper comprehension in order to answer questions in both extractive and deductive fashion. The dataset consist of 4,190 closed-domain texts and a total of 99,149 question-answer pairs. The texts are synthetically generated soccer match reports that verbalize the main events of each match. All texts are accompanied by a structured Datalog program that represents a (logical) model of its information. We show that state-of-the-art QA models do not perform well on the challenging long form contexts and reasoning requirements posed by the dataset. In particular, transformer based state-of-the-art models achieve F1-scores of only 39.0. We demonstrate how these synthetic datasets align structured knowledge with natural text and aid model introspection when approaching complex text understanding.



References used
https://aclanthology.org/
rate research

Read More

As part of the FEVEROUS shared task, we developed a robust and finely tuned architecture to handle the joint retrieval and entailment on text data as well as structured data like tables. We proposed two training schemes to tackle the hurdles inherent to multi-hop multi-modal datasets. The first one allows having a robust retrieval of full evidence sets, while the second one enables entailment to take full advantage of noisy evidence inputs. In addition, our work has revealed important insights and potential avenue of research for future improvement on this kind of dataset. In preliminary evaluation on the FEVEROUS shared task test set, our system achieves 0.271 FEVEROUS score, with 0.4258 evidence recall and 0.5607 entailment accuracy.
In this paper, we propose a definition and taxonomy of various types of non-standard textual content -- generally referred to as noise'' -- in Natural Language Processing (NLP). While data pre-processing is undoubtedly important in NLP, especially wh en dealing with user-generated content, a broader understanding of different sources of noise and how to deal with them is an aspect that has been largely neglected. We provide a comprehensive list of potential sources of noise, categorise and describe them, and show the impact of a subset of standard pre-processing strategies on different tasks. Our main goal is to raise awareness of non-standard content -- which should not always be considered as noise'' -- and of the need for careful, task-dependent pre-processing. This is an alternative to blanket, all-encompassing solutions generally applied by researchers through standard'' pre-processing pipelines. The intention is for this categorisation to serve as a point of reference to support NLP researchers in devising strategies to clean, normalise or embrace non-standard content.
Weakly-supervised text classification has received much attention in recent years for it can alleviate the heavy burden of annotating massive data. Among them, keyword-driven methods are the mainstream where user-provided keywords are exploited to ge nerate pseudo-labels for unlabeled texts. However, existing methods treat keywords independently, thus ignore the correlation among them, which should be useful if properly exploited. In this paper, we propose a novel framework called ClassKG to explore keyword-keyword correlation on keyword graph by GNN. Our framework is an iterative process. In each iteration, we first construct a keyword graph, so the task of assigning pseudo labels is transformed to annotating keyword subgraphs. To improve the annotation quality, we introduce a self-supervised task to pretrain a subgraph annotator, and then finetune it. With the pseudo labels generated by the subgraph annotator, we then train a text classifier to classify the unlabeled texts. Finally, we re-extract keywords from the classified texts. Extensive experiments on both long-text and short-text datasets show that our method substantially outperforms the existing ones.
This paper presents ArOntoLearn, a Framework for Arabic Ontology learning from textual resources. Supporting Arabic language and using domain knowledge in the learning process are the main features of our framework. Besides it represents the learne d ontology in Probabilistic Ontology Model (POM), which can be translated into any knowledge representation formalism, and implements data-driven change discovery. Therefore it updates the POM according to the corpus changes only, and allows user to trace the evolution of the ontology with respect to the changes in the underlying corpus. Our framework analyses Arabic textual resources, and matches them to Arabic Lexico-syntactic patterns in order to learn new Concepts and Relations. Supporting Arabic language is not that easy task, because current linguistic analysis tools are not efficient enough to process unvocalized Arabic corpuses that rarely contain appropriate punctuation. So we tried to build a flexible and freely configured framework whereas any linguistic analysis tool can be replaced by more sophisticated one whenever it is available.
The ease of access to pre-trained transformers has enabled developers to leverage large-scale language models to build exciting applications for their users. While such pre-trained models offer convenient starting points for researchers and developer s, there is little consideration for the societal biases captured within these model risking perpetuation of racial, gender, and other harmful biases when these models are deployed at scale. In this paper, we investigate gender and racial bias across ubiquitous pre-trained language models, including GPT-2, XLNet, BERT, RoBERTa, ALBERT and DistilBERT. We evaluate bias within pre-trained transformers using three metrics: WEAT, sequence likelihood, and pronoun ranking. We conclude with an experiment demonstrating the ineffectiveness of word-embedding techniques, such as WEAT, signaling the need for more robust bias testing in transformers.

suggested questions

comments
Fetching comments Fetching comments
Sign in to be able to follow your search criteria
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا