Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userQA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
QA-GNN: التفكير مع نماذج اللغة ورسم الرسوم البيانية المعرفة للحصول على السؤال الرد
418
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعرض مشكلة الإجابة على الأسئلة التي تستخدم المعرفة من طرازات اللغة المدربة مسبقا (LMS) ورسم الرسوم البيانية المعرفة (KGS) تحديين: بالنظر إلى سياق ضمان الجودة (اختيار الأسئلة والأجوبة)، فإن الأساليب تحتاج إلى (I) تحديد المعرفة ذات الصلة من KGS الكبيرة،و (2) أداء التفكير المشترك في سياق ضمان الجودة و KG.هنا نقترح نموذجا جديدا، QA-GNN، الذي يتناول التحديات المذكورة أعلاه من خلال ابتكارات رئيسيتين: (ط) تسجيل الملاءمة، حيث نستخدم LMS لتقدير أهمية عقد KG بالنسبة إلى سياق ضمان الجودة المحدد، و (2) مشتركالتفكير، حيث نتواصل مع سياق ضمان الجودة و KG لتشكيل رسم بياني مشترك، وتحديث خصائصها المتبادلة من خلال رسالة الرسوم البيانية القائمة على الرسم البياني.نقوم بتقييم QA-GNN على مجموعات بيانات Commonsenseenseqa و OpenBookqa، وإظهار تحسنها على نماذج LM و LM + KG الحالية، وكذلك قدرتها على أداء التفكير القابل للتفسير والمنظم، على سبيل المثال، المناولة الصحيحة في الأسئلة.
The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG. Here we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: (i) relevance scoring, where we use LMs to estimate the importance of KG nodes relative to the given QA context, and (ii) joint reasoning, where we connect the QA context and KG to form a joint graph, and mutually update their representations through graph-based message passing. We evaluate QA-GNN on the CommonsenseQA and OpenBookQA datasets, and show its improvement over existing LM and LM+KG models, as well as its capability to perform interpretable and structured reasoning, e.g., correctly handling negation in questions.
References used
https://aclanthology.org/
rate research
Read More
We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs. The task in QReCC is to find answers to conversational questions within a collection of 10M web page
s (split into 54M passages). Answers to questions in the same conversation may be distributed across several web pages. QReCC provides annotations that allow us to train and evaluate individual subtasks of question rewriting, passage retrieval and reading comprehension required for the end-to-end conversational question answering (QA) task. We report the effectiveness of a strong baseline approach that combines the state-of-the-art model for question rewriting, and competitive models for open-domain QA. Our results set the first baseline for the QReCC dataset with F1 of 19.10, compared to the human upper bound of 75.45, indicating the difficulty of the setup and a large room for improvement.
Abstract Recent works have shown that language models (LM) capture different types of knowledge regarding facts or common sense. However, because no model is perfect, they still fail to provide appropriate answers in many cases. In this paper, we ask
the question, How can we know when language models know, with confidence, the answer to a particular query?'' We examine this question from the point of view of calibration, the property of a probabilistic model's predicted probabilities actually being well correlated with the probabilities of correctness. We examine three strong generative models---T5, BART, and GPT-2---and study whether their probabilities on QA tasks are well calibrated, finding the answer is a relatively emphatic no. We then examine methods to calibrate such models to make their confidence scores correlate better with the likelihood of correctness through fine-tuning, post-hoc probability modification, or adjustment of the predicted outputs or inputs. Experiments on a diverse range of datasets demonstrate the effectiveness of our methods. We also perform analysis to study the strengths and limitations of these methods, shedding light on further improvements that may be made in methods for calibrating LMs. We have released the code at https://github.com/jzbjyb/lm-calibration.
Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs). This paper targets at empowering the IR-based KBQA models with the ability of numerical reasoning for answering ordinal constrained que
stions. A major challenge is the lack of explicit annotations about numerical properties. To address this challenge, we propose a pretraining numerical reasoning model consisting of NumGNN and NumTransformer, guided by explicit self-supervision signals. The two modules are pretrained to encode the magnitude and ordinal properties of numbers respectively and can serve as model-agnostic plugins for any IR-based KBQA model to enhance its numerical reasoning ability. Extensive experiments on two KBQA benchmarks verify the effectiveness of our method to enhance the numerical reasoning ability for IR-based KBQA models.
Recently, end-to-end (E2E) trained models for question answering over knowledge graphs (KGQA) have delivered promising results using only a weakly supervised dataset. However, these models are trained and evaluated in a setting where hand-annotated q
uestion entities are supplied to the model, leaving the important and non-trivial task of entity resolution (ER) outside the scope of E2E learning. In this work, we extend the boundaries of E2E learning for KGQA to include the training of an ER component. Our model only needs the question text and the answer entities to train, and delivers a stand-alone QA model that does not require an additional ER component to be supplied during runtime. Our approach is fully differentiable, thanks to its reliance on a recent method for building differentiable KGs (Cohen et al., 2020). We evaluate our E2E trained model on two public datasets and show that it comes close to baseline models that use hand-annotated entities.
The key challenge of question answering over knowledge bases (KBQA) is the inconsistency between the natural language questions and the reasoning paths in the knowledge base (KB). Recent graph-based KBQA methods are good at grasping the topological s
tructure of the graph but often ignore the textual information carried by the nodes and edges. Meanwhile, pre-trained language models learn massive open-world knowledge from the large corpus, but it is in the natural language form and not structured. To bridge the gap between the natural language and the structured KB, we propose three relation learning tasks for BERT-based KBQA, including relation extraction, relation matching, and relation reasoning. By relation-augmented training, the model learns to align the natural language expressions to the relations in the KB as well as reason over the missing connections in the KB. Experiments on WebQSP show that our method consistently outperforms other baselines, especially when the KB is incomplete.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
