Contextual Aware Joint Probability Model Towards Question Answering System
In this paper, we address the question answering challenge with the SQuAD 2.0 dataset. We design a model architecture which leverages BERT's capability of context-aware word embeddings and BiDAF's context interactive exploration mechanism. By integrating these two state-of-the-art architectures, our system tries to extract the contextual word representation at word and character levels, for better comprehension of both question and context and their correlations. We also propose our original joint posterior probability predictor module and its associated loss functions. Our best model so far obtains F1 score of 75.842% and EM score of 72.24% on the test PCE leaderboad.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringWord EmbeddingsSimilar Papers 제목 키워드 기반
Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions
We consider open-retrieval conversational question answering (OR-CONVQA), an extension of question answering where system responses need to be (i) aware of dialog history and (ii) grounded in documents (or document fragm…
Conversational Question AnsweringPeering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering
With the enhancement in the field of generative artificial intelligence (AI), contextual question answering has become extremely relevant. Attributing model generations to the input source document is essential to ensure…
Question AnsweringConQuest: Contextual Question Paraphrasing through Answer-Aware Synthetic Question Generation
Despite excellent performance on tasks such as question answering, Transformer-based architectures remain sensitive to syntactic and contextual ambiguities. Question Paraphrasing (QP) offers a promising solution as a mea…
Natural QuestionsQuestion AnsweringQuestion GenerationQuestion-GenerationRelational Graph Representation Learning for Open-Domain Question Answering
We introduce a relational graph neural network with bi-directional attention mechanism and hierarchical representation learning for open-domain question answering task. Our model can learn contextual representation by jo…
Graph Neural NetworkGraph Representation LearningOpen-Domain Question AnsweringQuestion Answering+1Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding
Recent advancements in multimodal large reasoning models (MLRMs) have significantly improved performance in visual question answering. However, we observe that transition words (e.g., because, however, and wait) are clos…
Visual Question Answering