Related papers: Exploiting Rich Syntax for Better Knowledge Base Q…
Retrieval augmented language models have recently become the standard for knowledge intensive tasks. Rather than relying purely on latent semantics within the parameters of large neural models, these methods enlist a semi-parametric memory…
Multi-hop Knowledge Base Question Answering(KBQA) aims to find the answer entity in a knowledge base which is several hops from the topic entity mentioned in the question. Existing Retrieval-based approaches first generate instructions from…
We study open-domain question answering with structured, unstructured and semi-structured knowledge sources, including text, tables, lists and knowledge bases. Departing from prior work, we propose a unifying approach that homogenizes all…
Knowledge graph question answering (KGQA) involves answering natural language questions by leveraging structured information stored in a knowledge graph. Typically, KGQA initially retrieve a targeted subgraph from a large-scale knowledge…
Reading comprehension models are based on recurrent neural networks that sequentially process the document tokens. As interest turns to answering more complex questions over longer documents, sequential reading of large portions of text…
We describe a unified and coherent syntactic framework for supporting a semantically-informed syntactic approach to statistical machine translation. Semantically enriched syntactic tags assigned to the target-language training texts…
End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs. There are two challenges for such systems: one is how to effectively incorporate external knowledge bases (KBs) into the learning…
Question answering over knowledge bases is considered a difficult problem due to the challenge of generalizing to a wide variety of possible natural language questions. Additionally, the heterogeneity of knowledge base schema items between…
Knowledge graph (KG) is known to be helpful for the task of question answering (QA), since it provides well-structured relational information between entities, and allows one to further infer indirect facts. However, it is challenging to…
Recently, unsupervised parsing of syntactic trees has gained considerable attention. A prototypical approach to such unsupervised parsing employs reinforcement learning and auto-encoders. However, no mechanism ensures that the learnt model…
We develop a unified system to answer directly from text open-domain questions that may require a varying number of retrieval steps. We employ a single multi-task transformer model to perform all the necessary subtasks -- retrieving…
Syntax has been shown to benefit Coreference Resolution from incorporating long-range dependencies and structured information captured by syntax trees, either in traditional statistical machine learning based systems or recently proposed…
With the rapid growth of knowledge bases (KBs), question answering over knowledge base, a.k.a. KBQA has drawn huge attention in recent years. Most of the existing KBQA methods follow so called encoder-compare framework. They map the…
We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. This is achieved by employing separate encoders for the sequential and parsed versions of the same source…
In this paper, we propose a novel Knowledge-based Embodied Question Answering (K-EQA) task, in which the agent intelligently explores the environment to answer various questions with the knowledge. Different from explicitly specifying the…
Recently, large language models (LLMs) have demonstrated impressive performance in Knowledge Graph Question Answering (KGQA) tasks, which aim to find answers based on knowledge graphs (KGs) for natural language questions. Existing…
Machine comprehension question answering, which finds an answer to the question given a passage, involves high-level reasoning processes of understanding and tracking the relevant contents across various semantic units such as words,…
Existing KBQA methods have traditionally relied on multi-stage methodologies, involving tasks such as entity linking, subgraph retrieval and query structure generation. However, multi-stage approaches are dependent on the accuracy of…
Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA datasets are mostly…
Multimodal Large Language Models (MLLMs) have pushed the frontiers of Knowledge-Based Visual Question Answering (KBVQA), yet their reasoning is fundamentally bottlenecked by a reliance on uni-dimensional evidence. This "seeing only the…