Related papers: Globally Normalized Reader
Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first…
We introduce the Globally Normalized Autoregressive Transducer (GNAT) for addressing the label bias problem in streaming speech recognition. Our solution admits a tractable exact computation of the denominator for the sequence-level…
While both extractive and generative readers have been successfully applied to the Question Answering (QA) task, little attention has been paid toward the systematic comparison of them. Characterizing the strengths and weaknesses of the two…
Given a graph with textual attributes, we enable users to `chat with their graph': that is, to ask questions about the graph using a conversational interface. In response to a user's questions, our method provides textual replies and…
Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge…
Recurrent neural networks are now the state-of-the-art in natural language processing because they can build rich contextual representations and process texts of arbitrary length. However, recent developments on attention mechanisms have…
Nielsen transformation is a standard approach for solving word equations: by repeatedly splitting equations and applying simplification steps, equations are rewritten until a solution is reached. When solving a conjunction of word equations…
In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing. Instead of predicting a probability, our model predicts a real-valued score at each step and does not suffer from the label bias…
Query-focused summarization (QFS) aims to provide a summary of a document that satisfies information need of a given query and is useful in various IR applications, such as abstractive snippet generation. Current QFS approaches typically…
Despite the rapid progress of large language models (LLMs), knowledge graph-based question answering (KGQA) remains essential for producing verifiable and hallucination-resistant answers in many real-world settings where answer…
This work studies the global convergence and implicit bias of Gauss Newton's (GN) when optimizing over-parameterized one-hidden layer networks in the mean-field regime. We first establish a global convergence result for GN in the…
Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multi-hop generative task (NarrativeQA), which requires the model to…
Recently, researches have explored the graph neural network (GNN) techniques on text classification, since GNN does well in handling complex structures and preserving global information. However, previous methods based on GNN are mainly…
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…
Retrieval-augmented generation (RAG) has emerged as a leading approach to reducing hallucinations in large language models (LLMs). Current RAG evaluation benchmarks primarily focus on what we call local RAG: retrieving relevant chunks from…
Event argument extraction has long been studied as a sequential prediction problem with extractive-based methods, tackling each argument in isolation. Although recent work proposes generation-based methods to capture cross-argument…
Retrieval augmented generation has revolutionized large language model (LLM) outputs by providing factual supports. Nevertheless, it struggles to capture all the necessary knowledge for complex reasoning questions. Existing retrieval…
Information Retriever (IR) aims to find the relevant documents (e.g. snippets, passages, and articles) to a given query at large scale. IR plays an important role in many tasks such as open domain question answering and dialogue systems,…
The generalized Gauss-Newton (GGN) approximation is often used to make practical Bayesian deep learning approaches scalable by replacing a second order derivative with a product of first order derivatives. In this paper we argue that the…
Iterative RAG for multi-hop question answering faces challenges with lengthy contexts and the buildup of irrelevant information. This hinders a model's capacity to process and reason over retrieved content and limits performance. While…