Related papers: FastFiD: Improve Inference Efficiency of Open Doma…
Large transformer-based language models have been shown to be very effective in many classification tasks. However, their computational complexity prevents their use in applications requiring the classification of a large set of candidates.…
Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft…
Keyphrase provides highly-condensed information that can be effectively used for understanding, organizing and retrieving text content. Though previous studies have provided many workable solutions for automated keyphrase extraction, they…
Generating knowledge-intensive and comprehensive long texts, such as encyclopedia articles, remains significant challenges for Large Language Models. It requires not only the precise integration of facts but also the maintenance of thematic…
The goal of this paper is to generate realistic audio with a lightweight and fast diffusion-based vocoder, named FreGrad. Our framework consists of the following three key components: (1) We employ discrete wavelet transform that decomposes…
Question answering (QA) models often rely on large-scale training datasets, which necessitates the development of a data generation framework to reduce the cost of manual annotations. Although several recent studies have aimed to generate…
Documents are central to many business systems, and include forms, reports, contracts, invoices or purchase orders. The information in documents is typically in natural language, but can be organized in various layouts and formats. There…
We propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that (a) maximizes the relevance of the selected sentences, (b) minimizes the overlap between the selected facts, and (c)…
Question answering (QA) is a high-level ability of natural language processing. Most extractive ma-chine reading comprehension models focus on factoid questions (e.g., who, when, where) and restrict the output answer as a short and…
Information retrieval (IR) or knowledge retrieval, is a critical component for many down-stream tasks such as open-domain question answering (QA). It is also very challenging, as it requires succinctness, completeness, and correctness. In…
Traditional information retrieval (such as that offered by web search engines) impedes users with information overload from extensive result pages and the need to manually locate the desired information therein. Conversely,…
The retrieval augmented generation (RAG) framework addresses an ambiguity in user queries in QA systems by retrieving passages that cover all plausible interpretations and generating comprehensive responses based on the passages. However,…
Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model…
Open-domain conversational question answering can be viewed as two tasks: passage retrieval and conversational question answering, where the former relies on selecting candidate passages from a large corpus and the latter requires better…
Detecting an Out-of-Domain (OOD) utterance is crucial for a robust dialog system. Most dialog systems are trained on a pool of annotated OOD data to achieve this goal. However, collecting the annotated OOD data for a given domain is an…
Long-context question-answering (LCQA) systems have greatly benefited from the powerful reasoning capabilities of large language models (LLMs), which can be categorized into slow and quick reasoning modes. However, both modes have their…
A systematic review identifies and collates various clinical studies and compares data elements and results in order to provide an evidence based answer for a particular clinical question. The process is manual and involves lot of time. A…
Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging. Retrieval models on the other hand can surface interesting responses, but are…
Language model fusion helps smart assistants recognize words which are rare in acoustic data but abundant in text-only corpora (typed search logs). However, such corpora have properties that hinder downstream performance, including being…
Natural language (NL) explanations of model predictions are gaining popularity as a means to understand and verify decisions made by large black-box pre-trained models, for NLP tasks such as Question Answering (QA) and Fact Verification.…