Related papers: On the Scalability of the Answer Extraction System…
This paper introduces MIX, a multi-task deep learning approach to solve open-ended question-answering. First, we design our system as a multi-stage pipeline of 3 building blocks: a BM25-based Retriever to reduce the search space, a…
The existing Retrieval-Augmented Generation (RAG) systems face significant challenges in terms of cost and effectiveness. On one hand, they need to encode the lengthy retrieved contexts before responding to the input tasks, which imposes…
Most reinforcement learning (RL) methods focus on learning optimal policies over low-level action spaces. While these methods can perform well in their training environments, they lack the flexibility to transfer to new tasks. Instead, RL…
Real-world document question answering is challenging. Analysts must synthesize evidence across multiple documents and different parts of each document. However, any fixed LLM context window can be exceeded as document collections grow. A…
Extractive methods have been proven effective in automatic document summarization. Previous works perform this task by identifying informative contents at sentence level. However, it is unclear whether performing extraction at sentence…
Achieving personalized alignment requires adapting large language models to each user's evolving context. While decoding-time personalization offers a scalable alternative to training-time methods, existing methods largely rely on implicit,…
Computer-based interactive items have become prevalent in recent educational assessments. In such items, the entire human-computer interactive process is recorded in a log file and is known as the response process. This paper aims at…
Retrieval-Augmented Generation (RAG) systems often rely on fixed top-k document selection mechanisms that ignore downstream generation quality and impose computational overheads. We propose SRAS (Sparse Reward-Aware Selector), a lightweight…
Pre-trained large language models can perform natural language processing downstream tasks by conditioning on human-designed prompts. However, a prompt-based approach often requires "prompt engineering" to design different prompts,…
Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare. The key challenge…
We examine the problem of generating definite noun phrases that are appropriate referring expressions; i.e, noun phrases that (1) successfully identify the intended referent to the hearer whilst (2) not conveying to her any false…
In the context of requirements engineering, relation extraction involves identifying and documenting the associations between different requirements artefacts. When dealing with textual requirements (i.e., requirements expressed using…
Programs for extracting structured information from text, namely information extractors, often operate separately on document segments obtained from a generic splitting operation such as sentences, paragraphs, k-grams, HTTP requests, and so…
The World Wide Web caters to the needs of billions of users in heterogeneous groups. Each user accessing the World Wide Web might have his / her own specific interest and would expect the web to respond to the specific requirements. The…
The performance of Open-Domain Question Answering (ODQA) retrieval systems can exhibit sub-optimal behavior, providing text excerpts with varying degrees of irrelevance. Unfortunately, many existing ODQA datasets lack examples specifically…
We study how document chunking choices impact the reliability of Retrieval-Augmented Generation (RAG) systems in industry. While practice often relies on heuristics, our end-to-end evaluation on Natural Questions systematically varies…
Nowadays, the huge amount of information distributed through the Web motivates studying techniques to be adopted in order to extract relevant data in an efficient and reliable way. Both academia and enterprises developed several approaches…
The performance of relation extraction models has increased considerably with the rise of neural networks. However, a key issue of neural relation extraction is robustness: the models do not scale well to long sentences with multiple…
Term extraction is one of the layers in the ontology development process which has the task to extract all the terms contained in the input document automatically. The purpose of this process is to generate list of terms that are relevant…
Algorithmic solutions have significant potential to improve decision-making across various domains, from healthcare to e-commerce. However, the widespread adoption of these solutions is hindered by a critical challenge: the lack of…