AIConfPaper
← Search

Reinald Kim Amplayo

10 accepted papers

2025

Agents' Room: Narrative Generation through Multi-step Collaboration

Fantine Huot, Reinald Kim Amplayo, Jennimaria Palomaki, Alice Shoshana Jakobovits, Elizabeth Clark, Mirella Lapata
ICLR 2025poster

Writing compelling fiction is a multifaceted process combining elements such as crafting a plot, developing interesting characters, and using evocative language. While large language models (LLMs) show promise for story writing, they currently rely heavily on intricate prompting, which limits their…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2024

Learning to Plan and Generate Text with Citations

Constanza Fierro, Reinald Kim Amplayo, Fantine Huot, Nicola De Cao, Joshua Maynez, Shashi Narayan +1
ACL 2024long

The increasing demand for the deployment of LLMs in information-seeking scenarios has spurred efforts in creating verifiable systems, which generate responses to queries along with supporting evidence. In this paper, we explore the attribution capabilities of plan-based models which have been recent…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2024

Scalable and Domain-General Abstractive Proposition Segmentation

Mohammad Javad Hosseini, Yang Gao, Tim Baumgärtner, Alex Fabrikant, Reinald Kim Amplayo
EMNLP 2024finding

Segmenting text into fine-grained units of meaning is important to a wide range of NLP applications. The default approach of segmenting text into sentences is often insufficient, especially since sentences are usually complex enough to include multiple units of meaning that merit separate treatment…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

Query Refinement Prompts for Closed-Book Long-Form QA

Reinald Kim Amplayo, Kellie Webster, Michael Collins, Dipanjan Das, Shashi Narayan
ACL 2023long

Large language models (LLMs) have been shown to perform well in answering questions and in producing long-form texts, both in few-shot closed-book settings. While the former can be validated using well-known evaluation metrics, the latter is difficult to evaluate. We resolve the difficulties to eval…

Cited by 0Source ↗PDF ↗Scholar ↗
2022

Attribute Injection for Pretrained Language Models: A New Benchmark and an Efficient Method

Reinald Kim Amplayo, Kang Min Yoo, Sang-Woo Lee
COLING 2022main

Metadata attributes (e.g., user and product IDs from reviews) can be incorporated as additional inputs to neural-based NLP models, by expanding the architecture of the models to improve performance. However, recent models rely on pretrained language models (PLMs), in which previously used techniques…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2022

Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning

Yu Jin Kim, Beong-woo Kwak, Youngwook Kim, Reinald Kim Amplayo, Seung-won Hwang, Jinyoung Yeo
NAACL 2022long

Commonsense reasoning systems should be able to generalize to diverse reasoning cases. However, most state-of-the-art approaches depend on expensive data annotations and overfit to a specific benchmark without learning how to perform general semantic reasoning. To overcome these drawbacks, zero-shot…

Cited by 16Source ↗PDF ↗Scholar ↗
2021

Unsupervised Opinion Summarization with Content Planning

Reinald Kim Amplayo, Stefanos Angelidis, Mirella Lapata
AAAI 2021technical

The recent success of deep learning techniques for abstractive summarization is predicated on the availability of large-scale datasets. When summarizing reviews (e.g., for products or movies), such training data is neither available nor can be easily sourced, motivating the development of methods w…

Cited by 57Source ↗PDF ↗code ↗Scholar ↗
2020

Retrieval-Augmented Controllable Review Generation

Jihyeok Kim, Seungtaek Choi, Reinald Kim Amplayo, Seung-won Hwang
COLING 2020main

In this paper, we study review generation given a set of attribute identifiers which are user ID, product ID and rating. This is a difficult subtask of natural language generation since models are limited to the given identifiers, without any specific descriptive information regarding the inputs, wh…

Cited by 25Source ↗PDF ↗Scholar ↗