no code implementations • 9 Jan 2024 • Zilong Wang, Hao Zhang, Chun-Liang Li, Julian Martin Eisenschlos, Vincent Perot, Zifeng Wang, Lesly Miculicich, Yasuhisa Fujii, Jingbo Shang, Chen-Yu Lee, Tomas Pfister
We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts.
Ranked #3 on Table-based Fact Verification on TabFact
1 code implementation • 27 Oct 2023 • James Henderson, Alireza Mohammadshahi, Andrei C. Coman, Lesly Miculicich
We argue that Transformers are essentially graph-to-graph models, with sequences just being a special case.
no code implementations • 26 May 2023 • Ruoxi Sun, Sercan Ö. Arik, Alex Muzio, Lesly Miculicich, Satya Gundabathula, Pengcheng Yin, Hanjun Dai, Hootan Nakhost, Rajarishi Sinha, Zifeng Wang, Tomas Pfister
Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially revolutionizing how humans interact with data.
no code implementations • 9 May 2023 • Lesly Miculicich, Yujia Xie, Song Wang, Pengcheng He
Many applications of text generation such as summarization benefit from accurately controlling the text length.
no code implementations • 20 Jan 2023 • Lesly Miculicich, Benjamin Han
In this paper, we exploit the innate document segment structure for improving the extractive summarization task.
Ranked #4 on Text Summarization on Arxiv HEP-TH citation graph
1 code implementation • 21 Dec 2022 • Wen Xiao, Lesly Miculicich, Yang Liu, Pengcheng He, Giuseppe Carenini
Content-Controllable Summarization generates summaries focused on the given controlling signals.
1 code implementation • Findings (ACL) 2022 • Lesly Miculicich, James Henderson
The state-of-the-art models for coreference resolution are based on independent mention pair-wise decisions.
Ranked #8 on Coreference Resolution on OntoNotes
no code implementations • 19 Nov 2019 • Dhananjay Ram, Lesly Miculicich, Hervé Bourlard
Here, we show that the CNN based matching outperforms DTW based matching using bottleneck features as well.
no code implementations • WS 2019 • Lesly Miculicich, Marc Marone, Hany Hassan
In this paper, we report our system submissions to all 6 tracks of the WNGT 2019 shared task on Document-Level Generation and Translation.
no code implementations • COLING (CRAC) 2020 • Lesly Miculicich, James Henderson
Learning to detect entity mentions without using syntactic information can be useful for integration and joint optimization with other tasks.
no code implementations • 30 Jun 2019 • Dhananjay Ram, Lesly Miculicich, Hervé Bourlard
State of the art solutions to query by example spoken term detection (QbE-STD) usually rely on bottleneck feature representation of the query and audio document to perform dynamic time warping (DTW) based template matching.
2 code implementations • EMNLP 2018 • Lesly Miculicich, Dhananjay Ram, Nikolaos Pappas, James Henderson
Neural Machine Translation (NMT) can be improved by including document-level contextual information.