Search Results for author: Rik Koncel-Kedziorski

Found 21 papers, 10 papers with code

DocFinQA: A Long-Context Financial Reasoning Dataset

no code implementations12 Jan 2024 Varshini Reddy, Rik Koncel-Kedziorski, Viet Dac Lai, Chris Tanner

Research in quantitative reasoning within the financial domain indeed necessitates the use of realistic tasks and data, primarily because of the significant impact of decisions made in business and finance.


BizBench: A Quantitative Reasoning Benchmark for Business and Finance

no code implementations11 Nov 2023 Rik Koncel-Kedziorski, Michael Krumdick, Viet Lai, Varshini Reddy, Charles Lovering, Chris Tanner

We conduct an in-depth evaluation of open-source and commercial LLMs, illustrating that BizBench is a challenging benchmark for quantitative reasoning in the finance and business domain.

Code Generation Program Synthesis +2

Learning Answer Generation using Supervision from Automatic Question Answering Evaluators

no code implementations24 May 2023 Matteo Gabburo, Siddhant Garg, Rik Koncel-Kedziorski, Alessandro Moschitti

Recent studies show that sentence-level extractive QA, i. e., based on Answer Sentence Selection (AS2), is outperformed by Generation-based QA (GenQA) models, which generate answers using the top-k answer sentences ranked by AS2 models (a la retrieval-augmented generation style).

Answer Generation Question Answering +2

Knowledge Transfer from Answer Ranking to Answer Generation

no code implementations23 Oct 2022 Matteo Gabburo, Rik Koncel-Kedziorski, Siddhant Garg, Luca Soldaini, Alessandro Moschitti

In this paper, we propose to train a GenQA model by transferring knowledge from a trained AS2 model, to overcome the aforementioned issue.

Answer Generation Question Answering +2

Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation

no code implementations14 Oct 2021 Benjamin Muller, Luca Soldaini, Rik Koncel-Kedziorski, Eric Lind, Alessandro Moschitti

Our cross-lingual generative system outperforms answer sentence selection baselines for all 5 languages and monolingual generative pipelines for three out of five languages studied.

Answer Generation Generative Question Answering +3

Extracting and Inferring Personal Attributes from Dialogue

1 code implementation NLP4ConvAI (ACL) 2022 Zhilin Wang, Xuhui Zhou, Rik Koncel-Kedziorski, Alex Marin, Fei Xia

Personal attributes represent structured information about a person, such as their hobbies, pets, family, likes and dislikes.

Attribute Language Modelling

Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text

no code implementations ACL 2022 Yao Dou, Maxwell Forbes, Rik Koncel-Kedziorski, Noah A. Smith, Yejin Choi

To support the broad range of real machine errors that can be identified by laypeople, the ten error categories of Scarecrow -- such as redundancy, commonsense errors, and incoherence -- are identified through several rounds of crowd annotation experiments without a predefined ontology.

Math Text Generation

Go Forth and Prosper: Language Modeling with Ancient Textual History

1 code implementation18 Apr 2021 Rik Koncel-Kedziorski, Noah A. Smith

This method can improve perplexity of pretrained LMs with no updates to the LM's own parameters.

Language Modelling

Extracting Summary Knowledge Graphs from Long Documents

1 code implementation19 Sep 2020 Zeqiu Wu, Rik Koncel-Kedziorski, Mari Ostendorf, Hannaneh Hajishirzi

Knowledge graphs capture entities and relations from long documents and can facilitate reasoning in many downstream applications.

Graph Learning Knowledge Graphs +1

A Controllable Model of Grounded Response Generation

1 code implementation1 May 2020 Zeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang, Xiang Gao, Chris Quirk, Rik Koncel-Kedziorski, Jianfeng Gao, Hannaneh Hajishirzi, Mari Ostendorf, Bill Dolan

Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting responses.

Informativeness Response Generation

MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

no code implementations NAACL 2019 Aida Amini, Saadia Gabriel, Peter Lin, Rik Koncel-Kedziorski, Yejin Choi, Hannaneh Hajishirzi

We introduce a new representation language to model precise operation programs corresponding to each math problem that aim to improve both the performance and the interpretability of the learned models.

Math Math Word Problem Solving

Text Generation from Knowledge Graphs with Graph Transformers

3 code implementations NAACL 2019 Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata, Hannaneh Hajishirzi

Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce.

Dialogue Generation KG-to-Text Generation +2

Pyramidal Recurrent Unit for Language Modeling

2 code implementations EMNLP 2018 Sachin Mehta, Rik Koncel-Kedziorski, Mohammad Rastegari, Hannaneh Hajishirzi

We introduce the Pyramidal Recurrent Unit (PRU), which enables learning representations in high dimensional space with more generalization power and fewer parameters.

Language Modelling

Data-Driven Methods for Solving Algebra Word Problems

no code implementations28 Apr 2018 Benjamin Robaidek, Rik Koncel-Kedziorski, Hannaneh Hajishirzi

We explore contemporary, data-driven techniques for solving math word problems over recent large-scale datasets.

Math World Knowledge

Parsing Algebraic Word Problems into Equations

no code implementations TACL 2015 Rik Koncel-Kedziorski, Hannaneh Hajishirzi, Ashish Sabharwal, Oren Etzioni, Siena Dumas Ang

This paper formalizes the problem of solving multi-sentence algebraic word problems as that of generating and scoring equation trees.

Coreference Resolution Sentence

Cannot find the paper you are looking for? You can Submit a new open access paper.