Search Results for author: David Reitter

Found 27 papers, 5 papers with code

Surprisal Predicts Code-Switching in Chinese-English Bilingual Text

no code implementations EMNLP 2020 Jes{\'u}s Calvillo, Le Fang, Jeremy Cole, David Reitter

We also found sentence length to be a significant predictor, which has been related to sentence complexity.

Are BERTs Sensitive to Native Interference in L2 Production?

no code implementations EMNLP (insights) 2021 Zixin Tang, Prasenjit Mitra, David Reitter

With the essays part from The International Corpus Network of Asian Learners of English (ICNALE) and the TOEFL11 corpus, we fine-tuned neural language models based on BERT to predict English learners’ native languages.

KL-Divergence Guided Temperature Sampling

1 code implementation2 Jun 2023 Chung-Ching Chang, David Reitter, Renat Aksitov, Yun-Hsuan Sung

One common approach to mitigate hallucinations is to provide source/grounding documents and the model is trained to produce predictions that bind to and are attributable to the provided source.

Conversational Question Answering Language Modelling +1

How do decoding algorithms distribute information in dialogue responses?

no code implementations29 Mar 2023 Saranya Venkatraman, He He, David Reitter

We find that (i) surprisingly, model-generated responses follow the UID principle to a greater extent than human responses, and (ii) decoding algorithms that promote UID do not generate higher-quality responses.

Dialogue Generation

Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language Models

no code implementations11 Feb 2023 Renat Aksitov, Chung-Ching Chang, David Reitter, Siamak Shakeri, YunHsuan Sung

One common solution to this is augmenting LLMs with a retrieval system and making sure that the generated output is attributable to the retrieved information.


Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence

no code implementations13 Oct 2022 Chris Callison-Burch, Gaurav Singh Tomar, Lara J. Martin, Daphne Ippolito, Suma Bailis, David Reitter

In this paper, we frame D&D specifically as a dialogue system challenge, where the tasks are to both generate the next conversational turn in the game and predict the state of the game given the dialogue history.

Language Modelling Large Language Model

Measuring Attribution in Natural Language Generation Models

1 code implementation23 Dec 2021 Hannah Rashkin, Vitaly Nikolaev, Matthew Lamm, Lora Aroyo, Michael Collins, Dipanjan Das, Slav Petrov, Gaurav Singh Tomar, Iulia Turc, David Reitter

With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world.

Text Generation

CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning

no code implementations16 Dec 2021 Zeqiu Wu, Yi Luan, Hannah Rashkin, David Reitter, Hannaneh Hajishirzi, Mari Ostendorf, Gaurav Singh Tomar

Compared to standard retrieval tasks, passage retrieval for conversational question answering (CQA) poses new challenges in understanding the current user question, as each question needs to be interpreted within the dialogue context.

Conversational Question Answering Passage Retrieval +3

Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark

1 code implementation30 Apr 2021 Nouha Dziri, Hannah Rashkin, Tal Linzen, David Reitter

To this end, we introduce the Benchmark for Evaluation of Grounded INteraction (BEGIN), comprised of 12k dialogue turns generated by neural dialogue systems trained on three knowledge-grounded dialogue corpora.

Language Modelling Natural Language Inference

Do We Need Neural Models to Explain Human Judgments of Acceptability?

no code implementations18 Sep 2019 Wang Jing, M. A. Kelly, David Reitter

We test the ability of computational language models, simple language features, and word embeddings to predict native English speakers judgments of acceptability on English-language essays written by non-native speakers.

Test Word Embeddings +1

Fusion of Detected Objects in Text for Visual Question Answering

1 code implementation IJCNLP 2019 Chris Alberti, Jeffrey Ling, Michael Collins, David Reitter

To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language.

Question Answering Visual Commonsense Reasoning +1

Treat the Word As a Whole or Look Inside? Subword Embeddings Model Language Change and Typology

1 code implementation WS 2019 Yang Xu, Jiasheng Zhang, David Reitter

We use a variant of word embedding model that incorporates subword information to characterize the degree of compositionality in lexical semantics.

The Timing of Lexical Memory Retrievals in Language Production

no code implementations NAACL 2018 Jeremy Cole, David Reitter

This paper explores the time course of lexical memory retrieval by modeling fluent language production.


Learning to Adapt by Minimizing Discrepancy

no code implementations30 Nov 2017 Alexander G. Ororbia II, Patrick Haffner, David Reitter, C. Lee Giles

We investigate the viability of a more neurocognitively-grounded approach in the context of unsupervised generative modeling of sequences.

Event Ordering with a Generalized Model for Sieve Prediction Ranking

no code implementations IJCNLP 2017 Bill McDowell, Nathanael Chambers, Alex Ororbia II, er, David Reitter

Within this prediction reranking framework, we propose an alternative scoring function, showing an 8. 8{\%} relative gain over the original CAEVO.

Word Embeddings

Spectral Analysis of Information Density in Dialogue Predicts Collaborative Task Performance

no code implementations ACL 2017 Yang Xu, David Reitter

We propose a perspective on dialogue that focuses on relative information contributions of conversation partners as a key to successful communication.

Learning Simpler Language Models with the Differential State Framework

no code implementations26 Mar 2017 Alexander G. Ororbia II, Tomas Mikolov, David Reitter

The Differential State Framework (DSF) is a simple and high-performing design that unifies previously introduced gated neural models.

Language Modelling

Online Semi-Supervised Learning with Deep Hybrid Boltzmann Machines and Denoising Autoencoders

no code implementations22 Nov 2015 Alexander G. Ororbia II, C. Lee Giles, David Reitter

Two novel deep hybrid architectures, the Deep Hybrid Boltzmann Machine and the Deep Hybrid Denoising Auto-encoder, are proposed for handling semi-supervised learning problems.


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