Search Results for author:
Found 27 papers, 5 papers with code
Surprisal Predicts Code-Switching in Chinese-English Bilingual Text
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?
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
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.
How do decoding algorithms distribute information in dialogue responses?
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.
Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language Models
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
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.
Measuring Attribution in Natural Language Generation Models
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.
CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
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.
Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features
At training time, additional inputs based on these evaluation measures are given to the dialogue model.
Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark
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.
Do We Need Neural Models to Explain Human Judgments of Acceptability?
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.
Fusion of Detected Objects in Text for Visual Question Answering
To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language.
Treat the Word As a Whole or Look Inside? Subword Embeddings Model Language Change and Typology
We use a variant of word embedding model that incorporates subword information to characterize the degree of compositionality in lexical semantics.
Not that much power: Linguistic alignment is influenced more by low-level linguistic features rather than social power
Linguistic alignment between dialogue partners has been claimed to be affected by their relative social power.
The Timing of Lexical Memory Retrievals in Language Production
This paper explores the time course of lexical memory retrieval by modeling fluent language production.
Like a Baby: Visually Situated Neural Language Acquisition
We examine the benefits of visual context in training neural language models to perform next-word prediction.
Learning to Adapt by Minimizing Discrepancy
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
Within this prediction reranking framework, we propose an alternative scoring function, showing an 8. 8{\%} relative gain over the original CAEVO.
Spectral Analysis of Information Density in Dialogue Predicts Collaborative Task Performance
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
The Differential State Framework (DSF) is a simple and high-performing design that unifies previously introduced gated neural models.
Online Semi-Supervised Learning with Deep Hybrid Boltzmann Machines and Denoising Autoencoders
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.
