Deyi Xiong

Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks

2018 · arXiv (Cornell University)

In this paper, we propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation. The recurrent units of ATR are heavily simplified to have the smallest number of weight matrices among units of …

Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue

2019 · arXiv (Cornell University)

The training of task-oriented dialogue systems is often confronted with the lack of annotated data. In contrast to previous work which augments training data through expensive crowd-sourcing efforts, we propose four different automatic approaches to …

Secoco: Self-Correcting Encoding for Neural Machine Translation

2021 · arXiv (Cornell University)

This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors. Different from previous robust approaches, Secoco enables NMT to explicitly correct noisy …

Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension

2022 · arXiv (Cornell University)

Multilingual pre-trained models are able to zero-shot transfer knowledge from rich-resource to low-resource languages in machine reading comprehension (MRC). However, inherent linguistic discrepancies in different languages could make answer spans predicted by zero-shot transfer violate …

Towards a Deep Understanding of Multilingual End-to-End Speech Translation

2023 · arXiv (Cornell University)

In this paper, we employ Singular Value Canonical Correlation Analysis (SVCCA) to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages. SVCCA enables us to estimate representational similarity across languages …

FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models

2023 · arXiv (Cornell University)

The effective assessment of the instruction-following ability of large language models (LLMs) is of paramount importance. A model that cannot adhere to human instructions might be not able to provide reliable and helpful responses. In …

Debate4MATH: Multi-Agent Debate for Fine-Grained Reasoning in Math

2025

Large language models (LLMs) have demonstrated impressive performance in reasoning.However, existing data annotation methods usually suffer from high annotation cost and the lack of effective automatic validation.To address these issues, we propose a Fine-grained Multi-Agent …

Variational Neural Machine Translation

2016

Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to …

Modeling Source Syntax for Neural Machine Translation

2017

Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly incorporated into …