---
title: "Qun Liu — papers, page 2 · Brookhaven National Laboratory"
description: "Qun Liu, Brookhaven National Laboratory: 30 papers on Elamur Research (2003–2026), h-index 26 — affiliations, topics, co-authors and who…"
canonical: "https://research.elamur.ai/free/en/authors/qun-liu/page/2/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/qun-liu/page/2/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Qun Liu](https://md.research.elamur.ai/free/en/authors/qun-liu/) / page 2

# Qun Liu · page 2

30 papers in our library · 2003–2026 · page 2 of 2

[The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/qun-liu/)

## Papers

The most cited first (OpenAlex and our library).

[← prev](https://md.research.elamur.ai/free/en/authors/qun-liu/) [1](https://md.research.elamur.ai/free/en/authors/qun-liu/) **2**

26. **[Sub-Character Tokenization for Chinese Pretrained Language Models](https://md.research.elamur.ai/free/en/papers/si-2023-sub-character-tokenization-chinese-pretrained/)** *(2023 · 29 citations)* Chinese pretrained language models usually tokenize text either one character at a time or by running sub-word algorithms directly on raw characters.
27. **[RED: A Reference Dependency Based MT Evaluation Metric](https://md.research.elamur.ai/free/en/papers/yu-2014-red-reference-dependency-based-mt/)** *(2014 · 28 citations)* RED parses only the reference, never the hypothesis, so that parsing noise from the MT output does not enter the score.
28. **[The DCU Discourse Parser for Connective, Argument Identification and Explicit Sense Classification](https://md.research.elamur.ai/free/en/papers/wang-2015-dcu-discourse-parser-connective-argument/)** *(2015 · 18 citations)* This paper presents Dublin City University's entry to the CoNLL-2015 shared task on shallow discourse parsing.
29. **[JABER and SABER: Junior and Senior Arabic BERt](https://md.research.elamur.ai/free/en/papers/ghaddar-2021-jaber-saber-junior-senior-arabic/)** *(2021 · 16 citations)* Before this work, several Arabic BERT models were public, but they had been compared under inconsistent settings. The authors also argue that most of them were trained for too short a time. They built two new Arabic models with the same recipe: JABER, a 12-layer base model, and SABER, a 24-layer large model.
30. **[Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents](https://md.research.elamur.ai/free/en/papers/wang-2026-trajectory2task-training-robust-tool-calling/)** *(2026 · 2 citations)* Tool-calling agents used in customer service often meet users whose requests lack key details, shift during the conversation, or break system policy.

[← prev](https://md.research.elamur.ai/free/en/authors/qun-liu/) [1](https://md.research.elamur.ai/free/en/authors/qun-liu/) **2**