English
Related papers

Related papers: Sneaking Syntax into Transformer Language Models w…

200 papers

Pretrained language models (PLM) have recently advanced graph-to-text generation, where the input graph is linearized into a sequence and fed into the PLM to obtain its representation. However, efficiently encoding the graph structure in…

Computation and Language · Computer Science 2021-09-09 Leonardo F. R. Ribeiro , Yue Zhang , Iryna Gurevych

Recurrent neural networks (RNNs) process input text sequentially and model the conditional transition between word tokens. In contrast, the advantages of recursive networks include that they explicitly model the compositionality and the…

Computation and Language · Computer Science 2017-03-01 Tsendsuren Munkhdalai , Hong Yu

The recent development of diffusion models has led to significant progress in solving inverse problems by leveraging these models as powerful generative priors. However, challenges persist due to the ill-posed nature of such problems, often…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Jeongsol Kim , Geon Yeong Park , Hyungjin Chung , Jong Chul Ye

Recently, the emergence of large language models (LLMs) has motivated integrating language descriptions into graphs, forming text-attributed graphs (TAGs) that enhance model encoding capabilities from a data-centric perspective. A review of…

Machine Learning · Computer Science 2026-02-03 Zhihan Zhang , Xunkai Li , Lei Zhu , Guang Zeng , Bowen Fan , Yanzhe Wen , Hongchao Qin , Rong-Hua Li , Guoren Wang

Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of their inductive biases and how those biases differ from other neural network architectures remains elusive. In this work, we identify…

Machine Learning · Computer Science 2025-02-14 Bhavya Vasudeva , Deqing Fu , Tianyi Zhou , Elliott Kau , Youqi Huang , Vatsal Sharan

Syntax has been shown useful for various NLP tasks, while existing work mostly encodes singleton syntactic tree using one hierarchical neural network. In this paper, we investigate a simple and effective method, Knowledge Distillation, to…

Computation and Language · Computer Science 2020-09-17 Hao Fei , Yafeng Ren , Donghong Ji

Lattices are compact representations that encode multiple hypotheses, such as speech recognition results or different word segmentations. It is shown that encoding lattices as opposed to 1-best results generated by automatic speech…

Computation and Language · Computer Science 2020-11-03 Chao-Wei Huang , Yun-Nung Chen

While most neural generative models generate outputs in a single pass, the human creative process is usually one of iterative building and refinement. Recent work has proposed models of editing processes, but these mostly focus on editing…

Machine Learning · Computer Science 2021-03-08 Ziyu Yao , Frank F. Xu , Pengcheng Yin , Huan Sun , Graham Neubig

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Computation and Language · Computer Science 2024-08-30 Davis Yoshida

The paper investigates the use of richer syntactic dependencies in the structured language model (SLM). We present two simple methods of enriching the dependencies in the syntactic parse trees used for intializing the SLM. We evaluate the…

Computation and Language · Computer Science 2007-05-23 Ciprian Chelba , Peng Xu

The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance,…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Lin Song , Yanwei Li , Zhengkai Jiang , Zeming Li , Xiangyu Zhang , Hongbin Sun , Jian Sun , Nanning Zheng

Pre-trained language models have demonstrated impressive performance in both natural language processing and program understanding, which represent the input as a token sequence without explicitly modeling its structure. Some prior works…

Computation and Language · Computer Science 2022-10-27 Da Shen , Xinyun Chen , Chenguang Wang , Koushik Sen , Dawn Song

A new language model for speech recognition is presented. The model develops hidden hierarchical syntactic-like structure incrementally and uses it to extract meaningful information from the word history, thus complementing the locality of…

Computation and Language · Computer Science 2007-05-23 Ciprian Chelba , Frederick Jelinek

Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence…

Computation and Language · Computer Science 2018-04-18 Nikita Nangia , Samuel R. Bowman

As a cornerstone in language modeling, tokenization involves segmenting text inputs into pre-defined atomic units. Conventional statistical tokenizers often disrupt constituent boundaries within words, thereby corrupting semantic…

Computation and Language · Computer Science 2025-07-11 Qingyang Zhu , Xiang Hu , Pengyu Ji , Wei Wu , Kewei Tu

A substantial thread of recent work on latent tree learning has attempted to develop neural network models with parse-valued latent variables and train them on non-parsing tasks, in the hope of having them discover interpretable tree…

Computation and Language · Computer Science 2018-08-31 Phu Mon Htut , Kyunghyun Cho , Samuel R. Bowman

Data augmentation is an effective approach to tackle over-fitting. Many previous works have proposed different data augmentations strategies for NLP, such as noise injection, word replacement, back-translation etc. Though effective, they…

Computation and Language · Computer Science 2022-07-13 Le Zhang , Zichao Yang , Diyi Yang

Network intrusion detection (NID) systems which leverage machine learning have been shown to have strong performance in practice when used to detect malicious network traffic. Decision trees in particular offer a strong balance between…

Computation and Language · Computer Science 2023-10-31 Noah Ziems , Gang Liu , John Flanagan , Meng Jiang

Recent works on structured text translation remain limited to the sentence level, as they struggle to effectively handle the complex document-level XML or HTML structures. To address this, we propose \textbf{Format Reinforcement Learning…

Computation and Language · Computer Science 2025-12-05 Haiyue Song , Johannes Eschbach-Dymanus , Hour Kaing , Sumire Honda , Hideki Tanaka , Bianka Buschbeck , Masao Utiyama

The primary goal in this thesis is to identify better syntactic constraint or bias, that is language independent but also efficiently exploitable during sentence processing. We focus on a particular syntactic construction called…

Computation and Language · Computer Science 2016-08-02 Hiroshi Noji