English
Related papers

Related papers: Syntactic Knowledge via Graph Attention with BERT …

200 papers

Aspect-level sentiment classification aims to identify the sentiment polarity towards a specific aspect term in a sentence. Most current approaches mainly consider the semantic information by utilizing attention mechanisms to capture the…

Computation and Language · Computer Science 2021-02-12 Xiaochen Hou , Jing Huang , Guangtao Wang , Xiaodong He , Bowen Zhou

In this paper, we propose a novel method to enhance sentiment analysis by addressing the challenge of context-specific word meanings. It combines the advantages of a BERT model with a knowledge graph based synonym data. This synergy…

Computation and Language · Computer Science 2025-03-20 Kavita Sharma , Ritu Patel , Sunita Iyer

In this paper, we introduce a hybrid search for attention-based neural machine translation (NMT). A target phrase learned with statistical MT models extends a hypothesis in the NMT beam search when the attention of the NMT model focuses on…

Computation and Language · Computer Science 2017-08-11 Leonard Dahlmann , Evgeny Matusov , Pavel Petrushkov , Shahram Khadivi

Multi-graph learning is crucial for extracting meaningful signals from collections of heterogeneous graphs. However, effectively integrating information across graphs with differing topologies, scales, and semantics, often in the absence of…

Machine Learning · Computer Science 2026-02-02 Zahra Moslemi , Ziyi Liang , Norbert Fortin , Babak Shahbaba

This work focuses on analyzing the form and extent of syntactic abstraction captured by BERT by extracting labeled dependency trees from self-attentions. Previous work showed that individual BERT heads tend to encode particular dependency…

Computation and Language · Computer Science 2021-01-01 Tomasz Limisiewicz , Rudolf Rosa , David Mareček

The task of link prediction aims to solve the problem of incomplete knowledge caused by the difficulty of collecting facts from the real world. GCNs-based models are widely applied to solve link prediction problems due to their…

Artificial Intelligence · Computer Science 2022-09-07 Shuanglong Yao , Dechang Pi , Junfu Chen , Yufei Liu , Zhiyuan Wu

Sequence feature embedding is a challenging task due to the unstructuredness of sequence, i.e., arbitrary strings of arbitrary length. Existing methods are efficient in extracting short-term dependencies but typically suffer from…

Machine Learning · Statistics 2021-10-06 Chitta Ranjan , Samaneh Ebrahimi , Kamran Paynabar

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…

Computation and Language · Computer Science 2017-05-03 Junhui Li , Deyi Xiong , Zhaopeng Tu , Muhua Zhu , Min Zhang , Guodong Zhou

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

Computation and Language · Computer Science 2019-02-18 Baosong Yang , Jian Li , Derek Wong , Lidia S. Chao , Xing Wang , Zhaopeng Tu

Since the popularization of the Transformer as a general-purpose feature encoder for NLP, many studies have attempted to decode linguistic structure from its novel multi-head attention mechanism. However, much of such work focused almost…

Computation and Language · Computer Science 2021-01-27 Vinit Ravishankar , Artur Kulmizev , Mostafa Abdou , Anders Søgaard , Joakim Nivre

Existing wisdom demonstrates the significance of syntactic knowledge for the improvement of neural machine translation models. However, most previous works merely focus on leveraging the source syntax in the well-known encoder-decoder…

Computation and Language · Computer Science 2023-05-30 Lei Li , Kai Fan , Lingyu Yang , Hongjia Li , Chun Yuan

Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack…

Computation and Language · Computer Science 2021-06-22 Pei Ke , Haozhe Ji , Yu Ran , Xin Cui , Liwei Wang , Linfeng Song , Xiaoyan Zhu , Minlie Huang

A fundamental question in natural language processing is - what kind of language structure and semantics is the language model capturing? Graph formats such as knowledge graphs are easy to evaluate as they explicitly express language…

Computation and Language · Computer Science 2023-05-10 Kaushik Roy , Tarun Garg , Vedant Palit , Yuxin Zi , Vignesh Narayanan , Amit Sheth

Extracting temporal relations between events and time expressions has many applications such as constructing event timelines and time-related question answering. It is a challenging problem which requires syntactic and semantic information…

Computation and Language · Computer Science 2020-10-06 Hayley Ross , Jonathon Cai , Bonan Min

Much recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. However, the effect of incorporating dependency tree information into pre-trained transformer models (e.g.,…

Computation and Language · Computer Science 2021-01-28 Devendra Singh Sachan , Yuhao Zhang , Peng Qi , William Hamilton

Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph…

Computation and Language · Computer Science 2025-10-17 Juri Opitz , Anette Frank

Graph neural networks (GNN) have recently been applied to exploit knowledge graph (KG) for recommendation. Existing GNN-based methods explicitly model the dependency between an entity and its local graph context in KG (i.e., the set of its…

Information Retrieval · Computer Science 2020-04-27 Susen Yang , Yong Liu , Yonghui Xu , Chunyan Miao , Min Wu , Juyong Zhang

Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlabeled target domain. Existing studies in this task attach more attention to…

Computation and Language · Computer Science 2022-05-19 Kai Zhang , Qi Liu , Zhenya Huang , Mingyue Cheng , Kun Zhang , Mengdi Zhang , Wei Wu , Enhong Chen

GPT-2 and BERT demonstrate the effectiveness of using pre-trained language models (LMs) on various natural language processing tasks. However, LM fine-tuning often suffers from catastrophic forgetting when applied to resource-rich tasks. In…

Computation and Language · Computer Science 2022-06-22 Jiacheng Yang , Mingxuan Wang , Hao Zhou , Chengqi Zhao , Yong Yu , Weinan Zhang , Lei Li

We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on over 3,000 datapoints spanning a wide range of syntactic phenomena, languages, models, and methods.…

Computation and Language · Computer Science 2026-05-28 Nora Graichen , Iria de-Dios-Flores , Gemma Boleda