English
Related papers

Related papers: Shallow Syntax in Deep Water

200 papers

Syntax has been demonstrated highly effective in neural machine translation (NMT). Previous NMT models integrate syntax by representing 1-best tree outputs from a well-trained parsing system, e.g., the representative Tree-RNN and…

Computation and Language · Computer Science 2019-05-09 Meishan Zhang , Zhenghua Li , Guohong Fu , Min Zhang

We design and conduct a simple experiment to study whether neural networks can perform several steps of approximate reasoning in a fixed dimensional latent space. The set of rewrites (i.e. transformations) that can be successfully performed…

Machine Learning · Computer Science 2019-09-27 Dennis Lee , Christian Szegedy , Markus N. Rabe , Sarah M. Loos , Kshitij Bansal

Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and…

Computation and Language · Computer Science 2019-08-15 Yuqi Si , Jingqi Wang , Hua Xu , Kirk Roberts

The low-level sensory and motor signals in deep reinforcement learning, which exist in high-dimensional spaces such as image observations or motor torques, are inherently challenging to understand or utilize directly for downstream tasks.…

Artificial Intelligence · Computer Science 2023-03-07 Pu Hua , Yubei Chen , Huazhe Xu

Deep learning techniques are increasingly popular in the textual entailment task, overcoming the fragility of traditional discrete models with hard alignments and logics. In particular, the recently proposed attention models (Rockt\"aschel…

Computation and Language · Computer Science 2017-09-05 Kai Zhao , Liang Huang , Mingbo Ma

Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words. In this paper, we argue this deprives the LM of crucial syntactic signals that can be detected at high confidence using existing…

Computation and Language · Computer Science 2018-03-13 Duncan Blythe , Alan Akbik , Roland Vollgraf

Vector representations of contextual embeddings learned by pre-trained large language models (LLMs) are effective in various downstream tasks in numerical domains such as time series forecasting. Despite their significant benefits, the…

Computation and Language · Computer Science 2025-06-24 Rashed Shelim , Shengzhe Xu , Walid Saad , Naren Ramakrishnan

We train multi-task autoencoders on linguistic tasks and analyze the learned hidden sentence representations. The representations change significantly when translation and part-of-speech decoders are added. The more decoders a model…

Computation and Language · Computer Science 2018-01-19 Gino Brunner , Yuyi Wang , Roger Wattenhofer , Michael Weigelt

The adaptation of pretrained language models to solve supervised tasks has become a baseline in NLP, and many recent works have focused on studying how linguistic information is encoded in the pretrained sentence representations. Among…

Computation and Language · Computer Science 2021-02-11 Laura Pérez-Mayos , Roberto Carlini , Miguel Ballesteros , Leo Wanner

Large language models (LLMs) represent words through contextual word embeddings encoding different language properties like semantics and syntax. Understanding these properties is crucial, especially for researchers investigating language…

Computation and Language · Computer Science 2025-04-16 Rita Sevastjanova , Robin Gerling , Thilo Spinner , Mennatallah El-Assady

This work lists and describes the main recent strategies for building fixed-length, dense and distributed representations for words, based on the distributional hypothesis. These representations are now commonly called word embeddings and,…

Computation and Language · Computer Science 2023-05-03 Felipe Almeida , Geraldo Xexéo

A growing interest in tasks involving language understanding by the NLP community has led to the need for effective semantic parsing and inference. Modern NLP systems use semantic representations that do not quite fulfill the nuanced needs…

Computation and Language · Computer Science 2019-04-01 Gene Louis Kim , Lenhart Schubert

Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks. However, further increases and…

Computation and Language · Computer Science 2022-05-30 Zhuoyuan Mao , Prakhar Gupta , Pei Wang , Chenhui Chu , Martin Jaggi , Sadao Kurohashi

In-context learning (ICL) is a powerful paradigm where large language models (LLMs) benefit from task demonstrations added to the prompt. Yet, selecting optimal demonstrations is not trivial, especially for complex or multi-modal tasks…

Computation and Language · Computer Science 2024-10-21 Chuhong Mai , Ro-ee Tal , Thahir Mohamed

Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, they almost exclusively focus on text-only representation, while neglecting cell-level layout information that is important…

Computation and Language · Computer Science 2021-05-25 Chenliang Li , Bin Bi , Ming Yan , Wei Wang , Songfang Huang , Fei Huang , Luo Si

Various NLP problems -- such as the prediction of sentence similarity, entailment, and discourse relations -- are all instances of the same general task: the modeling of semantic relations between a pair of textual elements. A popular model…

Computation and Language · Computer Science 2019-04-05 Damien Sileo , Tim Van-De-Cruys , Camille Pradel , Philippe Muller

Linguistic information is encoded at varying timescales (subwords, phrases, etc.) and communicative levels, such as syntax and semantics. Contextualized embeddings have analogously been found to capture these phenomena at distinctive layers…

Computation and Language · Computer Science 2022-10-24 Max Müller-Eberstein , Rob van der Goot , Barbara Plank

Embedding spaces are fundamental to modern AI, translating raw data into high-dimensional vectors that encode rich semantic relationships. Yet, their internal structures remain opaque, with existing approaches often sacrificing semantic…

Artificial Intelligence · Computer Science 2025-12-02 Yandong Sun , Qiang Huang , Ziwei Xu , Yiqun Sun , Yixuan Tang , Anthony K. H. Tung

Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why deep models help NMT is an open question. In this paper, we…

Computation and Language · Computer Science 2020-10-09 Bei Li , Ziyang Wang , Hui Liu , Yufan Jiang , Quan Du , Tong Xiao , Huizhen Wang , Jingbo Zhu

Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decision-making. To support efficient reasoning, recent studies…

Computation and Language · Computer Science 2025-09-03 Jindong Li , Yali Fu , Li Fan , Jiahong Liu , Yao Shu , Chengwei Qin , Menglin Yang , Irwin King , Rex Ying