English
Related papers

Related papers: Latent Tree Learning with Ordered Neurons: What Pa…

200 papers

In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of…

Machine Learning · Computer Science 2019-12-04 Jeremy Gordon , David Rawlinson , Subutai Ahmad

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…

Computation and Language · Computer Science 2018-08-30 Haoyue Shi , Hao Zhou , Jiaze Chen , Lei Li

The success of pretrained contextual encoders, such as ELMo and BERT, has brought a great deal of interest in what these models learn: do they, without explicit supervision, learn to encode meaningful notions of linguistic structure? If so,…

Computation and Language · Computer Science 2020-10-12 Julian Michael , Jan A. Botha , Ian Tenney

Discourse structure is integral to understanding a text and is helpful in many NLP tasks. Learning latent representations of discourse is an attractive alternative to acquiring expensive labeled discourse data. Liu and Lapata (2018) propose…

Computation and Language · Computer Science 2019-06-11 Elisa Ferracane , Greg Durrett , Junyi Jessy Li , Katrin Erk

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and…

Computation and Language · Computer Science 2017-10-02 Mingbo Ma , Kai Zhao , Liang Huang , Bing Xiang , Bowen Zhou

Language exhibits inherent structures, a property that explains both language acquisition and language change. Given this characteristic, we expect language models to manifest their own internal structures as well. While interpretability…

Computation and Language · Computer Science 2026-05-19 Haruki Sakajo , Frederikus Hudi , Yusuke Sakai , Hidetaka Kamigaito , Taro Watanabe

When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems…

Computation and Language · Computer Science 2022-11-07 Shikhar Murty , Pratyusha Sharma , Jacob Andreas , Christopher D. Manning

We explore neural language modeling for speech recognition where the context spans multiple sentences. Rather than encode history beyond the current sentence using a cache of words or document-level features, we focus our study on the…

Computation and Language · Computer Science 2019-11-13 Sarangarajan Parthasarathy , William Gale , Xie Chen , George Polovets , Shuangyu Chang

The need for tree structure modelling on top of sequence modelling is an open issue in neural dependency parsing. We investigate the impact of adding a tree layer on top of a sequential model by recursively composing subtree representations…

Computation and Language · Computer Science 2019-02-27 Miryam de Lhoneux , Miguel Ballesteros , Joakim Nivre

What can large language models learn? By definition, language models (LM) are distributions over strings. Therefore, an intuitive way of addressing the above question is to formalize it as a matter of learnability of classes of…

Computation and Language · Computer Science 2025-01-14 Nadav Borenstein , Anej Svete , Robin Chan , Josef Valvoda , Franz Nowak , Isabelle Augenstein , Eleanor Chodroff , Ryan Cotterell

Despite the popularity of deep learning, structure learning for deep models remains a relatively under-explored area. In contrast, structure learning has been studied extensively for probabilistic graphical models (PGMs). In particular, an…

Machine Learning · Computer Science 2018-03-19 Zhourong Chen , Xiaopeng Li , Nevin L. Zhang

In this paper, we investigate to which extent contextual neural language models (LMs) implicitly learn syntactic structure. More concretely, we focus on constituent structure as represented in the Penn Treebank (PTB). Using standard probing…

Computation and Language · Computer Science 2022-04-14 David Arps , Younes Samih , Laura Kallmeyer , Hassan Sajjad

Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate…

Computation and Language · Computer Science 2023-06-27 Chuyuan Li , Patrick Huber , Wen Xiao , Maxime Amblard , Chloé Braud , Giuseppe Carenini

The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities. Linguistic regularities are often sensitive to syntactic…

Computation and Language · Computer Science 2016-11-07 Tal Linzen , Emmanuel Dupoux , Yoav Goldberg

Recursive neural models, which use syntactic parse trees to recursively generate representations bottom-up, are a popular architecture. But there have not been rigorous evaluations showing for exactly which tasks this syntax-based method is…

Artificial Intelligence · Computer Science 2015-08-19 Jiwei Li , Minh-Thang Luong , Dan Jurafsky , Eudard Hovy

We suggest a compositional vector representation of parse trees that relies on a recursive combination of recurrent-neural network encoders. To demonstrate its effectiveness, we use the representation as the backbone of a greedy, bottom-up…

Computation and Language · Computer Science 2018-04-25 Eliyahu Kiperwasser , Yoav Goldberg

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Computation and Language · Computer Science 2025-09-29 Zheng Wei Lim , Alham Fikri Aji , Trevor Cohn

Sequence-based neural networks show significant sensitivity to syntactic structure, but they still perform less well on syntactic tasks than tree-based networks. Such tree-based networks can be provided with a constituency parse, a…

Computation and Language · Computer Science 2020-05-04 Michael A. Lepori , Tal Linzen , R. Thomas McCoy

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Computation and Language · Computer Science 2025-02-27 Sumanta Bhattacharyya , Pedram Rooshenas

Both bottom-up and top-down strategies have been used for neural transition-based constituent parsing. The parsing strategies differ in terms of the order in which they recognize productions in the derivation tree, where bottom-up…

Computation and Language · Computer Science 2017-07-18 Jiangming Liu , Yue Zhang