English
Related papers

Related papers: Inducing Syntactic Trees from BERT Representations

200 papers

Studies across many disciplines have shown that lexical choice can affect audience perception. For example, how users describe themselves in a social media profile can affect their perceived socio-economic status. However, we lack general…

Machine Learning · Computer Science 2018-11-16 Zhao Wang , Aron Culotta

In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequentially and neglect long-distance dependencies. To exploit both…

Computation and Language · Computer Science 2015-08-04 Mingbo Ma , Liang Huang , Bing Xiang , Bowen Zhou

Representing text into a multidimensional space can be done with sentence embedding models such as Sentence-BERT (SBERT). However, training these models when the data has a complex multilevel structure requires individually trained…

Computation and Language · Computer Science 2023-05-11 Paolo Tirotta , Akira Yuasa , Masashi Morita

The grammar representation of a narrowing tree for a syntactically deterministic conditional term rewriting system and a pair of terms is a regular tree grammar that generates expressions for substitutions obtained by all possible…

Logic in Computer Science · Computer Science 2019-02-25 Naoki Nishida , Yuya Maeda

Pretrained neural models such as BERT, when fine-tuned to perform natural language inference (NLI), often show high accuracy on standard datasets, but display a surprising lack of sensitivity to word order on controlled challenge sets. We…

Computation and Language · Computer Science 2020-04-28 Junghyun Min , R. Thomas McCoy , Dipanjan Das , Emily Pitler , Tal Linzen

Recent work has shown the surprising ability of multi-lingual BERT to serve as a zero-shot cross-lingual transfer model for a number of language processing tasks. We combine this finding with a similarly-recently proposal on sentence-level…

Information Retrieval · Computer Science 2019-11-11 Peng Shi , Jimmy Lin

Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data. Most recent analysis has focused…

Computation and Language · Computer Science 2019-06-12 Kevin Clark , Urvashi Khandelwal , Omer Levy , Christopher D. Manning

Instruction-based suppression is widely used to prevent language models from generating prohibited content, yet it remains unclear whether suppression reduces internal representation or merely suppresses expression. We investigate this…

Computation and Language · Computer Science 2026-05-28 Rebecca Ramnauth , Brian Scassellati

Classifiers tend to propagate biases present in the data on which they are trained. Hence, it is important to understand how the demographic identities of the annotators of comments affect the fairness of the resulting model. In this paper,…

Computation and Language · Computer Science 2021-06-07 Elizabeth Excell , Noura Al Moubayed

This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture…

Computation and Language · Computer Science 2014-01-23 Trevor Anthony Cohn , Mirella Lapata

Much like sentences are composed of words, words themselves are composed of smaller units. For example, the English word questionably can be analyzed as question+able+ly. However, this structural decomposition of the word does not directly…

Computation and Language · Computer Science 2018-11-13 Ryan Cotterell , Hinrich Schütze

Usage similarity estimation addresses the semantic proximity of word instances in different contexts. We apply contextualized (ELMo and BERT) word and sentence embeddings to this task, and propose supervised models that leverage these…

Computation and Language · Computer Science 2019-05-22 Aina Garí Soler , Marianna Apidianaki , Alexandre Allauzen

Pre-trained contextualized embedding models such as BERT are a standard building block in many natural language processing systems. We demonstrate that the sentence-level representations produced by some off-the-shelf contextualized…

Computation and Language · Computer Science 2022-06-06 Xiliang Zhu , David Rossouw , Shayna Gardiner , Simon Corston-Oliver

Abbreviations and contractions are commonly found in text across different domains. For example, doctors' notes contain many contractions that can be personalized based on their choices. Existing spelling correction models are not suitable…

Computation and Language · Computer Science 2022-07-11 Prateek Kacker , Andi Cupallari , Aswin Gridhar Subramanian , Nimit Jain

While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear what aspects of…

Computation and Language · Computer Science 2021-04-16 Matteo Alleman , Jonathan Mamou , Miguel A Del Rio , Hanlin Tang , Yoon Kim , SueYeon Chung

Lexical simplification (LS) aims to replace complex words in a given sentence with their simpler alternatives of equivalent meaning, to simplify the sentence. Recently unsupervised lexical simplification approaches only rely on the complex…

Computation and Language · Computer Science 2020-06-29 Jipeng Qiang , Yun Li , Yi Zhu , Yunhao Yuan , Xindong Wu

Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific level of linguistic unit, which cause great inconvenience when being confronted with handling multiple…

Computation and Language · Computer Science 2020-09-11 Yian Li , Hai Zhao

Variants of the BERT architecture specialised for producing full-sentence representations often achieve better performance on downstream tasks than sentence embeddings extracted from vanilla BERT. However, there is still little…

Computation and Language · Computer Science 2023-01-31 Dmitry Nikolaev , Sebastian Padó

Transformer-based language models have recently achieved remarkable results in many natural language tasks. However, performance on leaderboards is generally achieved by leveraging massive amounts of training data, and rarely by encoding…

Computation and Language · Computer Science 2022-07-21 Bai Li

We describe, analyze, and evaluate experimentally a new probabilistic model for word-sequence prediction in natural language based on prediction suffix trees (PSTs). By using efficient data structures, we extend the notion of PST to…

cmp-lg · Computer Science 2008-02-03 Fernando C. N. Pereira , Yoram Singer , Naftali Tishby