English
Related papers

Related papers: How Language Models Prioritize Contextual Grammati…

200 papers

Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…

Computation and Language · Computer Science 2020-10-13 Mengjie Zhao , Philipp Dufter , Yadollah Yaghoobzadeh , Hinrich Schütze

While finetuning language models from pairwise preferences has proven remarkably effective, the underspecified nature of natural language presents critical challenges. Direct preference feedback is uninterpretable, difficult to provide…

Computation and Language · Computer Science 2024-11-07 Silviu Pitis , Ziang Xiao , Nicolas Le Roux , Alessandro Sordoni

The pre-trained BERT model achieves a remarkable state of the art across a wide range of tasks in natural language processing. For solving the gender bias in gendered pronoun resolution task, I propose a novel neural network model based on…

Computation and Language · Computer Science 2019-08-02 Zili Wang

One of the most remarkable properties of word embeddings is the fact that they capture certain types of semantic and syntactic relationships. Recently, pre-trained language models such as BERT have achieved groundbreaking results across a…

Computation and Language · Computer Science 2019-12-02 Zied Bouraoui , Jose Camacho-Collados , Steven Schockaert

The use of transfer learning methods is largely responsible for the present breakthrough in Natural Learning Processing (NLP) tasks across multiple domains. In order to solve the problem of sentiment detection, we examined the performance…

Computation and Language · Computer Science 2023-07-05 Olumide Ebenezer Ojo , Hoang Thang Ta , Alexander Gelbukh , Hiram Calvo , Olaronke Oluwayemisi Adebanji , Grigori Sidorov

In English semantic similarity tasks, classic word embedding-based approaches explicitly model pairwise "interactions" between the word representations of a sentence pair. Transformer-based pretrained language models disregard this notion,…

Computation and Language · Computer Science 2019-11-11 Yinan Zhang , Raphael Tang , Jimmy Lin

Generated hateful and toxic content by a portion of users in social media is a rising phenomenon that motivated researchers to dedicate substantial efforts to the challenging direction of hateful content identification. We not only need an…

Social and Information Networks · Computer Science 2019-10-29 Marzieh Mozafari , Reza Farahbakhsh , Noel Crespi

Pre-training by language modeling has become a popular and successful approach to NLP tasks, but we have yet to understand exactly what linguistic capacities these pre-training processes confer upon models. In this paper we introduce a…

Computation and Language · Computer Science 2020-07-14 Allyson Ettinger

Recognizing and categorizing lexical collocations in context is useful for language learning, dictionary compilation and downstream NLP. However, it is a challenging task due to the varying degrees of frozenness lexical collocations…

Computation and Language · Computer Science 2022-05-24 Luis Espinosa-Anke , Alexander Shvets , Alireza Mohammadshahi , James Henderson , Leo Wanner

Large language models can produce powerful contextual representations that lead to improvements across many NLP tasks. Since these models are typically guided by a sequence of learned self attention mechanisms and may comprise undesired…

Computation and Language · Computer Science 2019-10-14 Benjamin Hoover , Hendrik Strobelt , Sebastian Gehrmann

Estimation of semantic similarity is an important research problem both in natural language processing and the natural language understanding, and that has tremendous application on various downstream tasks such as question answering,…

Computation and Language · Computer Science 2025-06-24 R. Prashanth

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the…

Computation and Language · Computer Science 2019-06-20 Jesse Vig , Yonatan Belinkov

This paper explores the ability of Transformer models to capture subject-verb and noun-adjective agreement dependencies in Galician. We conduct a series of word prediction experiments in which we manipulate dependency length together with…

Computation and Language · Computer Science 2022-06-07 Iria de-Dios-Flores , Marcos Garcia

Standard transformer-based language models, while powerful for general text, often struggle with the fine-grained syntax and entity relationships in complex technical, engineering documents. To address this, we propose the Contextual Graph…

Computation and Language · Computer Science 2025-08-05 Karan Reddy , Mayukha Pal

While gender bias in modern Neural Machine Translation (NMT) systems has received much attention, traditional evaluation metrics do not to fully capture the extent to which these systems integrate contextual gender cues. We propose a novel…

Computation and Language · Computer Science 2025-05-14 Chiara Manna , Afra Alishahi , Frédéric Blain , Eva Vanmassenhove

Natural language understanding has recently seen a surge of progress with the use of sentence encoders like ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2019) which are pretrained on variants of language modeling. We conduct the…

The neural architectures of language models are becoming increasingly complex, especially that of Transformers, based on the attention mechanism. Although their application to numerous natural language processing tasks has proven to be very…

Computation and Language · Computer Science 2023-12-04 Pablo Gamallo

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

Recent studies have shown that the multi-encoder models are agnostic to the choice of context, and the context encoder generates noise which helps improve the models in terms of BLEU score. In this paper, we further explore this idea by…

Computation and Language · Computer Science 2023-08-14 Ramakrishna Appicharla , Baban Gain , Santanu Pal , Asif Ekbal

To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perform this integration in a predictable way across different…

Computation and Language · Computer Science 2024-06-18 Kevin Du , Vésteinn Snæbjarnarson , Niklas Stoehr , Jennifer C. White , Aaron Schein , Ryan Cotterell