中文
相关论文

相关论文: Diverging Transformer Predictions for Human Senten…

200 篇论文

Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…

计算与语言 · 计算机科学 2020-10-09 Satwik Bhattamishra , Kabir Ahuja , Navin Goyal

Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based…

Recent psycholinguistic research has compared human reading times to surprisal estimates from language models to study the factors shaping human sentence processing difficulty. Previous studies have shown a strong fit between surprisal…

计算与语言 · 计算机科学 2024-09-18 Christian Clark , Byung-Doh Oh , William Schuler

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

计算与语言 · 计算机科学 2022-05-17 Gerard Sant , Gerard I. Gállego , Belen Alastruey , Marta R. Costa-Jussà

The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract…

计算与语言 · 计算机科学 2021-07-05 Yu Shi

Transformers have demonstrated remarkable performance in natural language processing and related domains, as they largely focus on sequential, autoregressive next-token prediction tasks. Yet, they struggle in logical reasoning, not…

人工智能 · 计算机科学 2025-10-08 Renee Ge , Qianli Liao , Tomaso Poggio

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpected observation - has…

计算与语言 · 计算机科学 2022-03-24 Nathan Young , Qiming Bao , Joshua Bensemann , Michael Witbrock

The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine Translation (NMT). Though…

计算与语言 · 计算机科学 2020-06-26 Hongfei Xu , Josef van Genabith , Deyi Xiong , Qiuhui Liu , Jingyi Zhang

Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of common sense reasoning ability. We show, however, with a new diagnostic…

计算与语言 · 计算机科学 2020-05-08 Mostafa Abdou , Vinit Ravishankar , Maria Barrett , Yonatan Belinkov , Desmond Elliott , Anders Søgaard

We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are…

计算与语言 · 计算机科学 2022-12-07 Laurent Sartran , Samuel Barrett , Adhiguna Kuncoro , Miloš Stanojević , Phil Blunsom , Chris Dyer

Interpreting the effects of variants within the human genome and proteome is essential for analysing disease risk, predicting medication response, and developing personalised health interventions. Due to the intrinsic similarities between…

计算与语言 · 计算机科学 2025-03-17 Megha Hegde , Jean-Christophe Nebel , Farzana Rahman

The transformers have achieved significant accomplishments in the natural language processing as its outstanding parallel processing capabilities and highly flexible attention mechanism. In addition, increasing studies based on transformers…

计算与语言 · 计算机科学 2024-07-19 Wei Lan , Guohang He , Mingyang Liu , Qingfeng Chen , Junyue Cao , Wei Peng

Large language models (LLMs) achieve remarkable fluency across linguistic and reasoning tasks but remain systematically prone to hallucination. Prevailing accounts attribute hallucinations to data gaps, limited context, or optimization…

计算机与社会 · 计算机科学 2025-09-23 Richard Ackermann , Simeon Emanuilov

The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts. However, to date, summarizers can fail on fusing sentences. They tend to produce few summary…

计算与语言 · 计算机科学 2020-10-09 Logan Lebanoff , Franck Dernoncourt , Doo Soon Kim , Lidan Wang , Walter Chang , Fei Liu

Many recent works have demonstrated that unsupervised sentence representations of neural networks encode syntactic information by observing that neural language models are able to predict the agreement between a verb and its subject. We…

计算与语言 · 计算机科学 2021-09-22 Bingzhi Li , Guillaume Wisniewski , Benoit Crabbé

We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with the Transformer English-German translation model. We…

计算与语言 · 计算机科学 2022-11-04 Gal Patel , Leshem Choshen , Omri Abend

We conduct a systematic study of the approximation properties of Transformer for sequence modeling with long, sparse and complicated memory. We investigate the mechanisms through which different components of Transformer, such as the…

机器学习 · 计算机科学 2024-10-31 Mingze Wang , Weinan E

Transformer language models have received widespread public attention, yet their generated text is often surprising even to NLP researchers. In this survey, we discuss over 250 recent studies of English language model behavior before…

计算与语言 · 计算机科学 2023-08-29 Tyler A. Chang , Benjamin K. Bergen

Representation of linguistic phenomena in computational language models is typically assessed against the predictions of existing linguistic theories of these phenomena. Using the notion of polarity as a case study, we show that this is not…

计算与语言 · 计算机科学 2022-03-21 Lisa Bylinina , Alexey Tikhonov

Transformer based models are the modern work horses for neural machine translation (NMT), reaching state of the art across several benchmarks. Despite their impressive accuracy, we observe a systemic and rudimentary class of errors made by…

计算与语言 · 计算机科学 2021-04-19 Adithya Renduchintala , Adina Williams