English
Related papers

Related papers: Individual corpora predict fast memory retrieval d…

200 papers

We propose a new large-scale (nearly a million questions) ultra-long-context (more than 50,000 words average document length) reading comprehension dataset. Using GPT 3.5, we summarized each scene in 1,500 hand-curated fiction books from…

Computation and Language · Computer Science 2023-12-11 Arseny Moskvichev , Ky-Vinh Mai

Eye movement recordings from reading are one of the richest signals of human language processing. Corpora of eye movements during reading of contextualized running text is a way of making such records available for natural language…

Computation and Language · Computer Science 2022-04-29 Nora Hollenstein , Maria Barrett , Marina Björnsdóttir

Why do modern language models, trained to do well on next-word prediction, appear to generate coherent documents and capture long-range structure? Here we show that next-token prediction is provably powerful for learning longer-range…

Machine Learning · Computer Science 2025-12-09 Xinyuan Cao , Santosh S. Vempala

Multilingual acoustic models have been successfully applied to low-resource speech recognition. Most existing works have combined many small corpora together and pretrained a multilingual model by sampling from each corpus uniformly. The…

Computation and Language · Computer Science 2019-08-06 Xinjian Li , Siddharth Dalmia , Alan W. Black , Florian Metze

Previous works have evaluated memorization by comparing model outputs with training corpora, examining how factors such as data duplication, model size, and prompt length influence memorization. However, analyzing these extensive training…

Computation and Language · Computer Science 2024-06-18 Bo Li , Qinghua Zhao , Lijie Wen

We explore leveraging corpus-specific vocabularies that improve both efficiency and effectiveness of learned sparse retrieval systems. We find that pre-training the underlying BERT model on the target corpus, specifically targeting…

Information Retrieval · Computer Science 2024-01-15 Puxuan Yu , Antonio Mallia , Matthias Petri

In information retrieval (IR) systems, trends and users' interests may change over time, altering either the distribution of requests or contents to be recommended. Since neural ranking approaches heavily depend on the training data, it is…

Information Retrieval · Computer Science 2022-01-11 Thomas Gerald , Laure Soulier

We present a novel corpus of 445 human- and computer-generated documents, comprising about 27,000 clauses, annotated for semantic clause types and coherence relations that allow for nuanced comparison of artificial and natural discourse…

Latent Semantic Analysis (LSA) and Word2vec are some of the most widely used word embeddings. Despite the popularity of these techniques, the precise mechanisms by which they acquire new semantic relations between words remain unclear. In…

Computation and Language · Computer Science 2019-01-23 Edgar Altszyler , Mariano Sigman , Diego Fernandez Slezak

The statistical study of human memory requires large-scale experiments, involving many stimuli conditions and test subjects. While this approach has proven to be quite fruitful for meaningless material such as random lists of words,…

Computation and Language · Computer Science 2024-11-26 Antonios Georgiou , Tankut Can , Mikhail Katkov , Misha Tsodyks

A lack of corpora has so far limited advances in integrating human gaze data as a supervisory signal in neural attention mechanisms for natural language processing(NLP). We propose a novel hybrid text saliency model(TSM) that, for the first…

Computation and Language · Computer Science 2020-10-28 Ekta Sood , Simon Tannert , Philipp Mueller , Andreas Bulling

BACKGROUND: The amount of biomedical literature is rapidly growing and it is becoming increasingly difficult to keep manually curated knowledge bases and ontologies up-to-date. In this study we applied the word2vec deep learning toolkit to…

Computation and Language · Computer Science 2015-02-13 Jose Antonio Miñarro-Giménez , Oscar Marín-Alonso , Matthias Samwald

We present a system that allows life-science researchers to search a linguistically annotated corpus of scientific texts using patterns over dependency graphs, as well as using patterns over token sequences and a powerful variant of boolean…

Computation and Language · Computer Science 2020-06-09 Hillel Taub-Tabib , Micah Shlain , Shoval Sadde , Dan Lahav , Matan Eyal , Yaara Cohen , Yoav Goldberg

Recently, much progress has been made in learning general-purpose sentence representations that can be used across domains. However, most of the existing models typically treat each word in a sentence equally. In contrast, extensive studies…

Computation and Language · Computer Science 2017-05-10 Shaonan Wang , Jiajun Zhang , Chengqing Zong

In this paper we describe an approach to automatic evaluation of both the speech recognition and understanding capabilities of a spoken dialogue system for train time table information. We use word accuracy for recognition and concept…

cmp-lg · Computer Science 2008-02-03 M. Boros , W. Eckert , F. Gallwitz , G. Goerz , G. Hanrieder , H. Niemann

A common practice in Natural Language Processing (NLP) is to visualize the text corpus without reading through the entire literature, still grasping the central idea and key points described. For a long time, researchers focused on…

Computation and Language · Computer Science 2022-07-29 Suvi Varshney , Divjeet Singh Jas

We propose a two-stage neural model to tackle question generation from documents. First, our model estimates the probability that word sequences in a document are ones that a human would pick when selecting candidate answers by training a…

Computation and Language · Computer Science 2018-05-31 Sandeep Subramanian , Tong Wang , Xingdi Yuan , Saizheng Zhang , Yoshua Bengio , Adam Trischler

Large language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although…

Computation and Language · Computer Science 2025-06-16 Sabri Eyuboglu , Ryan Ehrlich , Simran Arora , Neel Guha , Dylan Zinsley , Emily Liu , Will Tennien , Atri Rudra , James Zou , Azalia Mirhoseini , Christopher Re

The task of discovering topics in text corpora has been dominated by Latent Dirichlet Allocation and other Topic Models for over a decade. In order to apply these approaches to massive text corpora, the vocabulary needs to be reduced…

Computation and Language · Computer Science 2019-08-08 Gibran Fuentes-Pineda , Ivan Vladimir Meza-Ruiz

The forgetting curve has been extensively explored by psychologists, educationalists and cognitive scientists alike. In the context of Intelligent Tutoring Systems, modelling the forgetting curve for each user and knowledge component (e.g.…

Computation and Language · Computer Science 2020-04-24 Ahmed Zaidi , Andrew Caines , Russell Moore , Paula Buttery , Andrew Rice