English
Related papers

Related papers: Representation Degeneration Problem in Training Na…

200 papers

Using pre-trained word embeddings as input layer is a common practice in many natural language processing (NLP) tasks, but it is largely neglected for neural machine translation (NMT). In this paper, we conducted a systematic analysis on…

Computation and Language · Computer Science 2018-06-15 Shuoyang Ding , Kevin Duh

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Computation and Language · Computer Science 2023-05-26 Francesco Fusco , Diego Antognini

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for simple, surface-level textual relations over full semantic complexity of the problem. This proposal investigates a…

Computation and Language · Computer Science 2022-06-20 Michal Štefánik

Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the Embedded Topic…

Information Retrieval · Computer Science 2019-07-12 Adji B. Dieng , Francisco J. R. Ruiz , David M. Blei

Dialogue act recognition is an important component of a large number of natural language processing pipelines. Many research works have been carried out in this area, but relatively few investigate deep neural networks and word embeddings.…

Computation and Language · Computer Science 2020-10-23 Christophe Cerisara , Pavel Kral , Ladislav Lenc

Text normalization is an important enabling technology for several NLP tasks. Recently, neural-network-based approaches have outperformed well-established models in this task. However, in languages other than English, there has been little…

Computation and Language · Computer Science 2018-09-06 Daniel Watson , Nasser Zalmout , Nizar Habash

Word embeddings improve the performance of NLP systems by revealing the hidden structural relationships between words. Despite their success in many applications, word embeddings have seen very little use in computational social science NLP…

Computation and Language · Computer Science 2018-02-21 James Foulds

Word embeddings resulting from neural language models have been shown to be successful for a large variety of NLP tasks. However, such architecture might be difficult to train and time-consuming. Instead, we propose to drastically simplify…

Computation and Language · Computer Science 2017-01-05 Rémi Lebret , Ronan Collobert

Modern natural language understanding models depend on pretrained subword embeddings, but applications may need to reason about words that were never or rarely seen during pretraining. We show that examples that depend critically on a rarer…

Computation and Language · Computer Science 2021-03-08 Christopher Malon

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Information Retrieval · Computer Science 2023-11-21 Tong Wu , Yulei Qin , Enwei Zhang , Zihan Xu , Yuting Gao , Ke Li , Xing Sun

This work analyses the text memorization behavior of large language models (LLMs) when subjected to nucleus sampling. Stochastic decoding methods like nucleus sampling are typically applied to overcome issues such as monotonous and…

Computation and Language · Computer Science 2024-08-30 Luka Borec , Philipp Sadler , David Schlangen

Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…

Computation and Language · Computer Science 2021-09-22 Giulio Zhou , Gerasimos Lampouras

Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.) depending on the notion of context defined at training time. These properties manifest…

Computation and Language · Computer Science 2020-11-06 Jingyi He , KC Tsiolis , Kian Kenyon-Dean , Jackie Chi Kit Cheung

Neural approaches to program synthesis and understanding have proliferated widely in the last few years; at the same time graph based neural networks have become a promising new tool. This work aims to be the first empirical study comparing…

Software Engineering · Computer Science 2020-01-28 Austin P. Wright , Herbert Wiklicky

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…

Computation and Language · Computer Science 2021-12-13 Lei Ding , Dengdeng Yu , Jinhan Xie , Wenxing Guo , Shenggang Hu , Meichen Liu , Linglong Kong , Hongsheng Dai , Yanchun Bao , Bei Jiang

Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be…

Computation and Language · Computer Science 2020-08-21 Nishant Subramani , Nivedita Suresh

Graphs or networks are a very convenient way to represent data with lots of interaction. Recently, Machine Learning on Graph data has gained a lot of traction. In particular, vertex classification and missing edge detection have very…

Machine Learning · Computer Science 2020-09-07 Simon Brandeis , Adrian Jarret , Pierre Sevestre

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-16 Hejung Yang , Hong-Goo Kang

Deep learning uses neural networks which are parameterised by their weights. The neural networks are usually trained by tuning the weights to directly minimise a given loss function. In this paper we propose to re-parameterise the weights…

Neural and Evolutionary Computing · Computer Science 2022-03-14 Michael Fairbank , Spyridon Samothrakis , Luca Citi

This study addresses the problem of identifying the meaning of unknown words or entities in a discourse with respect to the word embedding approaches used in neural language models. We proposed a method for on-the-fly construction and…

Computation and Language · Computer Science 2017-10-18 Sosuke Kobayashi , Naoaki Okazaki , Kentaro Inui